Token | the |
Token ID | 262 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
cffff | +0.232 |
jri | +0.205 |
uberty | +0.197 |
odied | +0.189 |
attled | +0.179 |
Neg logit contributions | |
Parenthood | -0.207 |
mination | -0.206 |
ILA | -0.200 |
FTA | -0.189 |
buster | -0.186 |
Token | prime |
Token ID | 6994 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
cffff | +0.204 |
jri | +0.180 |
uberty | +0.172 |
odied | +0.165 |
attled | +0.155 |
Neg logit contributions | |
Parenthood | -0.203 |
mination | -0.203 |
ILA | -0.198 |
FTA | -0.187 |
buster | -0.184 |
Token | challenge |
Token ID | 4427 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Parenthood | +0.286 |
mination | +0.284 |
ILA | +0.276 |
FTA | +0.262 |
buster | +0.258 |
Neg logit contributions | |
cffff | -0.320 |
jri | -0.283 |
uberty | -0.272 |
odied | -0.261 |
attled | -0.247 |
Token | Belfast |
Token ID | 29713 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
cffff | +0.229 |
jri | +0.205 |
uberty | +0.198 |
odied | +0.190 |
attled | +0.181 |
Neg logit contributions | |
Parenthood | -0.174 |
mination | -0.173 |
ILA | -0.168 |
FTA | -0.158 |
buster | -0.155 |
Token | Te |
Token ID | 6767 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
cffff | +1.675 |
jri | +1.470 |
uberty | +1.410 |
odied | +1.349 |
attled | +1.270 |
Neg logit contributions | |
Parenthood | -1.681 |
mination | -1.669 |
ILA | -1.627 |
FTA | -1.548 |
buster | -1.524 |
Token | legraph |
Token ID | 16606 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Parenthood | +0.299 |
mination | +0.296 |
ILA | +0.289 |
FTA | +0.278 |
buster | +0.273 |
Neg logit contributions | |
cffff | -0.229 |
jri | -0.197 |
uberty | -0.189 |
odied | -0.179 |
urses | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
cffff | +2.859 |
jri | +2.488 |
uberty | +2.409 |
odied | +2.320 |
attled | +2.165 |
Neg logit contributions | |
mination | -3.010 |
Parenthood | -2.950 |
ILA | -2.907 |
FTA | -2.737 |
buster | -2.709 |
Token | co |
Token ID | 1073 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
cffff | +0.467 |
jri | +0.422 |
uberty | +0.406 |
odied | +0.399 |
urses | +0.382 |
Neg logit contributions | |
mination | -0.255 |
Parenthood | -0.255 |
ILA | -0.248 |
FTA | -0.230 |
buster | -0.224 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Parenthood | +0.599 |
mination | +0.595 |
ILA | +0.579 |
FTA | +0.548 |
buster | +0.539 |
Neg logit contributions | |
cffff | -0.701 |
jri | -0.623 |
uberty | -0.599 |
odied | -0.575 |
attled | -0.544 |
Token | uk |
Token ID | 2724 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
cffff | +0.336 |
jri | +0.292 |
uberty | +0.277 |
odied | +0.265 |
attled | +0.246 |
Neg logit contributions | |
Parenthood | -0.419 |
mination | -0.416 |
ILA | -0.405 |
FTA | -0.389 |
buster | -0.384 |
Token | Dis |
Token ID | 3167 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
cffff | +0.330 |
jri | +0.292 |
uberty | +0.281 |
odied | +0.271 |
attled | +0.255 |
Neg logit contributions | |
Parenthood | -0.306 |
mination | -0.306 |
ILA | -0.298 |
FTA | -0.280 |
buster | -0.278 |
Token | it |
Token ID | 340 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
cffff | +0.663 |
jri | +0.595 |
uberty | +0.574 |
odied | +0.554 |
attled | +0.526 |
Neg logit contributions | |
Parenthood | -0.478 |
mination | -0.474 |
ILA | -0.460 |
FTA | -0.433 |
buster | -0.425 |
Token | to |
Token ID | 284 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
cffff | +0.136 |
jri | +0.123 |
uberty | +0.119 |
odied | +0.115 |
attled | +0.110 |
Neg logit contributions | |
Parenthood | -0.087 |
mination | -0.087 |
ILA | -0.084 |
FTA | -0.078 |
buster | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Parenthood | +0.035 |
mination | +0.035 |
ILA | +0.034 |
FTA | +0.032 |
buster | +0.031 |
Neg logit contributions | |
cffff | -0.043 |
jri | -0.039 |
uberty | -0.037 |
odied | -0.036 |
attled | -0.034 |
Token | peer |
Token ID | 12720 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
cffff | +0.150 |
jri | +0.133 |
uberty | +0.127 |
odied | +0.122 |
attled | +0.115 |
Neg logit contributions | |
Parenthood | -0.146 |
mination | -0.145 |
ILA | -0.141 |
FTA | -0.134 |
buster | -0.132 |
Token | review |
Token ID | 2423 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
cffff | +1.456 |
jri | +1.309 |
uberty | +1.265 |
odied | +1.220 |
attled | +1.163 |
Neg logit contributions | |
Parenthood | -0.994 |
mination | -0.983 |
ILA | -0.952 |
FTA | -0.895 |
buster | -0.878 |
Token | journal |
Token ID | 3989 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
cffff | +1.308 |
jri | +1.156 |
uberty | +1.109 |
odied | +1.063 |
attled | +1.004 |
Neg logit contributions | |
Parenthood | -1.241 |
mination | -1.229 |
ILA | -1.198 |
FTA | -1.136 |
buster | -1.119 |
Token | . |
Token ID | 13 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
cffff | +3.093 |
jri | +2.756 |
uberty | +2.657 |
odied | +2.557 |
attled | +2.420 |
Neg logit contributions | |
Parenthood | -2.551 |
mination | -2.530 |
ILA | -2.463 |
FTA | -2.322 |
buster | -2.284 |
Token |
|
Token ID | 198 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
cffff | +0.558 |
jri | +0.500 |
uberty | +0.484 |
odied | +0.464 |
attled | +0.438 |
Neg logit contributions | |
Parenthood | -0.465 |
mination | -0.463 |
ILA | -0.450 |
FTA | -0.424 |
buster | -0.420 |
Token |
|
Token ID | 198 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
cffff | +0.566 |
jri | +0.507 |
uberty | +0.488 |
odied | +0.472 |
urses | +0.447 |
Neg logit contributions | |
Parenthood | -0.478 |
mination | -0.478 |
ILA | -0.464 |
FTA | -0.437 |
buster | -0.428 |
Token | I |
Token ID | 40 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
cffff | +0.649 |
jri | +0.586 |
uberty | +0.566 |
odied | +0.547 |
attled | +0.522 |
Neg logit contributions | |
Parenthood | -0.413 |
mination | -0.408 |
ILA | -0.394 |
FTA | -0.371 |
buster | -0.363 |
Token | think |
Token ID | 892 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
cffff | +0.319 |
jri | +0.283 |
uberty | +0.272 |
odied | +0.262 |
attled | +0.248 |
Neg logit contributions | |
Parenthood | -0.276 |
mination | -0.273 |
ILA | -0.265 |
FTA | -0.252 |
buster | -0.247 |
Token | www |
Token ID | 2503 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
Parenthood | +0.211 |
mination | +0.209 |
ILA | +0.203 |
FTA | +0.191 |
buster | +0.188 |
Neg logit contributions | |
cffff | -0.280 |
jri | -0.250 |
uberty | -0.241 |
odied | -0.232 |
attled | -0.221 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
cffff | +0.066 |
jri | +0.059 |
uberty | +0.056 |
odied | +0.054 |
urses | +0.051 |
Neg logit contributions | |
Parenthood | -0.066 |
mination | -0.066 |
ILA | -0.065 |
FTA | -0.061 |
buster | -0.059 |
Token | bel |
Token ID | 6667 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
cffff | +0.234 |
jri | +0.207 |
uberty | +0.200 |
odied | +0.191 |
attled | +0.180 |
Neg logit contributions | |
mination | -0.210 |
Parenthood | -0.209 |
ILA | -0.201 |
FTA | -0.192 |
buster | -0.192 |
Token | fast |
Token ID | 7217 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
cffff | +0.419 |
jri | +0.370 |
uberty | +0.355 |
odied | +0.340 |
attled | +0.321 |
Neg logit contributions | |
Parenthood | -0.383 |
mination | -0.381 |
ILA | -0.370 |
FTA | -0.352 |
buster | -0.347 |
Token | te |
Token ID | 660 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
cffff | +0.589 |
jri | +0.517 |
uberty | +0.497 |
odied | +0.476 |
attled | +0.450 |
Neg logit contributions | |
Parenthood | -0.570 |
mination | -0.564 |
ILA | -0.550 |
FTA | -0.524 |
buster | -0.514 |
Token | legraph |
Token ID | 16606 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Parenthood | +0.499 |
mination | +0.494 |
ILA | +0.484 |
FTA | +0.463 |
buster | +0.451 |
Neg logit contributions | |
cffff | -0.364 |
jri | -0.311 |
uberty | -0.299 |
odied | -0.284 |
attled | -0.264 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
cffff | +2.588 |
jri | +2.290 |
uberty | +2.176 |
odied | +2.092 |
attled | +1.977 |
Neg logit contributions | |
Parenthood | -2.825 |
mination | -2.815 |
ILA | -2.762 |
FTA | -2.599 |
buster | -2.526 |
Token | co |
Token ID | 1073 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
cffff | +0.098 |
jri | +0.089 |
uberty | +0.086 |
odied | +0.083 |
attled | +0.080 |
Neg logit contributions | |
Parenthood | -0.051 |
mination | -0.051 |
ILA | -0.049 |
FTA | -0.046 |
buster | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +9.20e-02 |
Pos logit contributions | |
Parenthood | +0.526 |
mination | +0.522 |
ILA | +0.509 |
FTA | +0.482 |
buster | +0.473 |
Neg logit contributions | |
cffff | -0.603 |
jri | -0.536 |
uberty | -0.515 |
odied | -0.495 |
attled | -0.468 |
Token | uk |
Token ID | 2724 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
cffff | +0.086 |
jri | +0.075 |
uberty | +0.071 |
odied | +0.068 |
attled | +0.063 |
Neg logit contributions | |
Parenthood | -0.103 |
mination | -0.102 |
ILA | -0.100 |
FTA | -0.095 |
buster | -0.094 |
Token | / |
Token ID | 14 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
cffff | +0.203 |
jri | +0.183 |
uberty | +0.177 |
odied | +0.171 |
attled | +0.163 |
Neg logit contributions | |
mination | -0.139 |
Parenthood | -0.138 |
ILA | -0.134 |
FTA | -0.125 |
buster | -0.122 |
Token | in |
Token ID | 287 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
cffff | +0.523 |
jri | +0.468 |
uberty | +0.451 |
odied | +0.435 |
attled | +0.414 |
Neg logit contributions | |
Parenthood | -0.382 |
mination | -0.379 |
ILA | -0.367 |
FTA | -0.348 |
buster | -0.342 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
cffff | +0.053 |
jri | +0.047 |
uberty | +0.045 |
odied | +0.044 |
attled | +0.041 |
Neg logit contributions | |
Parenthood | -0.044 |
mination | -0.043 |
ILA | -0.042 |
FTA | -0.040 |
buster | -0.039 |
Token | peer |
Token ID | 12720 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
cffff | +0.140 |
jri | +0.118 |
uberty | +0.112 |
odied | +0.105 |
attled | +0.097 |
Neg logit contributions | |
Parenthood | -0.213 |
mination | -0.211 |
ILA | -0.207 |
FTA | -0.200 |
buster | -0.196 |
Token | - |
Token ID | 12 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
cffff | +1.239 |
jri | +1.116 |
uberty | +1.080 |
odied | +1.044 |
attled | +0.996 |
Neg logit contributions | |
Parenthood | -0.774 |
mination | -0.766 |
ILA | -0.741 |
FTA | -0.695 |
buster | -0.681 |
Token | reviewed |
Token ID | 32974 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
cffff | +0.288 |
jri | +0.250 |
uberty | +0.239 |
odied | +0.227 |
attled | +0.213 |
Neg logit contributions | |
Parenthood | -0.340 |
mination | -0.336 |
ILA | -0.328 |
FTA | -0.314 |
buster | -0.309 |
Token | journal |
Token ID | 3989 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
cffff | +1.330 |
jri | +1.118 |
uberty | +1.055 |
odied | +0.991 |
attled | +0.908 |
Neg logit contributions | |
Parenthood | -2.177 |
mination | -2.166 |
ILA | -2.122 |
FTA | -2.041 |
buster | -2.017 |
Token | Clim |
Token ID | 28573 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
cffff | +2.771 |
jri | +2.457 |
uberty | +2.365 |
odied | +2.268 |
attled | +2.133 |
Neg logit contributions | |
Parenthood | -2.612 |
mination | -2.609 |
ILA | -2.546 |
FTA | -2.405 |
buster | -2.379 |
Token | atic |
Token ID | 1512 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
cffff | +1.593 |
jri | +1.414 |
uberty | +1.353 |
odied | +1.304 |
attled | +1.230 |
Neg logit contributions | |
Parenthood | -1.450 |
mination | -1.429 |
ILA | -1.395 |
FTA | -1.329 |
buster | -1.305 |
Token | Change |
Token ID | 9794 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Parenthood | +0.149 |
mination | +0.146 |
ILA | +0.143 |
FTA | +0.136 |
buster | +0.135 |
Neg logit contributions | |
cffff | -0.147 |
jri | -0.129 |
uberty | -0.124 |
odied | -0.118 |
attled | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
cffff | +1.830 |
jri | +1.631 |
uberty | +1.573 |
odied | +1.514 |
attled | +1.437 |
Neg logit contributions | |
Parenthood | -1.418 |
mination | -1.406 |
ILA | -1.365 |
FTA | -1.291 |
buster | -1.269 |
Token | provides |
Token ID | 3769 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
cffff | +0.271 |
jri | +0.240 |
uberty | +0.231 |
odied | +0.222 |
attled | +0.209 |
Neg logit contributions | |
Parenthood | -0.247 |
mination | -0.246 |
ILA | -0.239 |
FTA | -0.227 |
buster | -0.223 |
Token | Le |
Token ID | 1004 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
Parenthood | +0.205 |
mination | +0.204 |
ILA | +0.198 |
FTA | +0.188 |
buster | +0.185 |
Neg logit contributions | |
cffff | -0.237 |
jri | -0.209 |
uberty | -0.202 |
odied | -0.194 |
attled | -0.183 |
Token | a |
Token ID | 64 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
Parenthood | +0.560 |
mination | +0.556 |
ILA | +0.537 |
FTA | +0.506 |
buster | +0.490 |
Neg logit contributions | |
cffff | -0.937 |
jri | -0.852 |
uberty | -0.821 |
odied | -0.800 |
attled | -0.762 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
cffff | +0.003 |
jri | +0.003 |
uberty | +0.003 |
odied | +0.003 |
urses | +0.003 |
Neg logit contributions | |
mination | -0.002 |
Parenthood | -0.002 |
ILA | -0.002 |
FTA | -0.001 |
buster | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
mination | +0.242 |
Parenthood | +0.239 |
ILA | +0.235 |
FTA | +0.219 |
buster | +0.217 |
Neg logit contributions | |
cffff | -0.255 |
jri | -0.229 |
uberty | -0.219 |
odied | -0.211 |
urses | -0.199 |
Token | The |
Token ID | 383 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
mination | +0.211 |
Parenthood | +0.207 |
ILA | +0.204 |
FTA | +0.194 |
buster | +0.193 |
Neg logit contributions | |
cffff | -0.153 |
jri | -0.133 |
uberty | -0.126 |
odied | -0.121 |
attled | -0.112 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
cffff | +0.053 |
jri | +0.044 |
uberty | +0.041 |
odied | +0.038 |
attled | +0.035 |
Neg logit contributions | |
mination | -0.099 |
Parenthood | -0.099 |
ILA | -0.097 |
FTA | -0.093 |
buster | -0.092 |
Token | 15 |
Token ID | 1315 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
cffff | +3.129 |
jri | +2.828 |
uberty | +2.774 |
odied | +2.699 |
attled | +2.646 |
Neg logit contributions | |
mination | -1.966 |
ILA | -1.928 |
Parenthood | -1.874 |
buster | -1.687 |
FTA | -1.659 |
Token | of |
Token ID | 286 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
cffff | +0.046 |
jri | +0.042 |
uberty | +0.040 |
odied | +0.039 |
attled | +0.037 |
Neg logit contributions | |
mination | -0.032 |
Parenthood | -0.032 |
ILA | -0.031 |
FTA | -0.029 |
buster | -0.028 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
mination | +0.038 |
Parenthood | +0.037 |
ILA | +0.036 |
FTA | +0.033 |
buster | +0.033 |
Neg logit contributions | |
cffff | -0.072 |
jri | -0.065 |
uberty | -0.063 |
odied | -0.061 |
attled | -0.059 |
Token | Photo |
Token ID | 5555 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
cffff | +0.060 |
jri | +0.054 |
uberty | +0.053 |
odied | +0.051 |
attled | +0.048 |
Neg logit contributions | |
Parenthood | -0.039 |
mination | -0.039 |
ILA | -0.038 |
FTA | -0.035 |
buster | -0.035 |
Token | : |
Token ID | 25 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
mination | +0.664 |
Parenthood | +0.661 |
ILA | +0.645 |
FTA | +0.606 |
buster | +0.599 |
Neg logit contributions | |
cffff | -0.635 |
jri | -0.563 |
uberty | -0.534 |
odied | -0.518 |
attled | -0.488 |
Token | www |
Token ID | 2503 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
Parenthood | +0.466 |
mination | +0.460 |
ILA | +0.449 |
FTA | +0.423 |
buster | +0.414 |
Neg logit contributions | |
cffff | -0.603 |
jri | -0.540 |
uberty | -0.520 |
odied | -0.500 |
attled | -0.475 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
mination | +0.030 |
Parenthood | +0.030 |
ILA | +0.029 |
FTA | +0.027 |
buster | +0.027 |
Neg logit contributions | |
cffff | -0.030 |
jri | -0.026 |
uberty | -0.025 |
odied | -0.024 |
urses | -0.023 |
Token | bel |
Token ID | 6667 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
mination | +0.115 |
Parenthood | +0.115 |
ILA | +0.111 |
FTA | +0.106 |
buster | +0.105 |
Neg logit contributions | |
cffff | -0.127 |
jri | -0.112 |
uberty | -0.108 |
odied | -0.103 |
attled | -0.097 |
Token | fast |
Token ID | 7217 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
cffff | +0.493 |
jri | +0.436 |
uberty | +0.418 |
odied | +0.400 |
attled | +0.378 |
Neg logit contributions | |
Parenthood | -0.470 |
mination | -0.465 |
ILA | -0.456 |
FTA | -0.431 |
buster | -0.424 |
Token | te |
Token ID | 660 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
cffff | +0.504 |
jri | +0.443 |
uberty | +0.425 |
odied | +0.407 |
attled | +0.385 |
Neg logit contributions | |
Parenthood | -0.496 |
mination | -0.491 |
ILA | -0.481 |
FTA | -0.456 |
buster | -0.447 |
Token | legraph |
Token ID | 16606 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Parenthood | +0.678 |
mination | +0.671 |
ILA | +0.658 |
FTA | +0.630 |
buster | +0.618 |
Neg logit contributions | |
cffff | -0.533 |
jri | -0.461 |
uberty | -0.439 |
odied | -0.417 |
attled | -0.388 |
Token | . |
Token ID | 13 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
cffff | +2.448 |
jri | +2.177 |
uberty | +2.060 |
odied | +1.985 |
attled | +1.876 |
Neg logit contributions | |
Parenthood | -2.697 |
mination | -2.688 |
ILA | -2.624 |
FTA | -2.471 |
buster | -2.409 |
Token | co |
Token ID | 1073 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
Parenthood | +0.145 |
mination | +0.144 |
ILA | +0.139 |
FTA | +0.129 |
buster | +0.125 |
Neg logit contributions | |
cffff | -0.270 |
jri | -0.247 |
uberty | -0.237 |
odied | -0.231 |
attled | -0.221 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Parenthood | +0.595 |
mination | +0.592 |
ILA | +0.577 |
FTA | +0.545 |
buster | +0.536 |
Neg logit contributions | |
cffff | -0.664 |
jri | -0.591 |
uberty | -0.566 |
odied | -0.545 |
attled | -0.515 |
Token | uk |
Token ID | 2724 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Parenthood | +0.174 |
mination | +0.173 |
ILA | +0.169 |
FTA | +0.161 |
buster | +0.159 |
Neg logit contributions | |
cffff | -0.143 |
jri | -0.125 |
uberty | -0.119 |
odied | -0.114 |
attled | -0.106 |
Token | / |
Token ID | 14 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
cffff | +0.160 |
jri | +0.145 |
uberty | +0.140 |
odied | +0.135 |
attled | +0.129 |
Neg logit contributions | |
Parenthood | -0.110 |
mination | -0.110 |
ILA | -0.106 |
FTA | -0.099 |
buster | -0.097 |
Token | Le |
Token ID | 1004 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Parenthood | +0.212 |
mination | +0.210 |
ILA | +0.205 |
FTA | +0.195 |
buster | +0.192 |
Neg logit contributions | |
cffff | -0.235 |
jri | -0.208 |
uberty | -0.200 |
odied | -0.192 |
attled | -0.181 |
Token | a |
Token ID | 64 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Parenthood | +0.522 |
mination | +0.518 |
ILA | +0.500 |
FTA | +0.471 |
buster | +0.457 |
Neg logit contributions | |
cffff | -0.873 |
jri | -0.794 |
uberty | -0.764 |
odied | -0.745 |
attled | -0.710 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
mination | +0.012 |
Parenthood | +0.012 |
ILA | +0.012 |
FTA | +0.011 |
buster | +0.011 |
Neg logit contributions | |
cffff | -0.027 |
jri | -0.025 |
uberty | -0.024 |
odied | -0.023 |
urses | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
mination | +0.259 |
Parenthood | +0.255 |
ILA | +0.251 |
FTA | +0.234 |
buster | +0.231 |
Neg logit contributions | |
cffff | -0.273 |
jri | -0.245 |
uberty | -0.234 |
odied | -0.226 |
urses | -0.213 |
Token | The |
Token ID | 383 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
mination | +0.224 |
Parenthood | +0.220 |
ILA | +0.217 |
FTA | +0.206 |
buster | +0.205 |
Neg logit contributions | |
cffff | -0.163 |
jri | -0.142 |
uberty | -0.135 |
odied | -0.130 |
attled | -0.119 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
cffff | +0.055 |
jri | +0.046 |
uberty | +0.042 |
odied | +0.040 |
attled | +0.036 |
Neg logit contributions | |
mination | -0.102 |
Parenthood | -0.101 |
ILA | -0.100 |
FTA | -0.095 |
buster | -0.095 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
cffff | +2.993 |
jri | +2.774 |
uberty | +2.668 |
odied | +2.590 |
urses | +2.490 |
Neg logit contributions | |
mination | -2.066 |
ILA | -2.034 |
Parenthood | -2.012 |
FTA | -1.822 |
buster | -1.794 |
Token | of |
Token ID | 286 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
cffff | +0.021 |
jri | +0.019 |
uberty | +0.018 |
odied | +0.018 |
attled | +0.017 |
Neg logit contributions | |
mination | -0.014 |
Parenthood | -0.014 |
ILA | -0.014 |
FTA | -0.013 |
buster | -0.013 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
mination | +0.033 |
Parenthood | +0.032 |
ILA | +0.031 |
FTA | +0.028 |
buster | +0.028 |
Neg logit contributions | |
cffff | -0.060 |
jri | -0.054 |
uberty | -0.052 |
odied | -0.051 |
attled | -0.049 |
Token | Photo |
Token ID | 5555 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
cffff | +0.055 |
jri | +0.050 |
uberty | +0.048 |
odied | +0.047 |
attled | +0.044 |
Neg logit contributions | |
mination | -0.041 |
Parenthood | -0.041 |
ILA | -0.040 |
buster | -0.037 |
FTA | -0.037 |
Token | : |
Token ID | 25 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
mination | +0.698 |
Parenthood | +0.697 |
ILA | +0.679 |
FTA | +0.638 |
buster | +0.631 |
Neg logit contributions | |
cffff | -0.665 |
jri | -0.589 |
uberty | -0.559 |
odied | -0.541 |
attled | -0.510 |
Token | with |
Token ID | 351 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
cffff | +0.010 |
jri | +0.009 |
uberty | +0.009 |
odied | +0.008 |
attled | +0.008 |
Neg logit contributions | |
Parenthood | -0.008 |
mination | -0.008 |
ILA | -0.008 |
FTA | -0.007 |
buster | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Parenthood | +0.314 |
mination | +0.311 |
ILA | +0.304 |
FTA | +0.289 |
buster | +0.283 |
Neg logit contributions | |
cffff | -0.346 |
jri | -0.306 |
uberty | -0.295 |
odied | -0.283 |
attled | -0.266 |
Token | � |
Token ID | 564 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
Parenthood | +0.180 |
mination | +0.179 |
ILA | +0.174 |
FTA | +0.165 |
buster | +0.164 |
Neg logit contributions | |
cffff | -0.173 |
jri | -0.152 |
uberty | -0.145 |
odied | -0.138 |
attled | -0.130 |
Token | � |
Token ID | 250 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
cffff | +0.132 |
jri | +0.120 |
uberty | +0.117 |
odied | +0.114 |
attled | +0.109 |
Neg logit contributions | |
Parenthood | -0.055 |
mination | -0.054 |
ILA | -0.052 |
FTA | -0.047 |
buster | -0.046 |
Token | Que |
Token ID | 15681 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Parenthood | +0.354 |
mination | +0.351 |
ILA | +0.341 |
FTA | +0.323 |
buster | +0.318 |
Neg logit contributions | |
cffff | -0.430 |
jri | -0.382 |
uberty | -0.368 |
odied | -0.354 |
attled | -0.335 |
Token | bec |
Token ID | 9423 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
cffff | +0.139 |
jri | +0.121 |
uberty | +0.115 |
odied | +0.110 |
attled | +0.103 |
Neg logit contributions | |
Parenthood | -0.164 |
mination | -0.163 |
ILA | -0.159 |
FTA | -0.152 |
buster | -0.150 |
Token | - |
Token ID | 12 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
cffff | +2.795 |
jri | +2.478 |
uberty | +2.359 |
odied | +2.266 |
attled | +2.152 |
Neg logit contributions | |
Parenthood | -2.482 |
mination | -2.477 |
ILA | -2.379 |
FTA | -2.246 |
buster | -2.221 |
Token | b |
Token ID | 65 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
cffff | +0.302 |
jri | +0.269 |
uberty | +0.259 |
odied | +0.249 |
attled | +0.236 |
Neg logit contributions | |
Parenthood | -0.244 |
mination | -0.242 |
ILA | -0.235 |
FTA | -0.223 |
buster | -0.218 |
Token | ashing |
Token ID | 2140 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
cffff | +0.180 |
jri | +0.150 |
uberty | +0.141 |
odied | +0.130 |
icter | +0.118 |
Neg logit contributions | |
mination | -0.321 |
Parenthood | -0.320 |
ILA | -0.313 |
FTA | -0.302 |
buster | -0.300 |
Token | � |
Token ID | 447 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
cffff | +1.607 |
jri | +1.432 |
uberty | +1.362 |
odied | +1.309 |
attled | +1.252 |
Neg logit contributions | |
mination | -1.351 |
Parenthood | -1.350 |
ILA | -1.293 |
FTA | -1.221 |
buster | -1.206 |
Token | � |
Token ID | 251 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Parenthood | +0.025 |
mination | +0.025 |
ILA | +0.024 |
FTA | +0.022 |
buster | +0.022 |
Neg logit contributions | |
cffff | -0.043 |
jri | -0.038 |
uberty | -0.037 |
odied | -0.036 |
attled | -0.034 |
Token | Le |
Token ID | 1004 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
Parenthood | +0.257 |
mination | +0.255 |
ILA | +0.248 |
FTA | +0.236 |
buster | +0.232 |
Neg logit contributions | |
cffff | -0.281 |
jri | -0.248 |
uberty | -0.238 |
odied | -0.228 |
attled | -0.215 |
Token | a |
Token ID | 64 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
Parenthood | +0.526 |
mination | +0.522 |
ILA | +0.504 |
FTA | +0.475 |
buster | +0.460 |
Neg logit contributions | |
cffff | -0.880 |
jri | -0.800 |
uberty | -0.771 |
odied | -0.751 |
attled | -0.716 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
mination | +0.023 |
Parenthood | +0.022 |
ILA | +0.022 |
FTA | +0.020 |
buster | +0.019 |
Neg logit contributions | |
cffff | -0.049 |
jri | -0.045 |
uberty | -0.044 |
odied | -0.042 |
urses | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
mination | +0.266 |
Parenthood | +0.262 |
ILA | +0.258 |
FTA | +0.241 |
buster | +0.238 |
Neg logit contributions | |
cffff | -0.281 |
jri | -0.252 |
uberty | -0.241 |
odied | -0.233 |
urses | -0.219 |
Token | The |
Token ID | 383 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
mination | +0.237 |
Parenthood | +0.233 |
ILA | +0.230 |
FTA | +0.219 |
buster | +0.217 |
Neg logit contributions | |
cffff | -0.173 |
jri | -0.151 |
uberty | -0.143 |
odied | -0.138 |
attled | -0.127 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
cffff | +0.040 |
jri | +0.034 |
uberty | +0.031 |
odied | +0.029 |
attled | +0.027 |
Neg logit contributions | |
mination | -0.075 |
Parenthood | -0.075 |
ILA | -0.074 |
FTA | -0.070 |
buster | -0.070 |
Token | 13 |
Token ID | 1511 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
cffff | +2.897 |
jri | +2.653 |
uberty | +2.565 |
odied | +2.491 |
attled | +2.374 |
Neg logit contributions | |
mination | -2.131 |
ILA | -2.114 |
Parenthood | -2.077 |
FTA | -1.842 |
buster | -1.837 |
Token | of |
Token ID | 286 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
cffff | +0.741 |
jri | +0.670 |
uberty | +0.640 |
odied | +0.626 |
attled | +0.595 |
Neg logit contributions | |
mination | -0.523 |
Parenthood | -0.519 |
ILA | -0.506 |
FTA | -0.463 |
buster | -0.455 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
mination | +0.034 |
Parenthood | +0.033 |
ILA | +0.033 |
FTA | +0.030 |
buster | +0.030 |
Neg logit contributions | |
cffff | -0.063 |
jri | -0.057 |
uberty | -0.055 |
odied | -0.053 |
attled | -0.051 |
Token | Photo |
Token ID | 5555 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
cffff | +0.102 |
jri | +0.093 |
uberty | +0.089 |
odied | +0.087 |
attled | +0.082 |
Neg logit contributions | |
mination | -0.077 |
Parenthood | -0.076 |
ILA | -0.075 |
buster | -0.069 |
FTA | -0.069 |
Token | : |
Token ID | 25 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
mination | +0.739 |
Parenthood | +0.738 |
ILA | +0.720 |
FTA | +0.676 |
buster | +0.668 |
Neg logit contributions | |
cffff | -0.706 |
jri | -0.626 |
uberty | -0.594 |
odied | -0.575 |
attled | -0.542 |
Token | Le |
Token ID | 1004 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
Parenthood | +0.209 |
mination | +0.208 |
ILA | +0.202 |
FTA | +0.192 |
buster | +0.189 |
Neg logit contributions | |
cffff | -0.241 |
jri | -0.213 |
uberty | -0.205 |
odied | -0.197 |
attled | -0.186 |
Token | a |
Token ID | 64 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
Parenthood | +0.493 |
mination | +0.489 |
ILA | +0.472 |
FTA | +0.445 |
buster | +0.431 |
Neg logit contributions | |
cffff | -0.829 |
jri | -0.754 |
uberty | -0.726 |
odied | -0.708 |
attled | -0.675 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
mination | +0.017 |
Parenthood | +0.017 |
ILA | +0.017 |
FTA | +0.015 |
buster | +0.015 |
Neg logit contributions | |
cffff | -0.038 |
jri | -0.035 |
uberty | -0.034 |
odied | -0.033 |
urses | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
mination | +0.279 |
Parenthood | +0.274 |
ILA | +0.270 |
FTA | +0.252 |
buster | +0.249 |
Neg logit contributions | |
cffff | -0.297 |
jri | -0.267 |
uberty | -0.255 |
odied | -0.246 |
urses | -0.232 |
Token | The |
Token ID | 383 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
mination | +0.191 |
Parenthood | +0.187 |
ILA | +0.185 |
FTA | +0.175 |
buster | +0.174 |
Neg logit contributions | |
cffff | -0.140 |
jri | -0.122 |
uberty | -0.116 |
odied | -0.111 |
attled | -0.103 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
cffff | +0.069 |
jri | +0.057 |
uberty | +0.053 |
odied | +0.050 |
attled | +0.045 |
Neg logit contributions | |
mination | -0.128 |
Parenthood | -0.127 |
ILA | -0.126 |
FTA | -0.120 |
buster | -0.119 |
Token | 9 |
Token ID | 860 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
cffff | +3.054 |
jri | +2.776 |
uberty | +2.673 |
odied | +2.585 |
attled | +2.485 |
Neg logit contributions | |
mination | -2.060 |
Parenthood | -1.986 |
ILA | -1.985 |
FTA | -1.810 |
buster | -1.757 |
Token | of |
Token ID | 286 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
cffff | +0.286 |
jri | +0.260 |
uberty | +0.248 |
odied | +0.242 |
attled | +0.230 |
Neg logit contributions | |
mination | -0.203 |
Parenthood | -0.202 |
ILA | -0.197 |
FTA | -0.180 |
buster | -0.177 |
Token | 15 |
Token ID | 1315 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
mination | +0.037 |
Parenthood | +0.036 |
ILA | +0.036 |
FTA | +0.033 |
buster | +0.032 |
Neg logit contributions | |
cffff | -0.069 |
jri | -0.062 |
uberty | -0.060 |
odied | -0.059 |
attled | -0.056 |
Token | Photo |
Token ID | 5555 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
cffff | +0.113 |
jri | +0.102 |
uberty | +0.099 |
odied | +0.096 |
attled | +0.091 |
Neg logit contributions | |
mination | -0.085 |
Parenthood | -0.084 |
ILA | -0.082 |
buster | -0.076 |
FTA | -0.076 |
Token | : |
Token ID | 25 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
mination | +0.724 |
Parenthood | +0.722 |
ILA | +0.704 |
FTA | +0.662 |
buster | +0.654 |
Neg logit contributions | |
cffff | -0.691 |
jri | -0.613 |
uberty | -0.582 |
odied | -0.563 |
attled | -0.531 |
Token | Le |
Token ID | 1004 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
Parenthood | +0.209 |
mination | +0.207 |
ILA | +0.202 |
FTA | +0.191 |
buster | +0.188 |
Neg logit contributions | |
cffff | -0.249 |
jri | -0.220 |
uberty | -0.212 |
odied | -0.204 |
attled | -0.193 |
Token | a |
Token ID | 64 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
Parenthood | +0.534 |
mination | +0.529 |
ILA | +0.512 |
FTA | +0.481 |
buster | +0.467 |
Neg logit contributions | |
cffff | -0.898 |
jri | -0.816 |
uberty | -0.787 |
odied | -0.767 |
attled | -0.730 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
mination | +0.040 |
Parenthood | +0.039 |
ILA | +0.038 |
FTA | +0.035 |
buster | +0.034 |
Neg logit contributions | |
cffff | -0.086 |
jri | -0.079 |
uberty | -0.077 |
odied | -0.074 |
urses | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
mination | +0.267 |
Parenthood | +0.263 |
ILA | +0.259 |
FTA | +0.242 |
buster | +0.239 |
Neg logit contributions | |
cffff | -0.284 |
jri | -0.255 |
uberty | -0.244 |
odied | -0.235 |
urses | -0.222 |
Token | The |
Token ID | 383 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
mination | +0.223 |
Parenthood | +0.219 |
ILA | +0.216 |
FTA | +0.205 |
buster | +0.204 |
Neg logit contributions | |
cffff | -0.163 |
jri | -0.142 |
uberty | -0.135 |
odied | -0.129 |
attled | -0.119 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
cffff | +0.060 |
jri | +0.050 |
uberty | +0.046 |
odied | +0.043 |
attled | +0.039 |
Neg logit contributions | |
mination | -0.111 |
Parenthood | -0.111 |
ILA | -0.109 |
FTA | -0.104 |
buster | -0.103 |
Token | 10 |
Token ID | 838 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
cffff | +3.075 |
jri | +2.766 |
uberty | +2.712 |
odied | +2.604 |
attled | +2.517 |
Neg logit contributions | |
mination | -1.978 |
Parenthood | -1.941 |
ILA | -1.930 |
FTA | -1.761 |
buster | -1.759 |
Token | of |
Token ID | 286 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
cffff | +0.079 |
jri | +0.071 |
uberty | +0.068 |
odied | +0.066 |
attled | +0.063 |
Neg logit contributions | |
mination | -0.056 |
Parenthood | -0.056 |
ILA | -0.054 |
FTA | -0.050 |
buster | -0.049 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
mination | +0.016 |
Parenthood | +0.016 |
ILA | +0.016 |
FTA | +0.014 |
buster | +0.014 |
Neg logit contributions | |
cffff | -0.030 |
jri | -0.027 |
uberty | -0.026 |
odied | -0.026 |
attled | -0.025 |
Token | Photo |
Token ID | 5555 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
cffff | +0.119 |
jri | +0.108 |
uberty | +0.104 |
odied | +0.101 |
attled | +0.096 |
Neg logit contributions | |
mination | -0.090 |
Parenthood | -0.089 |
ILA | -0.087 |
buster | -0.080 |
FTA | -0.080 |
Token | : |
Token ID | 25 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
mination | +0.719 |
Parenthood | +0.717 |
ILA | +0.700 |
FTA | +0.658 |
buster | +0.650 |
Neg logit contributions | |
cffff | -0.687 |
jri | -0.609 |
uberty | -0.578 |
odied | -0.560 |
attled | -0.528 |
Token | Le |
Token ID | 1004 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
Parenthood | +0.237 |
mination | +0.234 |
ILA | +0.228 |
FTA | +0.217 |
buster | +0.213 |
Neg logit contributions | |
cffff | -0.268 |
jri | -0.236 |
uberty | -0.227 |
odied | -0.218 |
attled | -0.206 |
Token | a |
Token ID | 64 |
Feature activation | -8.16e-03 |
Pos logit contributions | |
Parenthood | +0.475 |
mination | +0.472 |
ILA | +0.456 |
FTA | +0.429 |
buster | +0.416 |
Neg logit contributions | |
cffff | -0.793 |
jri | -0.721 |
uberty | -0.694 |
odied | -0.677 |
attled | -0.645 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
mination | +0.005 |
Parenthood | +0.005 |
ILA | +0.005 |
FTA | +0.005 |
buster | +0.004 |
Neg logit contributions | |
cffff | -0.011 |
jri | -0.010 |
uberty | -0.010 |
odied | -0.010 |
urses | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
mination | +0.287 |
Parenthood | +0.282 |
ILA | +0.277 |
FTA | +0.260 |
buster | +0.256 |
Neg logit contributions | |
cffff | -0.304 |
jri | -0.273 |
uberty | -0.262 |
odied | -0.252 |
urses | -0.238 |
Token | The |
Token ID | 383 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
mination | +0.226 |
Parenthood | +0.221 |
ILA | +0.219 |
FTA | +0.208 |
buster | +0.206 |
Neg logit contributions | |
cffff | -0.165 |
jri | -0.144 |
uberty | -0.136 |
odied | -0.131 |
attled | -0.121 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
cffff | +0.065 |
jri | +0.054 |
uberty | +0.050 |
odied | +0.047 |
attled | +0.043 |
Neg logit contributions | |
mination | -0.121 |
Parenthood | -0.120 |
ILA | -0.119 |
FTA | -0.113 |
buster | -0.113 |
Token | 12 |
Token ID | 1105 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
cffff | +3.025 |
jri | +2.799 |
uberty | +2.735 |
odied | +2.648 |
urses | +2.527 |
Neg logit contributions | |
mination | -1.930 |
Parenthood | -1.901 |
ILA | -1.855 |
buster | -1.699 |
FTA | -1.698 |
Token | of |
Token ID | 286 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
cffff | +0.622 |
jri | +0.563 |
uberty | +0.537 |
odied | +0.524 |
attled | +0.498 |
Neg logit contributions | |
mination | -0.446 |
Parenthood | -0.443 |
ILA | -0.432 |
FTA | -0.395 |
buster | -0.389 |
Token | 15 |
Token ID | 1315 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
mination | +0.045 |
Parenthood | +0.043 |
ILA | +0.043 |
FTA | +0.039 |
buster | +0.039 |
Neg logit contributions | |
cffff | -0.081 |
jri | -0.073 |
uberty | -0.070 |
odied | -0.069 |
attled | -0.066 |
Token | Photo |
Token ID | 5555 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
cffff | +0.095 |
jri | +0.086 |
uberty | +0.083 |
odied | +0.081 |
attled | +0.076 |
Neg logit contributions | |
mination | -0.072 |
Parenthood | -0.071 |
ILA | -0.070 |
buster | -0.064 |
FTA | -0.064 |
Token | : |
Token ID | 25 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
mination | +0.773 |
Parenthood | +0.771 |
ILA | +0.752 |
FTA | +0.707 |
buster | +0.698 |
Neg logit contributions | |
cffff | -0.739 |
jri | -0.655 |
uberty | -0.621 |
odied | -0.602 |
attled | -0.567 |
Token | see |
Token ID | 766 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Parenthood | +0.049 |
mination | +0.049 |
ILA | +0.047 |
FTA | +0.044 |
buster | +0.044 |
Neg logit contributions | |
cffff | -0.058 |
jri | -0.052 |
uberty | -0.050 |
odied | -0.048 |
attled | -0.046 |
Token | your |
Token ID | 534 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Parenthood | +0.280 |
mination | +0.278 |
ILA | +0.270 |
FTA | +0.256 |
buster | +0.251 |
Neg logit contributions | |
cffff | -0.349 |
jri | -0.310 |
uberty | -0.299 |
odied | -0.288 |
attled | -0.273 |
Token | city |
Token ID | 1748 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Parenthood | +0.229 |
mination | +0.228 |
ILA | +0.222 |
FTA | +0.210 |
buster | +0.207 |
Neg logit contributions | |
cffff | -0.251 |
jri | -0.222 |
uberty | -0.213 |
odied | -0.204 |
attled | -0.193 |
Token | � |
Token ID | 14519 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
cffff | +1.214 |
jri | +1.079 |
uberty | +1.032 |
odied | +0.989 |
attled | +0.945 |
Neg logit contributions | |
Parenthood | -1.062 |
mination | -1.061 |
ILA | -1.026 |
FTA | -0.969 |
buster | -0.954 |
Token | � |
Token ID | 244 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
cffff | +1.546 |
jri | +1.399 |
uberty | +1.363 |
odied | +1.323 |
attled | +1.264 |
Neg logit contributions | |
Parenthood | -0.804 |
mination | -0.801 |
ILA | -0.767 |
FTA | -0.718 |
buster | -0.699 |
Token | ️ |
Token ID | 37929 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
cffff | +0.723 |
jri | +0.645 |
uberty | +0.622 |
odied | +0.599 |
attled | +0.569 |
Neg logit contributions | |
Parenthood | -0.551 |
mination | -0.546 |
ILA | -0.530 |
FTA | -0.500 |
buster | -0.491 |
Token | Be |
Token ID | 1355 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
cffff | +2.993 |
jri | +2.680 |
uberty | +2.589 |
odied | +2.494 |
attled | +2.379 |
Neg logit contributions | |
mination | -2.149 |
Parenthood | -2.145 |
ILA | -2.067 |
FTA | -1.937 |
buster | -1.909 |
Token | safe |
Token ID | 3338 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
cffff | +0.211 |
jri | +0.186 |
uberty | +0.178 |
odied | +0.171 |
attled | +0.161 |
Neg logit contributions | |
Parenthood | -0.202 |
mination | -0.201 |
ILA | -0.196 |
FTA | -0.186 |
buster | -0.183 |
Token | pic |
Token ID | 8301 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
cffff | +0.285 |
jri | +0.255 |
uberty | +0.246 |
odied | +0.237 |
attled | +0.225 |
Neg logit contributions | |
Parenthood | -0.211 |
mination | -0.210 |
ILA | -0.203 |
FTA | -0.192 |
buster | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
Parenthood | +1.100 |
mination | +1.099 |
ILA | +1.068 |
FTA | +1.007 |
buster | +0.993 |
Neg logit contributions | |
cffff | -1.217 |
jri | -1.080 |
uberty | -1.038 |
odied | -0.997 |
attled | -0.942 |
Token | twitter |
Token ID | 6956 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
cffff | +0.049 |
jri | +0.042 |
uberty | +0.040 |
odied | +0.038 |
urses | +0.036 |
Neg logit contributions | |
mination | -0.068 |
Parenthood | -0.068 |
ILA | -0.067 |
FTA | -0.064 |
buster | -0.062 |
Token | OR |
Token ID | 1581 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Parenthood | +0.018 |
mination | +0.018 |
ILA | +0.017 |
FTA | +0.016 |
buster | +0.016 |
Neg logit contributions | |
cffff | -0.028 |
jri | -0.025 |
uberty | -0.024 |
odied | -0.023 |
attled | -0.022 |
Token | ATH |
Token ID | 12599 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
cffff | +0.625 |
jri | +0.568 |
uberty | +0.553 |
odied | +0.536 |
urses | +0.513 |
Neg logit contributions | |
Parenthood | -0.290 |
mination | -0.286 |
ILA | -0.271 |
FTA | -0.254 |
buster | -0.248 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
cffff | +0.720 |
jri | +0.644 |
uberty | +0.622 |
odied | +0.598 |
attled | +0.568 |
Neg logit contributions | |
Parenthood | -0.544 |
mination | -0.539 |
ILA | -0.520 |
FTA | -0.493 |
buster | -0.486 |
Token |
|
Token ID | 198 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
cffff | +0.167 |
jri | +0.149 |
uberty | +0.143 |
odied | +0.138 |
urses | +0.131 |
Neg logit contributions | |
mination | -0.145 |
Parenthood | -0.145 |
ILA | -0.140 |
FTA | -0.131 |
buster | -0.129 |
Token | B |
Token ID | 33 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
cffff | +0.108 |
jri | +0.097 |
uberty | +0.094 |
odied | +0.091 |
attled | +0.086 |
Neg logit contributions | |
Parenthood | -0.068 |
mination | -0.067 |
ILA | -0.064 |
FTA | -0.061 |
buster | -0.059 |
Token | oulder |
Token ID | 17601 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
cffff | +0.483 |
jri | +0.428 |
uberty | +0.413 |
odied | +0.398 |
attled | +0.377 |
Neg logit contributions | |
Parenthood | -0.418 |
mination | -0.413 |
ILA | -0.400 |
FTA | -0.381 |
buster | -0.374 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
cffff | +2.797 |
jri | +2.494 |
uberty | +2.415 |
odied | +2.311 |
attled | +2.196 |
Neg logit contributions | |
Parenthood | -2.305 |
mination | -2.291 |
ILA | -2.235 |
FTA | -2.103 |
buster | -2.059 |
Token | " |
Token ID | 1 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
Parenthood | +0.641 |
mination | +0.635 |
ILA | +0.615 |
FTA | +0.575 |
buster | +0.565 |
Neg logit contributions | |
cffff | -1.024 |
jri | -0.922 |
uberty | -0.893 |
odied | -0.862 |
attled | -0.823 |
Token | What |
Token ID | 2061 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
Parenthood | +0.401 |
mination | +0.398 |
ILA | +0.383 |
FTA | +0.360 |
buster | +0.353 |
Neg logit contributions | |
cffff | -0.670 |
jri | -0.605 |
uberty | -0.587 |
odied | -0.567 |
attled | -0.541 |
Token | .. |
Token ID | 492 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
Parenthood | +0.280 |
mination | +0.279 |
ILA | +0.271 |
FTA | +0.255 |
buster | +0.251 |
Neg logit contributions | |
cffff | -0.370 |
jri | -0.331 |
uberty | -0.319 |
odied | -0.307 |
attled | -0.292 |
Token | " |
Token ID | 1 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Parenthood | +0.037 |
mination | +0.037 |
ILA | +0.036 |
FTA | +0.034 |
buster | +0.033 |
Neg logit contributions | |
cffff | -0.057 |
jri | -0.051 |
uberty | -0.050 |
odied | -0.048 |
attled | -0.046 |
Token | made |
Token ID | 9727 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
Parenthood | +0.104 |
mination | +0.103 |
ILA | +0.100 |
FTA | +0.095 |
buster | +0.093 |
Neg logit contributions | |
cffff | -0.129 |
jri | -0.114 |
uberty | -0.110 |
odied | -0.106 |
attled | -0.101 |
Token | ath |
Token ID | 776 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
cffff | +0.025 |
jri | +0.022 |
uberty | +0.021 |
odied | +0.020 |
urses | +0.019 |
Neg logit contributions | |
Parenthood | -0.027 |
mination | -0.027 |
ILA | -0.026 |
FTA | -0.025 |
buster | -0.025 |
Token | ) |
Token ID | 8 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
cffff | +0.170 |
jri | +0.152 |
uberty | +0.147 |
odied | +0.142 |
attled | +0.135 |
Neg logit contributions | |
Parenthood | -0.125 |
mination | -0.123 |
ILA | -0.120 |
FTA | -0.113 |
buster | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Parenthood | +0.028 |
mination | +0.028 |
ILA | +0.027 |
FTA | +0.025 |
buster | +0.025 |
Neg logit contributions | |
cffff | -0.039 |
jri | -0.035 |
uberty | -0.034 |
odied | -0.033 |
attled | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
cffff | +0.276 |
jri | +0.247 |
uberty | +0.237 |
odied | +0.230 |
urses | +0.218 |
Neg logit contributions | |
Parenthood | -0.239 |
mination | -0.239 |
ILA | -0.233 |
FTA | -0.217 |
buster | -0.214 |
Token | Craft |
Token ID | 14467 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
cffff | +0.324 |
jri | +0.291 |
uberty | +0.281 |
odied | +0.273 |
attled | +0.259 |
Neg logit contributions | |
Parenthood | -0.211 |
mination | -0.209 |
ILA | -0.200 |
FTA | -0.190 |
buster | -0.185 |
Token | thousands |
Token ID | 4138 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
cffff | +2.786 |
jri | +2.480 |
uberty | +2.359 |
odied | +2.292 |
attled | +2.177 |
Neg logit contributions | |
mination | -2.340 |
Parenthood | -2.338 |
ILA | -2.257 |
FTA | -2.141 |
buster | -2.099 |
Token | of |
Token ID | 286 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
cffff | +1.086 |
jri | +0.983 |
uberty | +0.953 |
odied | +0.922 |
attled | +0.881 |
Neg logit contributions | |
Parenthood | -0.619 |
mination | -0.612 |
ILA | -0.592 |
FTA | -0.552 |
buster | -0.541 |
Token | objects |
Token ID | 5563 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
cffff | +0.455 |
jri | +0.397 |
uberty | +0.377 |
odied | +0.363 |
attled | +0.341 |
Neg logit contributions | |
mination | -0.497 |
Parenthood | -0.496 |
ILA | -0.483 |
FTA | -0.460 |
buster | -0.455 |
Token | - |
Token ID | 532 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
Parenthood | +0.163 |
mination | +0.161 |
ILA | +0.156 |
FTA | +0.147 |
buster | +0.144 |
Neg logit contributions | |
cffff | -0.239 |
jri | -0.214 |
uberty | -0.208 |
odied | -0.200 |
attled | -0.190 |
Token | building |
Token ID | 2615 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
cffff | +0.090 |
jri | +0.080 |
uberty | +0.077 |
odied | +0.074 |
attled | +0.069 |
Neg logit contributions | |
mination | -0.082 |
Parenthood | -0.082 |
ILA | -0.080 |
FTA | -0.075 |
buster | -0.074 |
Token | Bre |
Token ID | 3719 |
Feature activation | -8.31e-02 |
Pos logit contributions | |
cffff | +1.448 |
jri | +1.274 |
uberty | +1.227 |
odied | +1.175 |
attled | +1.108 |
Neg logit contributions | |
mination | -1.645 |
ILA | -1.612 |
Parenthood | -1.611 |
FTA | -1.497 |
buster | -1.491 |
Token | th |
Token ID | 400 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Parenthood | +0.069 |
mination | +0.068 |
ILA | +0.067 |
FTA | +0.063 |
buster | +0.061 |
Neg logit contributions | |
cffff | -0.100 |
jri | -0.091 |
uberty | -0.088 |
odied | -0.085 |
attled | -0.081 |
Token | auer |
Token ID | 16261 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
cffff | +0.451 |
jri | +0.390 |
uberty | +0.370 |
odied | +0.348 |
attled | +0.326 |
Neg logit contributions | |
Parenthood | -0.632 |
mination | -0.629 |
ILA | -0.620 |
FTA | -0.591 |
buster | -0.579 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
mination | +0.225 |
Parenthood | +0.222 |
ILA | +0.218 |
FTA | +0.204 |
buster | +0.202 |
Neg logit contributions | |
cffff | -0.246 |
jri | -0.220 |
uberty | -0.213 |
odied | -0.203 |
attled | -0.193 |
Token | The |
Token ID | 383 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
mination | +0.130 |
Parenthood | +0.128 |
ILA | +0.126 |
FTA | +0.119 |
buster | +0.119 |
Neg logit contributions | |
cffff | -0.096 |
jri | -0.084 |
uberty | -0.080 |
odied | -0.076 |
attled | -0.071 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
cffff | +0.107 |
jri | +0.089 |
uberty | +0.082 |
odied | +0.077 |
attled | +0.070 |
Neg logit contributions | |
mination | -0.199 |
Parenthood | -0.198 |
ILA | -0.196 |
FTA | -0.186 |
buster | -0.186 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
cffff | +2.905 |
jri | +2.673 |
uberty | +2.640 |
odied | +2.541 |
attled | +2.455 |
Neg logit contributions | |
mination | -1.942 |
Parenthood | -1.894 |
ILA | -1.888 |
buster | -1.730 |
FTA | -1.701 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Parenthood | +0.215 |
mination | +0.215 |
ILA | +0.209 |
FTA | +0.195 |
buster | +0.192 |
Neg logit contributions | |
cffff | -0.259 |
jri | -0.232 |
uberty | -0.223 |
odied | -0.215 |
urses | -0.204 |
Token | Last |
Token ID | 5956 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Parenthood | +0.147 |
mination | +0.145 |
ILA | +0.141 |
FTA | +0.132 |
buster | +0.130 |
Neg logit contributions | |
cffff | -0.222 |
jri | -0.200 |
uberty | -0.193 |
odied | -0.187 |
attled | -0.178 |
Token | month |
Token ID | 1227 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Parenthood | +0.286 |
mination | +0.284 |
ILA | +0.277 |
FTA | +0.263 |
buster | +0.259 |
Neg logit contributions | |
cffff | -0.295 |
jri | -0.259 |
uberty | -0.249 |
odied | -0.238 |
attled | -0.225 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
cffff | +1.254 |
jri | +1.118 |
uberty | +1.077 |
odied | +1.037 |
attled | +0.983 |
Neg logit contributions | |
Parenthood | -0.981 |
mination | -0.971 |
ILA | -0.944 |
FTA | -0.894 |
buster | -0.877 |
Token | your |
Token ID | 534 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
Parenthood | +0.217 |
mination | +0.216 |
ILA | +0.210 |
FTA | +0.198 |
buster | +0.195 |
Neg logit contributions | |
cffff | -0.268 |
jri | -0.239 |
uberty | -0.230 |
odied | -0.221 |
attled | -0.210 |
Token | travel |
Token ID | 35927 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
cffff | +0.057 |
jri | +0.050 |
uberty | +0.048 |
odied | +0.046 |
attled | +0.044 |
Neg logit contributions | |
Parenthood | -0.056 |
mination | -0.056 |
ILA | -0.054 |
FTA | -0.052 |
buster | -0.051 |
Token | s |
Token ID | 82 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
cffff | +0.736 |
jri | +0.661 |
uberty | +0.635 |
odied | +0.613 |
attled | +0.584 |
Neg logit contributions | |
Parenthood | -0.548 |
mination | -0.540 |
ILA | -0.526 |
FTA | -0.496 |
buster | -0.484 |
Token | @ |
Token ID | 31 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Parenthood | +0.229 |
mination | +0.227 |
ILA | +0.220 |
FTA | +0.208 |
buster | +0.204 |
Neg logit contributions | |
cffff | -0.311 |
jri | -0.279 |
uberty | -0.269 |
odied | -0.259 |
attled | -0.247 |
Token | te |
Token ID | 660 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
cffff | +0.142 |
jri | +0.127 |
uberty | +0.122 |
odied | +0.118 |
attled | +0.112 |
Neg logit contributions | |
Parenthood | -0.101 |
mination | -0.100 |
ILA | -0.097 |
FTA | -0.092 |
buster | -0.090 |
Token | legraph |
Token ID | 16606 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Parenthood | +0.310 |
mination | +0.308 |
ILA | +0.301 |
FTA | +0.287 |
buster | +0.283 |
Neg logit contributions | |
cffff | -0.281 |
jri | -0.245 |
uberty | -0.234 |
odied | -0.223 |
attled | -0.209 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
cffff | +2.767 |
jri | +2.449 |
uberty | +2.358 |
odied | +2.260 |
attled | +2.146 |
Neg logit contributions | |
Parenthood | -2.388 |
mination | -2.362 |
ILA | -2.301 |
FTA | -2.178 |
buster | -2.135 |
Token | co |
Token ID | 1073 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
cffff | +0.168 |
jri | +0.152 |
uberty | +0.147 |
odied | +0.143 |
attled | +0.137 |
Neg logit contributions | |
Parenthood | -0.091 |
mination | -0.090 |
ILA | -0.088 |
FTA | -0.081 |
buster | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
Parenthood | +0.589 |
mination | +0.584 |
ILA | +0.566 |
FTA | +0.538 |
buster | +0.530 |
Neg logit contributions | |
cffff | -0.711 |
jri | -0.631 |
uberty | -0.608 |
odied | -0.584 |
attled | -0.553 |
Token | uk |
Token ID | 2724 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
cffff | +0.089 |
jri | +0.077 |
uberty | +0.074 |
odied | +0.070 |
attled | +0.066 |
Neg logit contributions | |
Parenthood | -0.106 |
mination | -0.105 |
ILA | -0.102 |
FTA | -0.098 |
buster | -0.096 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
cffff | +0.415 |
jri | +0.370 |
uberty | +0.358 |
odied | +0.345 |
attled | +0.328 |
Neg logit contributions | |
Parenthood | -0.319 |
mination | -0.317 |
ILA | -0.308 |
FTA | -0.290 |
buster | -0.285 |
Token | probably |
Token ID | 2192 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Parenthood | +0.004 |
mination | +0.004 |
ILA | +0.004 |
FTA | +0.003 |
buster | +0.003 |
Neg logit contributions | |
cffff | -0.005 |
jri | -0.005 |
uberty | -0.005 |
odied | -0.004 |
attled | -0.004 |
Token | no |
Token ID | 645 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Parenthood | +0.270 |
mination | +0.268 |
ILA | +0.260 |
FTA | +0.246 |
buster | +0.242 |
Neg logit contributions | |
cffff | -0.335 |
jri | -0.298 |
uberty | -0.287 |
odied | -0.276 |
attled | -0.262 |
Token | Kenny |
Token ID | 22102 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Parenthood | +0.129 |
mination | +0.128 |
ILA | +0.125 |
FTA | +0.118 |
buster | +0.116 |
Neg logit contributions | |
cffff | -0.144 |
jri | -0.127 |
uberty | -0.122 |
odied | -0.117 |
attled | -0.111 |
Token | Dal |
Token ID | 12348 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
cffff | +0.305 |
jri | +0.263 |
uberty | +0.252 |
odied | +0.240 |
attled | +0.223 |
Neg logit contributions | |
Parenthood | -0.373 |
mination | -0.371 |
ILA | -0.365 |
FTA | -0.345 |
buster | -0.341 |
Token | g |
Token ID | 70 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
cffff | +1.781 |
jri | +1.621 |
uberty | +1.591 |
odied | +1.546 |
attled | +1.513 |
Neg logit contributions | |
Parenthood | -0.853 |
mination | -0.836 |
ILA | -0.815 |
FTA | -0.733 |
buster | -0.706 |
Token | lish |
Token ID | 1836 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Parenthood | +1.186 |
mination | +1.175 |
ILA | +1.151 |
FTA | +1.100 |
buster | +1.084 |
Neg logit contributions | |
cffff | -0.981 |
jri | -0.852 |
uberty | -0.814 |
odied | -0.775 |
attled | -0.724 |
Token | either |
Token ID | 2035 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
cffff | +2.800 |
jri | +2.511 |
uberty | +2.397 |
odied | +2.297 |
attled | +2.192 |
Neg logit contributions | |
Parenthood | -2.302 |
mination | -2.289 |
ILA | -2.246 |
FTA | -2.096 |
buster | -2.043 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
cffff | +0.212 |
jri | +0.189 |
uberty | +0.181 |
odied | +0.174 |
attled | +0.166 |
Neg logit contributions | |
Parenthood | -0.177 |
mination | -0.175 |
ILA | -0.171 |
FTA | -0.161 |
buster | -0.158 |
Token | because |
Token ID | 780 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
cffff | +0.036 |
jri | +0.032 |
uberty | +0.031 |
odied | +0.030 |
attled | +0.028 |
Neg logit contributions | |
mination | -0.028 |
Parenthood | -0.028 |
ILA | -0.027 |
FTA | -0.025 |
buster | -0.025 |
Token | what |
Token ID | 644 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Parenthood | +0.177 |
mination | +0.176 |
ILA | +0.171 |
FTA | +0.162 |
buster | +0.159 |
Neg logit contributions | |
cffff | -0.219 |
jri | -0.195 |
uberty | -0.188 |
odied | -0.180 |
attled | -0.171 |
Token | would |
Token ID | 561 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
Parenthood | +0.277 |
mination | +0.277 |
ILA | +0.269 |
FTA | +0.253 |
buster | +0.250 |
Neg logit contributions | |
cffff | -0.336 |
jri | -0.301 |
uberty | -0.288 |
odied | -0.278 |
attled | -0.264 |
Token | s |
Token ID | 82 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Parenthood | +0.241 |
mination | +0.238 |
ILA | +0.230 |
FTA | +0.215 |
buster | +0.210 |
Neg logit contributions | |
cffff | -0.443 |
jri | -0.401 |
uberty | -0.390 |
odied | -0.377 |
attled | -0.361 |
Token | Jon |
Token ID | 5966 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Parenthood | +0.380 |
mination | +0.376 |
ILA | +0.366 |
FTA | +0.348 |
buster | +0.343 |
Neg logit contributions | |
cffff | -0.416 |
jri | -0.367 |
uberty | -0.352 |
odied | -0.338 |
attled | -0.319 |
Token | Brown |
Token ID | 4373 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
cffff | +0.220 |
jri | +0.190 |
uberty | +0.181 |
odied | +0.173 |
attled | +0.161 |
Neg logit contributions | |
Parenthood | -0.264 |
mination | -0.261 |
ILA | -0.255 |
FTA | -0.244 |
buster | -0.241 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
cffff | +0.004 |
jri | +0.004 |
uberty | +0.003 |
odied | +0.003 |
attled | +0.003 |
Neg logit contributions | |
Parenthood | -0.003 |
mination | -0.003 |
ILA | -0.003 |
FTA | -0.003 |
buster | -0.003 |
Token | newly |
Token ID | 8308 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
cffff | +0.017 |
jri | +0.015 |
uberty | +0.015 |
odied | +0.014 |
attled | +0.013 |
Neg logit contributions | |
Parenthood | -0.014 |
mination | -0.014 |
ILA | -0.014 |
FTA | -0.013 |
buster | -0.013 |
Token | mint |
Token ID | 21043 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
cffff | +0.929 |
jri | +0.805 |
uberty | +0.766 |
odied | +0.730 |
attled | +0.681 |
Neg logit contributions | |
Parenthood | -1.151 |
mination | -1.144 |
ILA | -1.117 |
FTA | -1.068 |
buster | -1.054 |
Token | ed |
Token ID | 276 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
cffff | +2.591 |
jri | +2.280 |
uberty | +2.183 |
odied | +2.125 |
attled | +2.016 |
Neg logit contributions | |
Parenthood | -2.481 |
mination | -2.476 |
ILA | -2.407 |
FTA | -2.280 |
buster | -2.238 |
Token | place |
Token ID | 1295 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
cffff | +0.315 |
jri | +0.279 |
uberty | +0.269 |
odied | +0.258 |
attled | +0.244 |
Neg logit contributions | |
Parenthood | -0.270 |
mination | -0.267 |
ILA | -0.260 |
FTA | -0.247 |
buster | -0.243 |
Token | k |
Token ID | 74 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
cffff | +0.719 |
jri | +0.645 |
uberty | +0.623 |
odied | +0.601 |
attled | +0.572 |
Neg logit contributions | |
Parenthood | -0.511 |
mination | -0.506 |
ILA | -0.491 |
FTA | -0.464 |
buster | -0.454 |
Token | icker |
Token ID | 15799 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Parenthood | +0.256 |
mination | +0.255 |
ILA | +0.249 |
FTA | +0.238 |
buster | +0.236 |
Neg logit contributions | |
cffff | -0.192 |
jri | -0.165 |
uberty | -0.157 |
odied | -0.149 |
attled | -0.138 |
Token | for |
Token ID | 329 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
cffff | +0.756 |
jri | +0.677 |
uberty | +0.653 |
odied | +0.630 |
attled | +0.599 |
Neg logit contributions | |
Parenthood | -0.554 |
mination | -0.550 |
ILA | -0.533 |
FTA | -0.503 |
buster | -0.493 |
Token | Le |
Token ID | 1004 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
Parenthood | +0.189 |
mination | +0.187 |
ILA | +0.183 |
FTA | +0.174 |
buster | +0.171 |
Neg logit contributions | |
cffff | -0.205 |
jri | -0.181 |
uberty | -0.174 |
odied | -0.167 |
attled | -0.157 |
Token | a |
Token ID | 64 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
Parenthood | +0.445 |
mination | +0.442 |
ILA | +0.427 |
FTA | +0.402 |
buster | +0.390 |
Neg logit contributions | |
cffff | -0.749 |
jri | -0.682 |
uberty | -0.657 |
odied | -0.640 |
attled | -0.610 |
Token | Suzuki |
Token ID | 35807 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
cffff | +0.031 |
jri | +0.028 |
uberty | +0.027 |
odied | +0.027 |
urses | +0.025 |
Neg logit contributions | |
mination | -0.014 |
Parenthood | -0.014 |
ILA | -0.014 |
FTA | -0.012 |
buster | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
mination | +0.271 |
Parenthood | +0.267 |
ILA | +0.263 |
FTA | +0.245 |
buster | +0.243 |
Neg logit contributions | |
cffff | -0.289 |
jri | -0.260 |
uberty | -0.249 |
odied | -0.240 |
urses | -0.226 |
Token | The |
Token ID | 383 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
mination | +0.170 |
Parenthood | +0.167 |
ILA | +0.165 |
FTA | +0.156 |
buster | +0.155 |
Neg logit contributions | |
cffff | -0.125 |
jri | -0.109 |
uberty | -0.103 |
odied | -0.099 |
attled | -0.092 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
cffff | +0.105 |
jri | +0.088 |
uberty | +0.081 |
odied | +0.076 |
attled | +0.069 |
Neg logit contributions | |
mination | -0.196 |
Parenthood | -0.195 |
ILA | -0.193 |
FTA | -0.184 |
buster | -0.183 |
Token | 8 |
Token ID | 807 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
cffff | +2.942 |
jri | +2.675 |
uberty | +2.614 |
odied | +2.538 |
urses | +2.431 |
Neg logit contributions | |
mination | -1.924 |
Parenthood | -1.874 |
ILA | -1.832 |
FTA | -1.693 |
buster | -1.681 |
Token | of |
Token ID | 286 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
cffff | +0.222 |
jri | +0.202 |
uberty | +0.193 |
odied | +0.188 |
attled | +0.179 |
Neg logit contributions | |
mination | -0.157 |
Parenthood | -0.156 |
ILA | -0.152 |
FTA | -0.139 |
buster | -0.136 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
mination | +0.005 |
Parenthood | +0.005 |
ILA | +0.005 |
FTA | +0.004 |
buster | +0.004 |
Neg logit contributions | |
cffff | -0.009 |
jri | -0.008 |
uberty | -0.008 |
odied | -0.008 |
attled | -0.007 |
Token | Photo |
Token ID | 5555 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
cffff | +0.155 |
jri | +0.140 |
uberty | +0.135 |
odied | +0.131 |
attled | +0.124 |
Neg logit contributions | |
mination | -0.116 |
Parenthood | -0.115 |
ILA | -0.113 |
buster | -0.104 |
FTA | -0.104 |
Token | : |
Token ID | 25 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
mination | +0.736 |
Parenthood | +0.734 |
ILA | +0.716 |
FTA | +0.674 |
buster | +0.665 |
Neg logit contributions | |
cffff | -0.701 |
jri | -0.622 |
uberty | -0.589 |
odied | -0.571 |
attled | -0.539 |
Token | competitors |
Token ID | 13861 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
cffff | +0.035 |
jri | +0.031 |
uberty | +0.029 |
odied | +0.028 |
attled | +0.027 |
Neg logit contributions | |
Parenthood | -0.030 |
mination | -0.029 |
ILA | -0.029 |
FTA | -0.027 |
buster | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Parenthood | +0.161 |
mination | +0.159 |
ILA | +0.155 |
FTA | +0.147 |
buster | +0.145 |
Neg logit contributions | |
cffff | -0.199 |
jri | -0.177 |
uberty | -0.171 |
odied | -0.164 |
attled | -0.155 |
Token | Even |
Token ID | 3412 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
cffff | +0.159 |
jri | +0.143 |
uberty | +0.138 |
odied | +0.133 |
attled | +0.126 |
Neg logit contributions | |
mination | -0.147 |
Parenthood | -0.147 |
ILA | -0.144 |
FTA | -0.134 |
buster | -0.132 |
Token | Chairman |
Token ID | 12787 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
cffff | +0.485 |
jri | +0.437 |
uberty | +0.422 |
odied | +0.408 |
attled | +0.388 |
Neg logit contributions | |
mination | -0.365 |
Parenthood | -0.365 |
ILA | -0.355 |
FTA | -0.330 |
buster | -0.325 |
Token | Bill |
Token ID | 3941 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
Parenthood | +0.399 |
mination | +0.395 |
ILA | +0.384 |
FTA | +0.364 |
buster | +0.358 |
Neg logit contributions | |
cffff | -0.494 |
jri | -0.440 |
uberty | -0.424 |
odied | -0.407 |
attled | -0.386 |
Token | Gates |
Token ID | 15953 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Parenthood | +0.695 |
mination | +0.684 |
ILA | +0.655 |
FTA | +0.610 |
buster | +0.607 |
Neg logit contributions | |
cffff | -1.304 |
jri | -1.181 |
uberty | -1.139 |
odied | -1.099 |
icter | -1.050 |
Token | said |
Token ID | 531 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Parenthood | +2.564 |
mination | +2.544 |
ILA | +2.476 |
FTA | +2.352 |
buster | +2.314 |
Neg logit contributions | |
cffff | -2.896 |
jri | -2.563 |
uberty | -2.466 |
odied | -2.365 |
attled | -2.235 |
Token | this |
Token ID | 428 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Parenthood | +0.155 |
mination | +0.154 |
ILA | +0.150 |
FTA | +0.141 |
buster | +0.139 |
Neg logit contributions | |
cffff | -0.194 |
jri | -0.173 |
uberty | -0.167 |
odied | -0.160 |
attled | -0.152 |
Token | week |
Token ID | 1285 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
Parenthood | +0.223 |
mination | +0.222 |
ILA | +0.216 |
FTA | +0.204 |
buster | +0.201 |
Neg logit contributions | |
cffff | -0.248 |
jri | -0.220 |
uberty | -0.212 |
odied | -0.203 |
attled | -0.192 |
Token | that |
Token ID | 326 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
cffff | +0.892 |
jri | +0.788 |
uberty | +0.756 |
odied | +0.723 |
attled | +0.684 |
Neg logit contributions | |
Parenthood | -0.866 |
mination | -0.861 |
ILA | -0.838 |
FTA | -0.796 |
buster | -0.784 |
Token | he |
Token ID | 339 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
cffff | +0.292 |
jri | +0.259 |
uberty | +0.249 |
odied | +0.239 |
attled | +0.226 |
Neg logit contributions | |
Parenthood | -0.259 |
mination | -0.257 |
ILA | -0.250 |
FTA | -0.237 |
buster | -0.233 |
Token | istic |
Token ID | 2569 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Parenthood | +0.891 |
mination | +0.885 |
ILA | +0.861 |
FTA | +0.818 |
buster | +0.805 |
Neg logit contributions | |
cffff | -0.993 |
jri | -0.878 |
uberty | -0.845 |
odied | -0.810 |
attled | -0.765 |
Token | exchanges |
Token ID | 14525 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
cffff | +0.245 |
jri | +0.216 |
uberty | +0.207 |
odied | +0.199 |
attled | +0.187 |
Neg logit contributions | |
Parenthood | -0.240 |
mination | -0.239 |
ILA | -0.233 |
FTA | -0.221 |
buster | -0.219 |
Token | between |
Token ID | 1022 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
cffff | +0.318 |
jri | +0.284 |
uberty | +0.274 |
odied | +0.264 |
attled | +0.251 |
Neg logit contributions | |
Parenthood | -0.238 |
mination | -0.236 |
ILA | -0.229 |
FTA | -0.217 |
buster | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
Parenthood | +0.021 |
mination | +0.021 |
ILA | +0.020 |
FTA | +0.019 |
buster | +0.019 |
Neg logit contributions | |
cffff | -0.026 |
jri | -0.023 |
uberty | -0.022 |
odied | -0.021 |
attled | -0.020 |
Token | two |
Token ID | 734 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
Parenthood | +0.062 |
mination | +0.061 |
ILA | +0.060 |
FTA | +0.057 |
buster | +0.056 |
Neg logit contributions | |
cffff | -0.061 |
jri | -0.053 |
uberty | -0.051 |
odied | -0.049 |
attled | -0.046 |
Token | Kore |
Token ID | 3374 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Parenthood | +0.017 |
mination | +0.017 |
ILA | +0.016 |
FTA | +0.015 |
buster | +0.015 |
Neg logit contributions | |
cffff | -0.024 |
jri | -0.022 |
uberty | -0.021 |
odied | -0.021 |
attled | -0.020 |
Token | as |
Token ID | 292 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Parenthood | +2.042 |
mination | +2.021 |
ILA | +1.953 |
FTA | +1.830 |
buster | +1.792 |
Neg logit contributions | |
cffff | -3.395 |
jri | -3.065 |
uberty | -2.967 |
odied | -2.868 |
attled | -2.739 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
cffff | +1.188 |
jri | +1.052 |
uberty | +1.012 |
odied | +0.972 |
attled | +0.923 |
Neg logit contributions | |
Parenthood | -1.017 |
mination | -1.011 |
ILA | -0.984 |
FTA | -0.927 |
buster | -0.915 |
Token | Others |
Token ID | 12691 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
mination | +0.099 |
Parenthood | +0.098 |
ILA | +0.097 |
buster | +0.090 |
FTA | +0.090 |
Neg logit contributions | |
cffff | -0.112 |
jri | -0.101 |
uberty | -0.099 |
odied | -0.094 |
attled | -0.089 |
Token | include |
Token ID | 2291 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
cffff | +0.202 |
jri | +0.178 |
uberty | +0.171 |
odied | +0.165 |
attled | +0.156 |
Neg logit contributions | |
Parenthood | -0.190 |
mination | -0.189 |
ILA | -0.184 |
FTA | -0.174 |
buster | -0.171 |
Token | the |
Token ID | 262 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
Parenthood | +0.115 |
mination | +0.114 |
ILA | +0.111 |
FTA | +0.105 |
buster | +0.104 |
Neg logit contributions | |
cffff | -0.132 |
jri | -0.118 |
uberty | -0.113 |
odied | -0.109 |
attled | -0.103 |
Token | The |
Token ID | 464 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Parenthood | +0.139 |
mination | +0.138 |
ILA | +0.133 |
FTA | +0.126 |
buster | +0.123 |
Neg logit contributions | |
cffff | -0.207 |
jri | -0.186 |
uberty | -0.179 |
odied | -0.173 |
attled | -0.165 |
Token | attempt |
Token ID | 2230 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
cffff | +0.400 |
jri | +0.355 |
uberty | +0.340 |
odied | +0.325 |
attled | +0.308 |
Neg logit contributions | |
Parenthood | -0.366 |
mination | -0.365 |
ILA | -0.355 |
FTA | -0.334 |
buster | -0.333 |
Token | to |
Token ID | 284 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
cffff | +0.340 |
jri | +0.307 |
uberty | +0.296 |
odied | +0.286 |
attled | +0.273 |
Neg logit contributions | |
Parenthood | -0.220 |
mination | -0.218 |
ILA | -0.211 |
FTA | -0.198 |
buster | -0.194 |
Token | blur |
Token ID | 23671 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Parenthood | +0.191 |
mination | +0.191 |
ILA | +0.186 |
FTA | +0.175 |
buster | +0.173 |
Neg logit contributions | |
cffff | -0.195 |
jri | -0.172 |
uberty | -0.165 |
odied | -0.158 |
attled | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Parenthood | +0.407 |
mination | +0.405 |
ILA | +0.393 |
FTA | +0.372 |
buster | +0.367 |
Neg logit contributions | |
cffff | -0.481 |
jri | -0.428 |
uberty | -0.411 |
odied | -0.395 |
attled | -0.374 |
Token | boundary |
Token ID | 18645 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
mination | +0.020 |
Parenthood | +0.020 |
ILA | +0.019 |
FTA | +0.018 |
buster | +0.018 |
Neg logit contributions | |
cffff | -0.026 |
jri | -0.023 |
uberty | -0.022 |
odied | -0.021 |
attled | -0.020 |
Token | lines |
Token ID | 3951 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Parenthood | +2.250 |
mination | +2.232 |
ILA | +2.163 |
FTA | +2.043 |
buster | +2.004 |
Neg logit contributions | |
cffff | -3.175 |
jri | -2.842 |
uberty | -2.747 |
odied | -2.649 |
attled | -2.518 |
Token | between |
Token ID | 1022 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Parenthood | +1.361 |
mination | +1.349 |
ILA | +1.308 |
FTA | +1.234 |
buster | +1.211 |
Neg logit contributions | |
cffff | -1.892 |
jri | -1.694 |
uberty | -1.636 |
odied | -1.577 |
attled | -1.499 |
Token | sovereign |
Token ID | 18901 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Parenthood | +0.527 |
mination | +0.525 |
ILA | +0.510 |
FTA | +0.482 |
buster | +0.477 |
Neg logit contributions | |
cffff | -0.590 |
jri | -0.522 |
uberty | -0.502 |
odied | -0.483 |
attled | -0.456 |
Token | Israel |
Token ID | 2692 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
Parenthood | +1.903 |
mination | +1.887 |
ILA | +1.838 |
FTA | +1.746 |
buster | +1.714 |
Neg logit contributions | |
cffff | -2.160 |
jri | -1.913 |
uberty | -1.841 |
odied | -1.765 |
attled | -1.670 |
Token | and |
Token ID | 290 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Parenthood | +0.623 |
mination | +0.617 |
ILA | +0.598 |
FTA | +0.562 |
buster | +0.552 |
Neg logit contributions | |
cffff | -0.927 |
jri | -0.833 |
uberty | -0.806 |
odied | -0.777 |
attled | -0.740 |
Token | echoes |
Token ID | 30346 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
cffff | +0.202 |
jri | +0.180 |
uberty | +0.173 |
odied | +0.168 |
attled | +0.159 |
Neg logit contributions | |
Parenthood | -0.157 |
mination | -0.156 |
ILA | -0.152 |
FTA | -0.144 |
buster | -0.142 |
Token | of |
Token ID | 286 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
cffff | +0.221 |
jri | +0.198 |
uberty | +0.191 |
odied | +0.185 |
attled | +0.176 |
Neg logit contributions | |
Parenthood | -0.151 |
mination | -0.150 |
ILA | -0.145 |
FTA | -0.136 |
buster | -0.134 |
Token | M |
Token ID | 337 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
cffff | +0.500 |
jri | +0.443 |
uberty | +0.428 |
odied | +0.412 |
attled | +0.387 |
Neg logit contributions | |
Parenthood | -0.439 |
mination | -0.439 |
ILA | -0.427 |
FTA | -0.403 |
buster | -0.399 |
Token | . |
Token ID | 13 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
cffff | +0.769 |
jri | +0.679 |
uberty | +0.653 |
odied | +0.626 |
attled | +0.589 |
Neg logit contributions | |
Parenthood | -0.731 |
mination | -0.725 |
ILA | -0.705 |
FTA | -0.673 |
buster | -0.661 |
Token | Night |
Token ID | 5265 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
cffff | +0.365 |
jri | +0.326 |
uberty | +0.316 |
odied | +0.305 |
attled | +0.288 |
Neg logit contributions | |
Parenthood | -0.268 |
mination | -0.268 |
ILA | -0.257 |
FTA | -0.244 |
buster | -0.241 |
Token | Shy |
Token ID | 36838 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
cffff | +1.083 |
jri | +0.992 |
uberty | +0.966 |
odied | +0.941 |
attled | +0.907 |
Neg logit contributions | |
mination | -0.395 |
Parenthood | -0.395 |
ILA | -0.374 |
FTA | -0.343 |
buster | -0.324 |
Token | am |
Token ID | 321 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Parenthood | +2.206 |
mination | +2.178 |
ILA | +2.082 |
FTA | +1.987 |
buster | +1.970 |
Neg logit contributions | |
cffff | -3.221 |
jri | -2.884 |
uberty | -2.794 |
odied | -2.663 |
attled | -2.575 |
Token | alan |
Token ID | 25786 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
cffff | +0.242 |
jri | +0.209 |
uberty | +0.200 |
odied | +0.191 |
attled | +0.176 |
Neg logit contributions | |
Parenthood | -0.312 |
mination | -0.310 |
ILA | -0.303 |
FTA | -0.290 |
buster | -0.286 |
Token | � |
Token ID | 447 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
cffff | +0.137 |
jri | +0.122 |
uberty | +0.118 |
odied | +0.114 |
attled | +0.108 |
Neg logit contributions | |
Parenthood | -0.100 |
mination | -0.100 |
ILA | -0.097 |
FTA | -0.091 |
buster | -0.089 |
Token | � |
Token ID | 247 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
Parenthood | +0.052 |
mination | +0.052 |
ILA | +0.050 |
FTA | +0.048 |
buster | +0.047 |
Neg logit contributions | |
cffff | -0.080 |
jri | -0.071 |
uberty | -0.070 |
odied | -0.067 |
attled | -0.064 |
Token | s |
Token ID | 82 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
cffff | +0.122 |
jri | +0.111 |
uberty | +0.107 |
odied | +0.104 |
attled | +0.099 |
Neg logit contributions | |
Parenthood | -0.068 |
mination | -0.067 |
ILA | -0.065 |
FTA | -0.061 |
buster | -0.059 |
Token | facts |
Token ID | 6419 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Parenthood | +0.135 |
mination | +0.134 |
ILA | +0.131 |
FTA | +0.124 |
buster | +0.122 |
Neg logit contributions | |
cffff | -0.156 |
jri | -0.139 |
uberty | -0.133 |
odied | -0.128 |
attled | -0.121 |
Token | of |
Token ID | 286 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
Parenthood | +0.359 |
mination | +0.355 |
ILA | +0.345 |
FTA | +0.327 |
buster | +0.321 |
Neg logit contributions | |
cffff | -0.471 |
jri | -0.420 |
uberty | -0.406 |
odied | -0.390 |
attled | -0.370 |
Token | nature |
Token ID | 3450 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
cffff | +0.038 |
jri | +0.033 |
uberty | +0.032 |
odied | +0.031 |
attled | +0.029 |
Neg logit contributions | |
Parenthood | -0.037 |
mination | -0.036 |
ILA | -0.035 |
FTA | -0.034 |
buster | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Parenthood | +0.446 |
mination | +0.441 |
ILA | +0.428 |
FTA | +0.406 |
buster | +0.398 |
Neg logit contributions | |
cffff | -0.577 |
jri | -0.515 |
uberty | -0.496 |
odied | -0.478 |
attled | -0.453 |
Token | The |
Token ID | 383 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
mination | +0.102 |
Parenthood | +0.101 |
ILA | +0.099 |
FTA | +0.093 |
buster | +0.092 |
Neg logit contributions | |
cffff | -0.117 |
jri | -0.104 |
uberty | -0.101 |
odied | -0.097 |
attled | -0.092 |
Token | boundary |
Token ID | 18645 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
cffff | +0.364 |
jri | +0.323 |
uberty | +0.310 |
odied | +0.298 |
attled | +0.282 |
Neg logit contributions | |
Parenthood | -0.329 |
mination | -0.329 |
ILA | -0.320 |
FTA | -0.302 |
buster | -0.299 |
Token | between |
Token ID | 1022 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
Parenthood | +2.223 |
mination | +2.213 |
ILA | +2.137 |
FTA | +2.028 |
buster | +1.997 |
Neg logit contributions | |
cffff | -3.101 |
jri | -2.768 |
uberty | -2.676 |
odied | -2.575 |
attled | -2.449 |
Token | Europe |
Token ID | 2031 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Parenthood | +0.600 |
mination | +0.597 |
ILA | +0.580 |
FTA | +0.548 |
buster | +0.541 |
Neg logit contributions | |
cffff | -0.708 |
jri | -0.629 |
uberty | -0.606 |
odied | -0.583 |
attled | -0.552 |
Token | and |
Token ID | 290 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
Parenthood | +0.441 |
mination | +0.437 |
ILA | +0.424 |
FTA | +0.398 |
buster | +0.391 |
Neg logit contributions | |
cffff | -0.660 |
jri | -0.593 |
uberty | -0.573 |
odied | -0.553 |
attled | -0.527 |
Token | Asia |
Token ID | 7229 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
cffff | +0.040 |
jri | +0.035 |
uberty | +0.034 |
odied | +0.033 |
attled | +0.031 |
Neg logit contributions | |
Parenthood | -0.033 |
mination | -0.033 |
ILA | -0.032 |
FTA | -0.030 |
buster | -0.030 |
Token | is |
Token ID | 318 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Parenthood | +0.481 |
mination | +0.478 |
ILA | +0.465 |
FTA | +0.438 |
buster | +0.431 |
Neg logit contributions | |
cffff | -0.622 |
jri | -0.556 |
uberty | -0.536 |
odied | -0.516 |
attled | -0.489 |
Token | shift |
Token ID | 6482 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Parenthood | +1.130 |
mination | +1.121 |
ILA | +1.088 |
FTA | +1.030 |
buster | +1.012 |
Neg logit contributions | |
cffff | -1.442 |
jri | -1.286 |
uberty | -1.240 |
odied | -1.193 |
attled | -1.132 |
Token | around |
Token ID | 1088 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
cffff | +0.156 |
jri | +0.138 |
uberty | +0.132 |
odied | +0.127 |
attled | +0.120 |
Neg logit contributions | |
Parenthood | -0.145 |
mination | -0.144 |
ILA | -0.140 |
FTA | -0.133 |
buster | -0.131 |
Token | arbitrarily |
Token ID | 40647 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
cffff | +0.315 |
jri | +0.280 |
uberty | +0.269 |
odied | +0.259 |
attled | +0.245 |
Neg logit contributions | |
Parenthood | -0.266 |
mination | -0.265 |
ILA | -0.257 |
FTA | -0.243 |
buster | -0.240 |
Token | ; |
Token ID | 26 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Parenthood | +0.010 |
mination | +0.010 |
ILA | +0.009 |
FTA | +0.009 |
buster | +0.009 |
Neg logit contributions | |
cffff | -0.012 |
jri | -0.011 |
uberty | -0.010 |
odied | -0.010 |
attled | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +4.95e-04 |
Pos logit contributions | |
cffff | +0.309 |
jri | +0.274 |
uberty | +0.263 |
odied | +0.252 |
attled | +0.238 |
Neg logit contributions | |
mination | -0.276 |
Parenthood | -0.276 |
ILA | -0.270 |
FTA | -0.253 |
buster | -0.251 |
Token | separation |
Token ID | 14139 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
cffff | +0.001 |
jri | +0.000 |
uberty | +0.000 |
odied | +0.000 |
attled | +0.000 |
Neg logit contributions | |
Parenthood | -0.000 |
mination | -0.000 |
ILA | -0.000 |
FTA | -0.000 |
buster | -0.000 |
Token | wall |
Token ID | 3355 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Parenthood | +2.309 |
mination | +2.297 |
ILA | +2.224 |
FTA | +2.124 |
buster | +2.079 |
Neg logit contributions | |
cffff | -2.980 |
jri | -2.647 |
uberty | -2.567 |
odied | -2.463 |
attled | -2.337 |
Token | cuts |
Token ID | 6630 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
Parenthood | +1.641 |
mination | +1.627 |
ILA | +1.580 |
FTA | +1.495 |
buster | +1.469 |
Neg logit contributions | |
cffff | -2.128 |
jri | -1.897 |
uberty | -1.831 |
odied | -1.762 |
attled | -1.672 |
Token | people |
Token ID | 661 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
Parenthood | +0.865 |
mination | +0.862 |
ILA | +0.837 |
FTA | +0.785 |
buster | +0.776 |
Neg logit contributions | |
cffff | -1.157 |
jri | -1.039 |
uberty | -0.999 |
odied | -0.963 |
attled | -0.915 |
Token | off |
Token ID | 572 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
cffff | +0.584 |
jri | +0.523 |
uberty | +0.499 |
odied | +0.483 |
attled | +0.459 |
Neg logit contributions | |
Parenthood | -0.438 |
mination | -0.438 |
ILA | -0.422 |
FTA | -0.397 |
buster | -0.392 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
Parenthood | +0.424 |
mination | +0.421 |
ILA | +0.407 |
FTA | +0.381 |
buster | +0.374 |
Neg logit contributions | |
cffff | -0.675 |
jri | -0.608 |
uberty | -0.588 |
odied | -0.568 |
attled | -0.542 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Parenthood | +0.268 |
mination | +0.268 |
ILA | +0.261 |
FTA | +0.243 |
buster | +0.239 |
Neg logit contributions | |
cffff | -0.322 |
jri | -0.288 |
uberty | -0.276 |
odied | -0.267 |
urses | -0.253 |
Token | Israel |
Token ID | 14040 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Parenthood | +0.196 |
mination | +0.194 |
ILA | +0.186 |
FTA | +0.177 |
buster | +0.173 |
Neg logit contributions | |
cffff | -0.292 |
jri | -0.264 |
uberty | -0.254 |
odied | -0.245 |
attled | -0.233 |
Token | also |
Token ID | 635 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Parenthood | +0.643 |
mination | +0.640 |
ILA | +0.621 |
FTA | +0.587 |
buster | +0.578 |
Neg logit contributions | |
cffff | -0.802 |
jri | -0.715 |
uberty | -0.688 |
odied | -0.662 |
attled | -0.628 |
Token | nurt |
Token ID | 23868 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
Parenthood | +0.099 |
mination | +0.099 |
ILA | +0.097 |
FTA | +0.091 |
buster | +0.090 |
Neg logit contributions | |
cffff | -0.108 |
jri | -0.095 |
uberty | -0.091 |
odied | -0.088 |
attled | -0.083 |
Token | ures |
Token ID | 942 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Parenthood | +0.428 |
mination | +0.423 |
ILA | +0.409 |
FTA | +0.383 |
buster | +0.378 |
Neg logit contributions | |
cffff | -0.647 |
jri | -0.578 |
uberty | -0.562 |
odied | -0.545 |
urses | -0.521 |
Token | separation |
Token ID | 14139 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Parenthood | +0.468 |
mination | +0.465 |
ILA | +0.452 |
FTA | +0.429 |
buster | +0.422 |
Neg logit contributions | |
cffff | -0.537 |
jri | -0.476 |
uberty | -0.458 |
odied | -0.439 |
attled | -0.416 |
Token | within |
Token ID | 1626 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
Parenthood | +2.211 |
mination | +2.181 |
ILA | +2.113 |
FTA | +2.011 |
buster | +1.978 |
Neg logit contributions | |
cffff | -3.075 |
jri | -2.742 |
uberty | -2.668 |
odied | -2.571 |
attled | -2.435 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
cffff | +0.007 |
jri | +0.006 |
uberty | +0.006 |
odied | +0.006 |
attled | +0.006 |
Neg logit contributions | |
Parenthood | -0.006 |
mination | -0.006 |
ILA | -0.006 |
FTA | -0.005 |
buster | -0.005 |
Token | West |
Token ID | 2688 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
mination | +0.160 |
Parenthood | +0.160 |
ILA | +0.156 |
FTA | +0.146 |
buster | +0.145 |
Neg logit contributions | |
cffff | -0.191 |
jri | -0.169 |
uberty | -0.163 |
odied | -0.157 |
attled | -0.149 |
Token | Bank |
Token ID | 5018 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Parenthood | +1.500 |
mination | +1.484 |
ILA | +1.434 |
FTA | +1.345 |
buster | +1.317 |
Neg logit contributions | |
cffff | -2.452 |
jri | -2.211 |
uberty | -2.140 |
odied | -2.069 |
attled | -1.975 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Parenthood | +0.370 |
mination | +0.369 |
ILA | +0.358 |
FTA | +0.337 |
buster | +0.331 |
Neg logit contributions | |
cffff | -0.480 |
jri | -0.429 |
uberty | -0.413 |
odied | -0.397 |
attled | -0.378 |
Token | 1 |
Token ID | 16 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
cffff | +0.381 |
jri | +0.344 |
uberty | +0.333 |
odied | +0.324 |
attled | +0.309 |
Neg logit contributions | |
Parenthood | -0.229 |
mination | -0.225 |
ILA | -0.220 |
FTA | -0.206 |
buster | -0.198 |
Token | when |
Token ID | 618 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Parenthood | +0.584 |
mination | +0.579 |
ILA | +0.562 |
FTA | +0.529 |
buster | +0.519 |
Neg logit contributions | |
cffff | -0.834 |
jri | -0.748 |
uberty | -0.722 |
odied | -0.697 |
attled | -0.663 |
Token | leading |
Token ID | 3756 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Parenthood | +0.271 |
mination | +0.268 |
ILA | +0.261 |
FTA | +0.249 |
buster | +0.244 |
Neg logit contributions | |
cffff | -0.313 |
jri | -0.278 |
uberty | -0.267 |
odied | -0.256 |
attled | -0.242 |
Token | after |
Token ID | 706 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Parenthood | +0.305 |
mination | +0.301 |
ILA | +0.292 |
FTA | +0.275 |
buster | +0.270 |
Neg logit contributions | |
cffff | -0.444 |
jri | -0.398 |
uberty | -0.384 |
odied | -0.370 |
attled | -0.352 |
Token | eight |
Token ID | 3624 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
Parenthood | +0.102 |
mination | +0.101 |
ILA | +0.098 |
FTA | +0.093 |
buster | +0.091 |
Neg logit contributions | |
cffff | -0.127 |
jri | -0.114 |
uberty | -0.110 |
odied | -0.105 |
attled | -0.100 |
Token | innings |
Token ID | 16267 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
cffff | +0.112 |
jri | +0.103 |
uberty | +0.100 |
odied | +0.097 |
attled | +0.094 |
Neg logit contributions | |
Parenthood | -0.038 |
mination | -0.038 |
ILA | -0.037 |
FTA | -0.032 |
buster | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
Parenthood | +2.181 |
mination | +2.150 |
ILA | +2.064 |
FTA | +1.976 |
buster | +1.948 |
Neg logit contributions | |
cffff | -3.036 |
jri | -2.719 |
uberty | -2.615 |
odied | -2.526 |
icter | -2.401 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Parenthood | +0.068 |
mination | +0.068 |
ILA | +0.066 |
FTA | +0.062 |
buster | +0.062 |
Neg logit contributions | |
cffff | -0.077 |
jri | -0.068 |
uberty | -0.066 |
odied | -0.063 |
attled | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
Parenthood | +0.121 |
mination | +0.121 |
ILA | +0.117 |
FTA | +0.110 |
buster | +0.108 |
Neg logit contributions | |
cffff | -0.143 |
jri | -0.128 |
uberty | -0.122 |
odied | -0.119 |
urses | -0.112 |
Token | That |
Token ID | 2504 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
Parenthood | +0.067 |
mination | +0.066 |
ILA | +0.064 |
FTA | +0.061 |
buster | +0.059 |
Neg logit contributions | |
cffff | -0.101 |
jri | -0.091 |
uberty | -0.088 |
odied | -0.085 |
attled | -0.081 |
Token | � |
Token ID | 447 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
cffff | +0.296 |
jri | +0.265 |
uberty | +0.255 |
odied | +0.245 |
attled | +0.233 |
Neg logit contributions | |
Parenthood | -0.240 |
mination | -0.238 |
ILA | -0.231 |
FTA | -0.218 |
buster | -0.215 |
Token |
|
Token ID | 198 |
Feature activation | -8.85e-02 |
Pos logit contributions | |
cffff | +0.048 |
jri | +0.043 |
uberty | +0.042 |
odied | +0.039 |
attled | +0.037 |
Neg logit contributions | |
mination | -0.041 |
Parenthood | -0.041 |
ILA | -0.040 |
FTA | -0.038 |
buster | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
Parenthood | +0.082 |
mination | +0.082 |
ILA | +0.080 |
FTA | +0.074 |
buster | +0.073 |
Neg logit contributions | |
cffff | -0.096 |
jri | -0.086 |
uberty | -0.083 |
odied | -0.080 |
urses | -0.076 |
Token | � |
Token ID | 447 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
Parenthood | +0.084 |
mination | +0.083 |
ILA | +0.080 |
FTA | +0.076 |
buster | +0.074 |
Neg logit contributions | |
cffff | -0.118 |
jri | -0.106 |
uberty | -0.103 |
odied | -0.099 |
attled | -0.094 |
Token | � |
Token ID | 250 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
cffff | +0.110 |
jri | +0.101 |
uberty | +0.099 |
odied | +0.096 |
attled | +0.092 |
Neg logit contributions | |
mination | -0.041 |
Parenthood | -0.041 |
ILA | -0.039 |
FTA | -0.036 |
buster | -0.035 |
Token | Teen |
Token ID | 45639 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
Parenthood | +0.241 |
mination | +0.238 |
ILA | +0.229 |
FTA | +0.218 |
buster | +0.212 |
Neg logit contributions | |
cffff | -0.370 |
jri | -0.333 |
uberty | -0.323 |
odied | -0.311 |
attled | -0.297 |
Token | agers |
Token ID | 10321 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
cffff | +0.016 |
jri | +0.014 |
uberty | +0.014 |
odied | +0.013 |
attled | +0.013 |
Neg logit contributions | |
Parenthood | -0.014 |
mination | -0.014 |
ILA | -0.014 |
FTA | -0.013 |
buster | -0.013 |
Token | are |
Token ID | 389 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
Parenthood | +2.301 |
mination | +2.260 |
ILA | +2.200 |
FTA | +2.094 |
buster | +2.064 |
Neg logit contributions | |
cffff | -2.828 |
jri | -2.524 |
uberty | -2.412 |
odied | -2.319 |
attled | -2.201 |
Token | often |
Token ID | 1690 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
cffff | +0.043 |
jri | +0.038 |
uberty | +0.037 |
odied | +0.035 |
attled | +0.033 |
Neg logit contributions | |
Parenthood | -0.040 |
mination | -0.039 |
ILA | -0.038 |
FTA | -0.036 |
buster | -0.036 |
Token | known |
Token ID | 1900 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
Parenthood | +0.249 |
mination | +0.249 |
ILA | +0.242 |
FTA | +0.230 |
buster | +0.227 |
Neg logit contributions | |
cffff | -0.244 |
jri | -0.214 |
uberty | -0.206 |
odied | -0.197 |
attled | -0.185 |
Token | for |
Token ID | 329 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Parenthood | +0.566 |
mination | +0.558 |
ILA | +0.538 |
FTA | +0.508 |
buster | +0.498 |
Neg logit contributions | |
cffff | -0.897 |
jri | -0.808 |
uberty | -0.782 |
odied | -0.755 |
attled | -0.720 |
Token | their |
Token ID | 511 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
cffff | +0.756 |
jri | +0.668 |
uberty | +0.646 |
odied | +0.616 |
attled | +0.583 |
Neg logit contributions | |
Parenthood | -0.687 |
mination | -0.683 |
ILA | -0.666 |
FTA | -0.630 |
buster | -0.621 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Parenthood | +0.315 |
mination | +0.312 |
ILA | +0.303 |
FTA | +0.286 |
buster | +0.281 |
Neg logit contributions | |
cffff | -0.429 |
jri | -0.384 |
uberty | -0.371 |
odied | -0.357 |
attled | -0.340 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Parenthood | +0.229 |
mination | +0.229 |
ILA | +0.223 |
FTA | +0.208 |
buster | +0.204 |
Neg logit contributions | |
cffff | -0.271 |
jri | -0.243 |
uberty | -0.233 |
odied | -0.226 |
urses | -0.214 |
Token | " |
Token ID | 1 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Parenthood | +0.171 |
mination | +0.169 |
ILA | +0.163 |
FTA | +0.154 |
buster | +0.151 |
Neg logit contributions | |
cffff | -0.261 |
jri | -0.235 |
uberty | -0.227 |
odied | -0.219 |
attled | -0.209 |
Token | The |
Token ID | 464 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
Parenthood | +0.413 |
mination | +0.406 |
ILA | +0.390 |
FTA | +0.369 |
buster | +0.358 |
Neg logit contributions | |
cffff | -0.739 |
jri | -0.676 |
uberty | -0.653 |
odied | -0.632 |
urses | -0.604 |
Token | two |
Token ID | 734 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
cffff | +0.032 |
jri | +0.029 |
uberty | +0.027 |
odied | +0.026 |
attled | +0.025 |
Neg logit contributions | |
Parenthood | -0.027 |
mination | -0.027 |
ILA | -0.026 |
FTA | -0.024 |
buster | -0.024 |
Token | innings |
Token ID | 16267 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Parenthood | +0.075 |
mination | +0.075 |
ILA | +0.073 |
FTA | +0.068 |
buster | +0.067 |
Neg logit contributions | |
cffff | -0.104 |
jri | -0.094 |
uberty | -0.090 |
odied | -0.087 |
attled | -0.083 |
Token | that |
Token ID | 326 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
Parenthood | +2.222 |
mination | +2.203 |
ILA | +2.134 |
FTA | +2.022 |
buster | +1.989 |
Neg logit contributions | |
cffff | -2.887 |
jri | -2.574 |
uberty | -2.482 |
odied | -2.389 |
attled | -2.267 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Parenthood | +0.019 |
mination | +0.019 |
ILA | +0.019 |
FTA | +0.018 |
buster | +0.017 |
Neg logit contributions | |
cffff | -0.028 |
jri | -0.025 |
uberty | -0.024 |
odied | -0.023 |
attled | -0.022 |
Token | me |
Token ID | 502 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
Parenthood | +0.165 |
mination | +0.163 |
ILA | +0.159 |
FTA | +0.150 |
buster | +0.147 |
Neg logit contributions | |
cffff | -0.212 |
jri | -0.189 |
uberty | -0.182 |
odied | -0.175 |
attled | -0.166 |
Token | the |
Token ID | 262 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
cffff | +0.073 |
jri | +0.065 |
uberty | +0.063 |
odied | +0.061 |
attled | +0.057 |
Neg logit contributions | |
Parenthood | -0.062 |
mination | -0.062 |
ILA | -0.060 |
FTA | -0.056 |
buster | -0.056 |
Token | most |
Token ID | 749 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
Parenthood | +0.431 |
mination | +0.429 |
ILA | +0.420 |
FTA | +0.397 |
buster | +0.392 |
Neg logit contributions | |
cffff | -0.429 |
jri | -0.379 |
uberty | -0.361 |
odied | -0.346 |
attled | -0.327 |
Token | West |
Token ID | 2688 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
cffff | +0.541 |
jri | +0.484 |
uberty | +0.466 |
odied | +0.449 |
attled | +0.426 |
Neg logit contributions | |
Parenthood | -0.415 |
mination | -0.411 |
ILA | -0.399 |
FTA | -0.376 |
buster | -0.370 |
Token | Indies |
Token ID | 42556 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Parenthood | +1.020 |
mination | +1.009 |
ILA | +0.977 |
FTA | +0.914 |
buster | +0.897 |
Neg logit contributions | |
cffff | -1.664 |
jri | -1.508 |
uberty | -1.455 |
odied | -1.408 |
attled | -1.342 |
Token | in |
Token ID | 287 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
cffff | +0.263 |
jri | +0.237 |
uberty | +0.226 |
odied | +0.219 |
attled | +0.209 |
Neg logit contributions | |
Parenthood | -0.192 |
mination | -0.191 |
ILA | -0.187 |
FTA | -0.173 |
buster | -0.170 |
Token | the |
Token ID | 262 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Parenthood | +0.369 |
mination | +0.367 |
ILA | +0.358 |
FTA | +0.340 |
buster | +0.335 |
Neg logit contributions | |
cffff | -0.395 |
jri | -0.350 |
uberty | -0.335 |
odied | -0.322 |
attled | -0.303 |
Token | second |
Token ID | 1218 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Parenthood | +0.242 |
mination | +0.240 |
ILA | +0.235 |
FTA | +0.219 |
buster | +0.217 |
Neg logit contributions | |
cffff | -0.305 |
jri | -0.275 |
uberty | -0.263 |
odied | -0.254 |
attled | -0.241 |
Token | innings |
Token ID | 16267 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
cffff | +0.549 |
jri | +0.503 |
uberty | +0.490 |
odied | +0.474 |
attled | +0.455 |
Neg logit contributions | |
Parenthood | -0.286 |
mination | -0.284 |
ILA | -0.277 |
FTA | -0.250 |
buster | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Parenthood | +2.024 |
mination | +2.005 |
ILA | +1.943 |
FTA | +1.827 |
buster | +1.791 |
Neg logit contributions | |
cffff | -3.009 |
jri | -2.704 |
uberty | -2.613 |
odied | -2.522 |
attled | -2.403 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
mination | +0.384 |
Parenthood | +0.380 |
ILA | +0.374 |
FTA | +0.350 |
buster | +0.347 |
Neg logit contributions | |
cffff | -0.439 |
jri | -0.393 |
uberty | -0.383 |
odied | -0.366 |
attled | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
mination | +0.274 |
Parenthood | +0.273 |
ILA | +0.267 |
FTA | +0.249 |
buster | +0.244 |
Neg logit contributions | |
cffff | -0.322 |
jri | -0.289 |
uberty | -0.276 |
odied | -0.267 |
urses | -0.253 |
Token | " |
Token ID | 1 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Parenthood | +0.246 |
mination | +0.245 |
ILA | +0.237 |
FTA | +0.221 |
buster | +0.217 |
Neg logit contributions | |
cffff | -0.398 |
jri | -0.359 |
uberty | -0.347 |
odied | -0.336 |
attled | -0.320 |
Token | When |
Token ID | 2215 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Parenthood | +0.576 |
mination | +0.568 |
ILA | +0.548 |
FTA | +0.518 |
buster | +0.503 |
Neg logit contributions | |
cffff | -0.986 |
jri | -0.899 |
uberty | -0.869 |
odied | -0.841 |
attled | -0.803 |
Token | The |
Token ID | 464 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Parenthood | +0.534 |
mination | +0.530 |
ILA | +0.513 |
FTA | +0.479 |
buster | +0.471 |
Neg logit contributions | |
cffff | -0.856 |
jri | -0.771 |
uberty | -0.747 |
odied | -0.721 |
attled | -0.688 |
Token | imminent |
Token ID | 21161 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
cffff | +0.319 |
jri | +0.283 |
uberty | +0.272 |
odied | +0.261 |
attled | +0.247 |
Neg logit contributions | |
Parenthood | -0.284 |
mination | -0.283 |
ILA | -0.275 |
FTA | -0.260 |
buster | -0.257 |
Token | merger |
Token ID | 24589 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
cffff | +0.430 |
jri | +0.377 |
uberty | +0.362 |
odied | +0.346 |
attled | +0.325 |
Neg logit contributions | |
Parenthood | -0.441 |
mination | -0.440 |
ILA | -0.429 |
FTA | -0.407 |
buster | -0.402 |
Token | between |
Token ID | 1022 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
Parenthood | +0.824 |
mination | +0.819 |
ILA | +0.789 |
FTA | +0.740 |
buster | +0.727 |
Neg logit contributions | |
cffff | -1.384 |
jri | -1.248 |
uberty | -1.205 |
odied | -1.167 |
attled | -1.112 |
Token | Time |
Token ID | 3862 |
Feature activation | +7.33e-03 |
Pos logit contributions | |
Parenthood | +0.031 |
mination | +0.031 |
ILA | +0.030 |
FTA | +0.029 |
buster | +0.028 |
Neg logit contributions | |
cffff | -0.039 |
jri | -0.035 |
uberty | -0.034 |
odied | -0.033 |
attled | -0.031 |
Token | Warner |
Token ID | 14469 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
cffff | +0.008 |
jri | +0.007 |
uberty | +0.007 |
odied | +0.007 |
attled | +0.006 |
Neg logit contributions | |
Parenthood | -0.007 |
mination | -0.007 |
ILA | -0.007 |
FTA | -0.006 |
buster | -0.006 |
Token | Cable |
Token ID | 20249 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Parenthood | +2.050 |
mination | +2.020 |
ILA | +1.962 |
FTA | +1.843 |
buster | +1.821 |
Neg logit contributions | |
cffff | -2.982 |
jri | -2.667 |
uberty | -2.582 |
odied | -2.488 |
attled | -2.365 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Parenthood | +0.433 |
mination | +0.430 |
ILA | +0.416 |
FTA | +0.392 |
buster | +0.384 |
Neg logit contributions | |
cffff | -0.627 |
jri | -0.563 |
uberty | -0.545 |
odied | -0.524 |
attled | -0.500 |
Token | Comcast |
Token ID | 21830 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
cffff | +0.124 |
jri | +0.111 |
uberty | +0.108 |
odied | +0.104 |
attled | +0.099 |
Neg logit contributions | |
Parenthood | -0.088 |
mination | -0.088 |
ILA | -0.085 |
FTA | -0.080 |
buster | -0.078 |
Token | herald |
Token ID | 28783 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Parenthood | +0.954 |
mination | +0.945 |
ILA | +0.918 |
FTA | +0.867 |
buster | +0.852 |
Neg logit contributions | |
cffff | -1.265 |
jri | -1.131 |
uberty | -1.090 |
odied | -1.050 |
attled | -0.997 |
Token | s |
Token ID | 82 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
cffff | +2.114 |
jri | +1.902 |
uberty | +1.838 |
odied | +1.784 |
attled | +1.715 |
Neg logit contributions | |
Parenthood | -1.284 |
mination | -1.269 |
ILA | -1.229 |
FTA | -1.150 |
buster | -1.127 |
Token | with |
Token ID | 351 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Parenthood | +0.127 |
mination | +0.126 |
ILA | +0.123 |
FTA | +0.115 |
buster | +0.114 |
Neg logit contributions | |
cffff | -0.158 |
jri | -0.140 |
uberty | -0.135 |
odied | -0.130 |
attled | -0.124 |
Token | little |
Token ID | 1310 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
cffff | +0.136 |
jri | +0.120 |
uberty | +0.116 |
odied | +0.111 |
attled | +0.105 |
Neg logit contributions | |
Parenthood | -0.117 |
mination | -0.116 |
ILA | -0.113 |
FTA | -0.107 |
buster | -0.105 |
Token | pressing |
Token ID | 12273 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Parenthood | +0.089 |
mination | +0.088 |
ILA | +0.087 |
FTA | +0.081 |
buster | +0.080 |
Neg logit contributions | |
cffff | -0.098 |
jri | -0.088 |
uberty | -0.084 |
odied | -0.081 |
attled | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
Parenthood | +0.180 |
mination | +0.179 |
ILA | +0.175 |
FTA | +0.164 |
buster | +0.161 |
Neg logit contributions | |
cffff | -0.229 |
jri | -0.205 |
uberty | -0.197 |
odied | -0.190 |
attled | -0.181 |
Token | few |
Token ID | 1178 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
cffff | +0.042 |
jri | +0.037 |
uberty | +0.036 |
odied | +0.035 |
attled | +0.033 |
Neg logit contributions | |
Parenthood | -0.036 |
mination | -0.035 |
ILA | -0.034 |
FTA | -0.032 |
buster | -0.032 |
Token | penet |
Token ID | 11958 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Parenthood | +0.342 |
mination | +0.339 |
ILA | +0.332 |
FTA | +0.314 |
buster | +0.310 |
Neg logit contributions | |
cffff | -0.353 |
jri | -0.311 |
uberty | -0.298 |
odied | -0.286 |
attled | -0.270 |
Token | rative |
Token ID | 13260 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
mination | +2.523 |
Parenthood | +2.513 |
ILA | +2.440 |
FTA | +2.338 |
buster | +2.307 |
Neg logit contributions | |
cffff | -2.469 |
jri | -2.182 |
uberty | -2.074 |
odied | -1.990 |
attled | -1.868 |
Token | runs |
Token ID | 4539 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Parenthood | +0.461 |
mination | +0.457 |
ILA | +0.446 |
FTA | +0.423 |
buster | +0.417 |
Neg logit contributions | |
cffff | -0.485 |
jri | -0.428 |
uberty | -0.410 |
odied | -0.394 |
attled | -0.372 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Parenthood | +0.965 |
mination | +0.957 |
ILA | +0.930 |
FTA | +0.881 |
buster | +0.866 |
Neg logit contributions | |
cffff | -1.184 |
jri | -1.053 |
uberty | -1.015 |
odied | -0.976 |
attled | -0.925 |
Token |
|
Token ID | 198 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Parenthood | +0.179 |
mination | +0.179 |
ILA | +0.174 |
FTA | +0.163 |
buster | +0.162 |
Neg logit contributions | |
cffff | -0.213 |
jri | -0.189 |
uberty | -0.185 |
odied | -0.177 |
attled | -0.167 |
Token |
|
Token ID | 198 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Parenthood | +0.250 |
mination | +0.250 |
ILA | +0.242 |
FTA | +0.228 |
buster | +0.224 |
Neg logit contributions | |
cffff | -0.310 |
jri | -0.277 |
uberty | -0.268 |
odied | -0.258 |
urses | -0.244 |
Token | ization |
Token ID | 1634 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
Parenthood | +0.172 |
mination | +0.169 |
ILA | +0.164 |
FTA | +0.153 |
buster | +0.150 |
Neg logit contributions | |
cffff | -0.303 |
jri | -0.274 |
uberty | -0.266 |
odied | -0.257 |
attled | -0.246 |
Token | and |
Token ID | 290 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
cffff | +0.046 |
jri | +0.042 |
uberty | +0.040 |
odied | +0.038 |
attled | +0.036 |
Neg logit contributions | |
Parenthood | -0.037 |
mination | -0.037 |
ILA | -0.035 |
FTA | -0.033 |
buster | -0.033 |
Token | details |
Token ID | 3307 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
Parenthood | +0.038 |
mination | +0.038 |
ILA | +0.037 |
FTA | +0.034 |
buster | +0.034 |
Neg logit contributions | |
cffff | -0.046 |
jri | -0.041 |
uberty | -0.039 |
odied | -0.038 |
attled | -0.036 |
Token | such |
Token ID | 884 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
Parenthood | +0.736 |
mination | +0.730 |
ILA | +0.708 |
FTA | +0.665 |
buster | +0.654 |
Neg logit contributions | |
cffff | -1.057 |
jri | -0.949 |
uberty | -0.915 |
odied | -0.883 |
attled | -0.842 |
Token | as |
Token ID | 355 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
mination | +0.560 |
Parenthood | +0.560 |
ILA | +0.545 |
FTA | +0.507 |
buster | +0.502 |
Neg logit contributions | |
cffff | -0.756 |
jri | -0.677 |
uberty | -0.650 |
odied | -0.629 |
attled | -0.598 |
Token | PV |
Token ID | 31392 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Parenthood | +0.294 |
mination | +0.292 |
ILA | +0.284 |
FTA | +0.266 |
buster | +0.263 |
Neg logit contributions | |
cffff | -0.381 |
jri | -0.340 |
uberty | -0.326 |
odied | -0.315 |
attled | -0.299 |
Token | vs |
Token ID | 3691 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
Parenthood | +2.131 |
mination | +2.112 |
ILA | +2.048 |
FTA | +1.935 |
buster | +1.901 |
Neg logit contributions | |
cffff | -2.879 |
jri | -2.575 |
uberty | -2.485 |
odied | -2.392 |
attled | -2.274 |
Token | PV |
Token ID | 31392 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
cffff | +0.051 |
jri | +0.045 |
uberty | +0.044 |
odied | +0.042 |
attled | +0.040 |
Neg logit contributions | |
Parenthood | -0.038 |
mination | -0.037 |
ILA | -0.036 |
FTA | -0.034 |
buster | -0.034 |
Token | H |
Token ID | 39 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Parenthood | +1.861 |
mination | +1.843 |
ILA | +1.783 |
FTA | +1.676 |
buster | +1.644 |
Neg logit contributions | |
cffff | -2.886 |
jri | -2.598 |
uberty | -2.512 |
odied | -2.425 |
attled | -2.313 |
Token | VM |
Token ID | 15996 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Parenthood | +0.145 |
mination | +0.143 |
ILA | +0.137 |
FTA | +0.129 |
buster | +0.126 |
Neg logit contributions | |
cffff | -0.251 |
jri | -0.227 |
uberty | -0.220 |
odied | -0.213 |
attled | -0.203 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Parenthood | +0.171 |
mination | +0.170 |
ILA | +0.166 |
FTA | +0.156 |
buster | +0.154 |
Neg logit contributions | |
cffff | -0.202 |
jri | -0.180 |
uberty | -0.173 |
odied | -0.165 |
attled | -0.157 |
Token | mer |
Token ID | 4017 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
cffff | +0.408 |
jri | +0.363 |
uberty | +0.349 |
odied | +0.336 |
attled | +0.318 |
Neg logit contributions | |
Parenthood | -0.339 |
mination | -0.337 |
ILA | -0.327 |
FTA | -0.310 |
buster | -0.305 |
Token | de |
Token ID | 2934 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Parenthood | +0.050 |
mination | +0.050 |
ILA | +0.049 |
FTA | +0.047 |
buster | +0.046 |
Neg logit contributions | |
cffff | -0.040 |
jri | -0.034 |
uberty | -0.033 |
odied | -0.031 |
attled | -0.029 |
Token | ,' |
Token ID | 4032 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
cffff | +0.124 |
jri | +0.111 |
uberty | +0.107 |
odied | +0.102 |
attled | +0.097 |
Neg logit contributions | |
Parenthood | -0.100 |
mination | -0.099 |
ILA | -0.097 |
FTA | -0.091 |
buster | -0.090 |
Token | said |
Token ID | 531 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Parenthood | +0.353 |
mination | +0.350 |
ILA | +0.340 |
FTA | +0.323 |
buster | +0.317 |
Neg logit contributions | |
cffff | -0.445 |
jri | -0.396 |
uberty | -0.382 |
odied | -0.367 |
attled | -0.348 |
Token | Michel |
Token ID | 12386 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Parenthood | +0.191 |
mination | +0.189 |
ILA | +0.184 |
FTA | +0.176 |
buster | +0.172 |
Neg logit contributions | |
cffff | -0.213 |
jri | -0.188 |
uberty | -0.181 |
odied | -0.174 |
attled | -0.164 |
Token | Plat |
Token ID | 32715 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Parenthood | +0.932 |
mination | +0.924 |
ILA | +0.897 |
FTA | +0.849 |
buster | +0.834 |
Neg logit contributions | |
cffff | -1.182 |
jri | -1.053 |
uberty | -1.015 |
odied | -0.977 |
attled | -0.926 |
Token | ini |
Token ID | 5362 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
Parenthood | +1.701 |
mination | +1.686 |
ILA | +1.622 |
FTA | +1.507 |
buster | +1.473 |
Neg logit contributions | |
cffff | -3.299 |
jri | -2.995 |
uberty | -2.903 |
odied | -2.809 |
attled | -2.692 |
Token | , |
Token ID | 11 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Parenthood | +0.699 |
mination | +0.693 |
ILA | +0.673 |
FTA | +0.636 |
buster | +0.624 |
Neg logit contributions | |
cffff | -0.929 |
jri | -0.830 |
uberty | -0.801 |
odied | -0.772 |
attled | -0.733 |
Token | president |
Token ID | 1893 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
Parenthood | +0.087 |
mination | +0.086 |
ILA | +0.084 |
FTA | +0.080 |
buster | +0.079 |
Neg logit contributions | |
cffff | -0.090 |
jri | -0.079 |
uberty | -0.076 |
odied | -0.073 |
attled | -0.068 |
Token | of |
Token ID | 286 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Parenthood | +0.003 |
mination | +0.003 |
ILA | +0.003 |
FTA | +0.003 |
buster | +0.003 |
Neg logit contributions | |
cffff | -0.006 |
jri | -0.005 |
uberty | -0.005 |
odied | -0.005 |
attled | -0.004 |
Token | UEFA |
Token ID | 40858 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
Parenthood | +0.104 |
mination | +0.103 |
ILA | +0.100 |
FTA | +0.096 |
buster | +0.093 |
Neg logit contributions | |
cffff | -0.125 |
jri | -0.112 |
uberty | -0.108 |
odied | -0.103 |
attled | -0.098 |
Token |
|
Token ID | 198 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
mination | +0.039 |
Parenthood | +0.039 |
ILA | +0.038 |
FTA | +0.036 |
buster | +0.035 |
Neg logit contributions | |
cffff | -0.045 |
jri | -0.041 |
uberty | -0.039 |
odied | -0.038 |
urses | -0.036 |
Token | see |
Token ID | 3826 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Parenthood | +0.032 |
mination | +0.031 |
ILA | +0.030 |
FTA | +0.029 |
buster | +0.028 |
Neg logit contributions | |
cffff | -0.050 |
jri | -0.045 |
uberty | -0.043 |
odied | -0.042 |
attled | -0.040 |
Token | also |
Token ID | 635 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
Parenthood | +0.189 |
mination | +0.188 |
ILA | +0.183 |
FTA | +0.173 |
buster | +0.170 |
Neg logit contributions | |
cffff | -0.238 |
jri | -0.211 |
uberty | -0.203 |
odied | -0.196 |
urses | -0.185 |
Token | Trump |
Token ID | 1301 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Parenthood | +0.039 |
mination | +0.039 |
ILA | +0.037 |
FTA | +0.035 |
buster | +0.035 |
Neg logit contributions | |
cffff | -0.052 |
jri | -0.047 |
uberty | -0.045 |
odied | -0.043 |
attled | -0.041 |
Token | warns |
Token ID | 22145 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Parenthood | +0.291 |
mination | +0.289 |
ILA | +0.281 |
FTA | +0.267 |
buster | +0.263 |
Neg logit contributions | |
cffff | -0.331 |
jri | -0.294 |
uberty | -0.282 |
odied | -0.271 |
attled | -0.257 |
Token | Mueller |
Token ID | 17768 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
cffff | +0.362 |
jri | +0.323 |
uberty | +0.311 |
odied | +0.299 |
attled | +0.285 |
Neg logit contributions | |
Parenthood | -0.282 |
mination | -0.281 |
ILA | -0.272 |
FTA | -0.257 |
buster | -0.253 |
Token | not |
Token ID | 407 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Parenthood | +2.183 |
mination | +2.154 |
ILA | +2.091 |
FTA | +1.992 |
buster | +1.959 |
Neg logit contributions | |
cffff | -2.799 |
jri | -2.496 |
uberty | -2.412 |
odied | -2.325 |
attled | -2.185 |
Token | to |
Token ID | 284 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Parenthood | +0.117 |
mination | +0.116 |
ILA | +0.112 |
FTA | +0.104 |
buster | +0.102 |
Neg logit contributions | |
cffff | -0.192 |
jri | -0.173 |
uberty | -0.167 |
odied | -0.162 |
attled | -0.155 |
Token | probe |
Token ID | 12774 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
cffff | +0.166 |
jri | +0.146 |
uberty | +0.140 |
odied | +0.134 |
attled | +0.128 |
Neg logit contributions | |
Parenthood | -0.154 |
mination | -0.154 |
ILA | -0.150 |
FTA | -0.140 |
buster | -0.138 |
Token | into |
Token ID | 656 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Parenthood | +0.716 |
mination | +0.710 |
ILA | +0.690 |
FTA | +0.654 |
buster | +0.642 |
Neg logit contributions | |
cffff | -0.889 |
jri | -0.791 |
uberty | -0.762 |
odied | -0.733 |
attled | -0.695 |
Token | his |
Token ID | 465 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
cffff | +0.239 |
jri | +0.212 |
uberty | +0.204 |
odied | +0.196 |
attled | +0.186 |
Neg logit contributions | |
Parenthood | -0.201 |
mination | -0.200 |
ILA | -0.194 |
FTA | -0.184 |
buster | -0.181 |
Token | log |
Token ID | 6404 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
Parenthood | +0.320 |
mination | +0.317 |
ILA | +0.307 |
FTA | +0.289 |
buster | +0.284 |
Neg logit contributions | |
cffff | -0.470 |
jri | -0.422 |
uberty | -0.408 |
odied | -0.393 |
attled | -0.374 |
Token | y |
Token ID | 88 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
cffff | +0.097 |
jri | +0.086 |
uberty | +0.083 |
odied | +0.080 |
attled | +0.076 |
Neg logit contributions | |
Parenthood | -0.078 |
mination | -0.078 |
ILA | -0.076 |
FTA | -0.072 |
buster | -0.070 |
Token | - |
Token ID | 12 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Parenthood | +0.536 |
mination | +0.532 |
ILA | +0.515 |
FTA | +0.484 |
buster | +0.475 |
Neg logit contributions | |
cffff | -0.795 |
jri | -0.715 |
uberty | -0.692 |
odied | -0.668 |
attled | -0.636 |
Token | Jimmy |
Token ID | 40335 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Parenthood | +0.353 |
mination | +0.350 |
ILA | +0.338 |
FTA | +0.319 |
buster | +0.312 |
Neg logit contributions | |
cffff | -0.529 |
jri | -0.477 |
uberty | -0.461 |
odied | -0.446 |
attled | -0.424 |
Token | & |
Token ID | 5 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Parenthood | +0.269 |
mination | +0.267 |
ILA | +0.259 |
FTA | +0.244 |
buster | +0.240 |
Neg logit contributions | |
cffff | -0.353 |
jri | -0.316 |
uberty | -0.305 |
odied | -0.293 |
attled | -0.279 |
Token | GF |
Token ID | 21713 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Parenthood | +0.363 |
mination | +0.360 |
ILA | +0.348 |
FTA | +0.328 |
buster | +0.321 |
Neg logit contributions | |
cffff | -0.543 |
jri | -0.489 |
uberty | -0.472 |
odied | -0.456 |
attled | -0.434 |
Token | Break |
Token ID | 12243 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Parenthood | +2.084 |
mination | +2.065 |
ILA | +1.999 |
FTA | +1.891 |
buster | +1.858 |
Neg logit contributions | |
cffff | -2.894 |
jri | -2.588 |
uberty | -2.496 |
odied | -2.403 |
attled | -2.285 |
Token | Up |
Token ID | 3205 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
Parenthood | +0.872 |
mination | +0.864 |
ILA | +0.838 |
FTA | +0.786 |
buster | +0.770 |
Neg logit contributions | |
cffff | -1.322 |
jri | -1.189 |
uberty | -1.150 |
odied | -1.111 |
attled | -1.058 |
Token | - |
Token ID | 12 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Parenthood | +0.431 |
mination | +0.428 |
ILA | +0.416 |
FTA | +0.391 |
buster | +0.384 |
Neg logit contributions | |
cffff | -0.596 |
jri | -0.535 |
uberty | -0.518 |
odied | -0.499 |
attled | -0.475 |
Token | Fake |
Token ID | 49233 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
Parenthood | +0.326 |
mination | +0.324 |
ILA | +0.312 |
FTA | +0.296 |
buster | +0.289 |
Neg logit contributions | |
cffff | -0.490 |
jri | -0.443 |
uberty | -0.427 |
odied | -0.413 |
attled | -0.393 |
Token | Teen |
Token ID | 21432 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
mination | +0.580 |
Parenthood | +0.580 |
ILA | +0.564 |
FTA | +0.530 |
buster | +0.520 |
Neg logit contributions | |
cffff | -0.738 |
jri | -0.659 |
uberty | -0.637 |
odied | -0.613 |
attled | -0.581 |
Token | és |
Token ID | 20954 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
Parenthood | +0.473 |
mination | +0.471 |
ILA | +0.461 |
FTA | +0.444 |
buster | +0.439 |
Neg logit contributions | |
cffff | -0.278 |
jri | -0.232 |
uberty | -0.219 |
odied | -0.205 |
attled | -0.187 |
Token | et |
Token ID | 2123 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
cffff | +0.303 |
jri | +0.271 |
uberty | +0.261 |
odied | +0.251 |
attled | +0.238 |
Neg logit contributions | |
Parenthood | -0.236 |
mination | -0.234 |
ILA | -0.228 |
FTA | -0.214 |
buster | -0.211 |
Token | le |
Token ID | 443 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
cffff | +0.047 |
jri | +0.042 |
uberty | +0.041 |
odied | +0.039 |
attled | +0.037 |
Neg logit contributions | |
Parenthood | -0.037 |
mination | -0.037 |
ILA | -0.036 |
FTA | -0.034 |
buster | -0.033 |
Token | ur |
Token ID | 333 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
Parenthood | +1.002 |
mination | +0.993 |
ILA | +0.968 |
FTA | +0.919 |
buster | +0.905 |
Neg logit contributions | |
cffff | -1.105 |
jri | -0.978 |
uberty | -0.940 |
odied | -0.901 |
attled | -0.851 |
Token | dé |
Token ID | 39073 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
cffff | +0.724 |
jri | +0.643 |
uberty | +0.616 |
odied | +0.592 |
attled | +0.559 |
Neg logit contributions | |
Parenthood | -0.641 |
mination | -0.633 |
ILA | -0.621 |
FTA | -0.584 |
buster | -0.578 |
Token | part |
Token ID | 3911 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
cffff | +0.487 |
jri | +0.439 |
uberty | +0.423 |
odied | +0.409 |
attled | +0.388 |
Neg logit contributions | |
Parenthood | -0.331 |
mination | -0.324 |
ILA | -0.318 |
FTA | -0.299 |
buster | -0.291 |
Token | est |
Token ID | 1556 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Parenthood | +2.197 |
mination | +2.186 |
ILA | +2.113 |
FTA | +2.012 |
buster | +1.978 |
Neg logit contributions | |
cffff | -2.752 |
jri | -2.446 |
uberty | -2.361 |
odied | -2.268 |
attled | -2.157 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
cffff | +0.113 |
jri | +0.101 |
uberty | +0.097 |
odied | +0.093 |
attled | +0.088 |
Neg logit contributions | |
Parenthood | -0.094 |
mination | -0.093 |
ILA | -0.090 |
FTA | -0.085 |
buster | -0.084 |
Token | uss |
Token ID | 1046 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
Parenthood | +0.149 |
mination | +0.147 |
ILA | +0.143 |
FTA | +0.136 |
buster | +0.134 |
Neg logit contributions | |
cffff | -0.162 |
jri | -0.144 |
uberty | -0.138 |
odied | -0.133 |
attled | -0.125 |
Token | i |
Token ID | 72 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Parenthood | +0.046 |
mination | +0.045 |
ILA | +0.044 |
FTA | +0.041 |
buster | +0.040 |
Neg logit contributions | |
cffff | -0.081 |
jri | -0.073 |
uberty | -0.071 |
odied | -0.069 |
attled | -0.066 |
Token | sur |
Token ID | 969 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Parenthood | +0.195 |
mination | +0.193 |
ILA | +0.188 |
FTA | +0.178 |
buster | +0.175 |
Neg logit contributions | |
cffff | -0.240 |
jri | -0.214 |
uberty | -0.206 |
odied | -0.198 |
attled | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
cffff | +0.153 |
jri | +0.137 |
uberty | +0.131 |
odied | +0.127 |
urses | +0.121 |
Neg logit contributions | |
mination | -0.131 |
Parenthood | -0.130 |
ILA | -0.127 |
FTA | -0.119 |
buster | -0.117 |
Token | Along |
Token ID | 24035 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
cffff | +0.152 |
jri | +0.137 |
uberty | +0.133 |
odied | +0.128 |
attled | +0.122 |
Neg logit contributions | |
Parenthood | -0.103 |
mination | -0.102 |
ILA | -0.098 |
FTA | -0.093 |
buster | -0.091 |
Token | side |
Token ID | 1589 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Parenthood | +0.387 |
mination | +0.384 |
ILA | +0.372 |
FTA | +0.351 |
buster | +0.344 |
Neg logit contributions | |
cffff | -0.554 |
jri | -0.497 |
uberty | -0.480 |
odied | -0.463 |
attled | -0.441 |
Token | efforts |
Token ID | 4040 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
cffff | +0.215 |
jri | +0.191 |
uberty | +0.183 |
odied | +0.175 |
attled | +0.166 |
Neg logit contributions | |
Parenthood | -0.194 |
mination | -0.193 |
ILA | -0.188 |
FTA | -0.177 |
buster | -0.176 |
Token | at |
Token ID | 379 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Parenthood | +0.777 |
mination | +0.768 |
ILA | +0.743 |
FTA | +0.698 |
buster | +0.683 |
Neg logit contributions | |
cffff | -1.256 |
jri | -1.132 |
uberty | -1.096 |
odied | -1.059 |
attled | -1.010 |
Token | separation |
Token ID | 14139 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Parenthood | +0.506 |
mination | +0.504 |
ILA | +0.492 |
FTA | +0.465 |
buster | +0.462 |
Neg logit contributions | |
cffff | -0.509 |
jri | -0.448 |
uberty | -0.428 |
odied | -0.410 |
attled | -0.386 |
Token | between |
Token ID | 1022 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
Parenthood | +2.083 |
mination | +2.063 |
ILA | +1.993 |
FTA | +1.895 |
buster | +1.863 |
Neg logit contributions | |
cffff | -2.849 |
jri | -2.536 |
uberty | -2.447 |
odied | -2.367 |
attled | -2.249 |
Token | Palestinian |
Token ID | 8501 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Parenthood | +0.455 |
mination | +0.453 |
ILA | +0.440 |
FTA | +0.416 |
buster | +0.411 |
Neg logit contributions | |
cffff | -0.520 |
jri | -0.461 |
uberty | -0.444 |
odied | -0.426 |
attled | -0.403 |
Token | people |
Token ID | 661 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
Parenthood | +0.956 |
mination | +0.951 |
ILA | +0.923 |
FTA | +0.874 |
buster | +0.860 |
Neg logit contributions | |
cffff | -1.191 |
jri | -1.061 |
uberty | -1.023 |
odied | -0.985 |
attled | -0.933 |
Token | and |
Token ID | 290 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
cffff | +0.878 |
jri | +0.788 |
uberty | +0.758 |
odied | +0.733 |
attled | +0.696 |
Neg logit contributions | |
Parenthood | -0.626 |
mination | -0.622 |
ILA | -0.603 |
FTA | -0.567 |
buster | -0.557 |
Token | land |
Token ID | 1956 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
cffff | +0.030 |
jri | +0.027 |
uberty | +0.026 |
odied | +0.025 |
attled | +0.023 |
Neg logit contributions | |
Parenthood | -0.030 |
mination | -0.030 |
ILA | -0.029 |
FTA | -0.028 |
buster | -0.027 |
Token | Aff |
Token ID | 6708 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Parenthood | +0.064 |
mination | +0.064 |
ILA | +0.062 |
FTA | +0.059 |
buster | +0.058 |
Neg logit contributions | |
cffff | -0.076 |
jri | -0.068 |
uberty | -0.065 |
odied | -0.063 |
attled | -0.059 |
Token | ili |
Token ID | 2403 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
Parenthood | +1.362 |
mination | +1.360 |
ILA | +1.318 |
FTA | +1.250 |
buster | +1.233 |
Neg logit contributions | |
cffff | -1.523 |
jri | -1.342 |
uberty | -1.288 |
odied | -1.231 |
attled | -1.165 |
Token | ative |
Token ID | 876 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
mination | +1.140 |
Parenthood | +1.140 |
ILA | +1.112 |
FTA | +1.066 |
buster | +1.052 |
Neg logit contributions | |
cffff | -0.835 |
jri | -0.712 |
uberty | -0.675 |
odied | -0.640 |
attled | -0.595 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
Parenthood | +1.095 |
mination | +1.086 |
ILA | +1.058 |
FTA | +1.007 |
buster | +0.991 |
Neg logit contributions | |
cffff | -1.159 |
jri | -1.022 |
uberty | -0.981 |
odied | -0.940 |
attled | -0.886 |
Token | aggressive |
Token ID | 8361 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Parenthood | +0.027 |
mination | +0.027 |
ILA | +0.027 |
FTA | +0.025 |
buster | +0.025 |
Neg logit contributions | |
cffff | -0.025 |
jri | -0.022 |
uberty | -0.021 |
odied | -0.020 |
attled | -0.019 |
Token | dimensions |
Token ID | 15225 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Parenthood | +2.056 |
mination | +2.037 |
ILA | +1.980 |
FTA | +1.888 |
buster | +1.857 |
Neg logit contributions | |
cffff | -2.220 |
jri | -1.958 |
uberty | -1.880 |
odied | -1.802 |
attled | -1.701 |
Token | and |
Token ID | 290 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Parenthood | +1.964 |
mination | +1.936 |
ILA | +1.874 |
FTA | +1.773 |
buster | +1.740 |
Neg logit contributions | |
cffff | -2.964 |
jri | -2.641 |
uberty | -2.557 |
odied | -2.454 |
attled | -2.343 |
Token | possible |
Token ID | 1744 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
Parenthood | +0.271 |
mination | +0.270 |
ILA | +0.263 |
FTA | +0.250 |
buster | +0.247 |
Neg logit contributions | |
cffff | -0.270 |
jri | -0.238 |
uberty | -0.228 |
odied | -0.218 |
attled | -0.205 |
Token | functions |
Token ID | 5499 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
cffff | +0.143 |
jri | +0.125 |
uberty | +0.120 |
odied | +0.115 |
attled | +0.107 |
Neg logit contributions | |
mination | -0.154 |
Parenthood | -0.153 |
ILA | -0.150 |
FTA | -0.142 |
buster | -0.141 |
Token | . |
Token ID | 764 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Parenthood | +0.858 |
mination | +0.847 |
ILA | +0.818 |
FTA | +0.772 |
buster | +0.755 |
Neg logit contributions | |
cffff | -1.335 |
jri | -1.197 |
uberty | -1.159 |
odied | -1.117 |
attled | -1.067 |
Token | Merrill |
Token ID | 40418 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
Parenthood | +0.185 |
mination | +0.183 |
ILA | +0.179 |
FTA | +0.171 |
buster | +0.168 |
Neg logit contributions | |
cffff | -0.175 |
jri | -0.153 |
uberty | -0.147 |
odied | -0.140 |
attled | -0.132 |
Token | media |
Token ID | 2056 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
cffff | +0.738 |
jri | +0.651 |
uberty | +0.624 |
odied | +0.597 |
attled | +0.564 |
Neg logit contributions | |
Parenthood | -0.702 |
mination | -0.697 |
ILA | -0.679 |
FTA | -0.645 |
buster | -0.637 |
Token | outlets |
Token ID | 12527 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
cffff | +0.057 |
jri | +0.049 |
uberty | +0.047 |
odied | +0.045 |
attled | +0.042 |
Neg logit contributions | |
Parenthood | -0.063 |
mination | -0.063 |
ILA | -0.062 |
FTA | -0.059 |
buster | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
cffff | +0.388 |
jri | +0.345 |
uberty | +0.332 |
odied | +0.319 |
attled | +0.302 |
Neg logit contributions | |
Parenthood | -0.323 |
mination | -0.320 |
ILA | -0.311 |
FTA | -0.295 |
buster | -0.290 |
Token | including |
Token ID | 1390 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Parenthood | +0.082 |
mination | +0.082 |
ILA | +0.079 |
FTA | +0.075 |
buster | +0.074 |
Neg logit contributions | |
cffff | -0.097 |
jri | -0.086 |
uberty | -0.083 |
odied | -0.080 |
attled | -0.076 |
Token | The |
Token ID | 383 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Parenthood | +0.156 |
mination | +0.154 |
ILA | +0.150 |
FTA | +0.144 |
buster | +0.140 |
Neg logit contributions | |
cffff | -0.179 |
jri | -0.158 |
uberty | -0.152 |
odied | -0.147 |
attled | -0.138 |
Token | Herald |
Token ID | 18277 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
cffff | +0.139 |
jri | +0.123 |
uberty | +0.118 |
odied | +0.112 |
attled | +0.106 |
Neg logit contributions | |
Parenthood | -0.140 |
mination | -0.140 |
ILA | -0.136 |
FTA | -0.129 |
buster | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
cffff | +2.288 |
jri | +2.044 |
uberty | +1.975 |
odied | +1.900 |
attled | +1.810 |
Neg logit contributions | |
Parenthood | -1.761 |
mination | -1.747 |
ILA | -1.690 |
FTA | -1.594 |
buster | -1.573 |
Token | � |
Token ID | 564 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Parenthood | +0.249 |
mination | +0.248 |
ILA | +0.240 |
FTA | +0.227 |
buster | +0.224 |
Neg logit contributions | |
cffff | -0.318 |
jri | -0.285 |
uberty | -0.274 |
odied | -0.264 |
attled | -0.251 |
Token | � |
Token ID | 250 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
cffff | +0.150 |
jri | +0.136 |
uberty | +0.132 |
odied | +0.128 |
attled | +0.122 |
Neg logit contributions | |
Parenthood | -0.082 |
mination | -0.081 |
ILA | -0.078 |
FTA | -0.073 |
buster | -0.072 |
Token | Mr |
Token ID | 5246 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
Parenthood | +0.361 |
mination | +0.358 |
ILA | +0.346 |
FTA | +0.328 |
buster | +0.322 |
Neg logit contributions | |
cffff | -0.491 |
jri | -0.440 |
uberty | -0.424 |
odied | -0.408 |
attled | -0.388 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Parenthood | +0.863 |
mination | +0.852 |
ILA | +0.830 |
FTA | +0.787 |
buster | +0.772 |
Neg logit contributions | |
cffff | -1.062 |
jri | -0.941 |
uberty | -0.906 |
odied | -0.874 |
attled | -0.827 |
Token | well |
Token ID | 880 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Parenthood | +0.078 |
mination | +0.077 |
ILA | +0.075 |
FTA | +0.071 |
buster | +0.070 |
Neg logit contributions | |
cffff | -0.089 |
jri | -0.079 |
uberty | -0.076 |
odied | -0.073 |
attled | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
cffff | +0.253 |
jri | +0.225 |
uberty | +0.216 |
odied | +0.208 |
attled | +0.197 |
Neg logit contributions | |
Parenthood | -0.211 |
mination | -0.209 |
ILA | -0.204 |
FTA | -0.193 |
buster | -0.190 |
Token |
|
Token ID | 198 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
cffff | +0.053 |
jri | +0.047 |
uberty | +0.046 |
odied | +0.044 |
attled | +0.041 |
Neg logit contributions | |
mination | -0.048 |
Parenthood | -0.047 |
ILA | -0.046 |
FTA | -0.043 |
buster | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
cffff | +0.101 |
jri | +0.091 |
uberty | +0.087 |
odied | +0.084 |
urses | +0.080 |
Neg logit contributions | |
mination | -0.086 |
Parenthood | -0.086 |
ILA | -0.084 |
FTA | -0.078 |
buster | -0.077 |
Token | Occ |
Token ID | 29223 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
cffff | +0.165 |
jri | +0.149 |
uberty | +0.144 |
odied | +0.139 |
attled | +0.132 |
Neg logit contributions | |
Parenthood | -0.113 |
mination | -0.112 |
ILA | -0.108 |
FTA | -0.102 |
buster | -0.100 |
Token | asionally |
Token ID | 31775 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
cffff | +0.235 |
jri | +0.205 |
uberty | +0.196 |
odied | +0.187 |
attled | +0.175 |
Neg logit contributions | |
Parenthood | -0.268 |
mination | -0.266 |
ILA | -0.260 |
FTA | -0.249 |
buster | -0.245 |
Token | dismissed |
Token ID | 11126 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
cffff | +1.774 |
jri | +1.587 |
uberty | +1.532 |
odied | +1.478 |
attled | +1.394 |
Neg logit contributions | |
mination | -1.459 |
Parenthood | -1.456 |
ILA | -1.415 |
FTA | -1.334 |
buster | -1.315 |
Token | as |
Token ID | 355 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
cffff | +0.296 |
jri | +0.265 |
uberty | +0.257 |
odied | +0.248 |
attled | +0.235 |
Neg logit contributions | |
Parenthood | -0.210 |
mination | -0.209 |
ILA | -0.203 |
FTA | -0.190 |
buster | -0.187 |
Token | a |
Token ID | 257 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
cffff | +0.074 |
jri | +0.066 |
uberty | +0.064 |
odied | +0.061 |
attled | +0.058 |
Neg logit contributions | |
Parenthood | -0.063 |
mination | -0.063 |
ILA | -0.061 |
FTA | -0.058 |
buster | -0.057 |
Token | one |
Token ID | 530 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
cffff | +0.075 |
jri | +0.067 |
uberty | +0.064 |
odied | +0.061 |
attled | +0.058 |
Neg logit contributions | |
Parenthood | -0.064 |
mination | -0.064 |
ILA | -0.062 |
FTA | -0.059 |
buster | -0.058 |
Token | - |
Token ID | 12 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Parenthood | +0.346 |
mination | +0.343 |
ILA | +0.332 |
FTA | +0.312 |
buster | +0.304 |
Neg logit contributions | |
cffff | -0.525 |
jri | -0.474 |
uberty | -0.458 |
odied | -0.443 |
attled | -0.421 |
Token | - |
Token ID | 532 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
cffff | +0.394 |
jri | +0.360 |
uberty | +0.348 |
odied | +0.337 |
attled | +0.324 |
Neg logit contributions | |
Parenthood | -0.215 |
mination | -0.212 |
ILA | -0.205 |
FTA | -0.189 |
buster | -0.186 |
Token | Kirk |
Token ID | 13855 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
Parenthood | +0.073 |
mination | +0.072 |
ILA | +0.070 |
FTA | +0.067 |
buster | +0.066 |
Neg logit contributions | |
cffff | -0.081 |
jri | -0.071 |
uberty | -0.068 |
odied | -0.066 |
attled | -0.062 |
Token | Cousins |
Token ID | 32644 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
cffff | +0.061 |
jri | +0.054 |
uberty | +0.052 |
odied | +0.050 |
attled | +0.048 |
Neg logit contributions | |
Parenthood | -0.047 |
mination | -0.047 |
ILA | -0.046 |
FTA | -0.043 |
buster | -0.042 |
Token | (@ |
Token ID | 4275 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
cffff | +0.149 |
jri | +0.136 |
uberty | +0.131 |
odied | +0.127 |
attled | +0.121 |
Neg logit contributions | |
Parenthood | -0.085 |
mination | -0.084 |
ILA | -0.081 |
FTA | -0.075 |
buster | -0.074 |
Token | K |
Token ID | 42 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
Parenthood | +0.064 |
mination | +0.064 |
ILA | +0.061 |
FTA | +0.057 |
buster | +0.056 |
Neg logit contributions | |
cffff | -0.122 |
jri | -0.110 |
uberty | -0.107 |
odied | -0.104 |
attled | -0.099 |
Token | irk |
Token ID | 14232 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Parenthood | +0.429 |
mination | +0.425 |
ILA | +0.413 |
FTA | +0.392 |
buster | +0.385 |
Neg logit contributions | |
cffff | -0.514 |
jri | -0.457 |
uberty | -0.440 |
odied | -0.422 |
attled | -0.400 |
Token | C |
Token ID | 34 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
cffff | +2.250 |
jri | +2.042 |
uberty | +1.950 |
odied | +1.902 |
attled | +1.807 |
Neg logit contributions | |
Parenthood | -1.478 |
mination | -1.429 |
ILA | -1.394 |
FTA | -1.324 |
buster | -1.266 |
Token | ous |
Token ID | 516 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
cffff | +0.784 |
jri | +0.691 |
uberty | +0.663 |
odied | +0.636 |
attled | +0.599 |
Neg logit contributions | |
Parenthood | -0.722 |
mination | -0.718 |
ILA | -0.698 |
FTA | -0.664 |
buster | -0.655 |
Token | ins |
Token ID | 1040 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
cffff | +0.739 |
jri | +0.669 |
uberty | +0.632 |
odied | +0.613 |
urses | +0.576 |
Neg logit contributions | |
Parenthood | -0.697 |
ILA | -0.676 |
mination | -0.673 |
FTA | -0.640 |
buster | -0.616 |
Token | 8 |
Token ID | 23 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
cffff | +0.526 |
jri | +0.478 |
uberty | +0.460 |
odied | +0.445 |
attled | +0.426 |
Neg logit contributions | |
Parenthood | -0.330 |
mination | -0.323 |
ILA | -0.311 |
FTA | -0.292 |
buster | -0.286 |
Token | ) |
Token ID | 8 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
Parenthood | +0.280 |
mination | +0.276 |
ILA | +0.267 |
FTA | +0.250 |
buster | +0.245 |
Neg logit contributions | |
cffff | -0.456 |
jri | -0.411 |
uberty | -0.398 |
odied | -0.385 |
attled | -0.367 |
Token | : |
Token ID | 25 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Parenthood | +0.736 |
mination | +0.731 |
ILA | +0.713 |
FTA | +0.675 |
buster | +0.662 |
Neg logit contributions | |
cffff | -0.866 |
jri | -0.768 |
uberty | -0.737 |
odied | -0.709 |
attled | -0.671 |
Token | Yes |
Token ID | 3363 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
cffff | +0.215 |
jri | +0.191 |
uberty | +0.186 |
odied | +0.178 |
attled | +0.168 |
Neg logit contributions | |
mination | -0.186 |
Parenthood | -0.184 |
ILA | -0.180 |
FTA | -0.170 |
buster | -0.169 |
Token | ! |
Token ID | 0 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
cffff | +0.263 |
jri | +0.234 |
uberty | +0.226 |
odied | +0.217 |
attled | +0.206 |
Neg logit contributions | |
Parenthood | -0.204 |
mination | -0.202 |
ILA | -0.196 |
FTA | -0.185 |
buster | -0.182 |
Token | I |
Token ID | 314 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
cffff | +0.219 |
jri | +0.195 |
uberty | +0.190 |
odied | +0.182 |
urses | +0.171 |
Neg logit contributions | |
mination | -0.183 |
Parenthood | -0.181 |
ILA | -0.176 |
FTA | -0.166 |
buster | -0.165 |
Token | think |
Token ID | 892 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
cffff | +0.243 |
jri | +0.215 |
uberty | +0.207 |
odied | +0.199 |
attled | +0.188 |
Neg logit contributions | |
Parenthood | -0.216 |
mination | -0.215 |
ILA | -0.208 |
FTA | -0.197 |
buster | -0.195 |
Token | Claire |
Token ID | 20758 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
cffff | +0.181 |
jri | +0.162 |
uberty | +0.156 |
odied | +0.150 |
attled | +0.142 |
Neg logit contributions | |
Parenthood | -0.146 |
mination | -0.146 |
ILA | -0.141 |
FTA | -0.134 |
buster | -0.131 |
Token | even |
Token ID | 772 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
cffff | +1.984 |
jri | +1.770 |
uberty | +1.716 |
odied | +1.648 |
attled | +1.561 |
Neg logit contributions | |
Parenthood | -1.508 |
mination | -1.499 |
ILA | -1.455 |
FTA | -1.374 |
buster | -1.350 |
Token | comments |
Token ID | 3651 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
cffff | +0.018 |
jri | +0.016 |
uberty | +0.015 |
odied | +0.015 |
attled | +0.014 |
Neg logit contributions | |
Parenthood | -0.018 |
mination | -0.018 |
ILA | -0.017 |
FTA | -0.016 |
buster | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Parenthood | +0.344 |
mination | +0.342 |
ILA | +0.332 |
FTA | +0.313 |
buster | +0.308 |
Neg logit contributions | |
cffff | -0.434 |
jri | -0.387 |
uberty | -0.373 |
odied | -0.359 |
attled | -0.340 |
Token | when |
Token ID | 618 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
cffff | +0.266 |
jri | +0.236 |
uberty | +0.228 |
odied | +0.219 |
attled | +0.207 |
Neg logit contributions | |
Parenthood | -0.223 |
mination | -0.222 |
ILA | -0.216 |
FTA | -0.204 |
buster | -0.201 |
Token | she |
Token ID | 673 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Parenthood | +0.363 |
mination | +0.359 |
ILA | +0.349 |
FTA | +0.332 |
buster | +0.326 |
Neg logit contributions | |
cffff | -0.412 |
jri | -0.365 |
uberty | -0.350 |
odied | -0.337 |
attled | -0.318 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
Parenthood | +0.860 |
mination | +0.851 |
ILA | +0.829 |
FTA | +0.784 |
buster | +0.764 |
Neg logit contributions | |
cffff | -1.060 |
jri | -0.942 |
uberty | -0.908 |
odied | -0.873 |
attled | -0.829 |
Token | As |
Token ID | 1081 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
mination | +0.049 |
Parenthood | +0.048 |
ILA | +0.047 |
FTA | +0.044 |
buster | +0.044 |
Neg logit contributions | |
cffff | -0.056 |
jri | -0.050 |
uberty | -0.048 |
odied | -0.046 |
attled | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
cffff | +0.412 |
jri | +0.367 |
uberty | +0.354 |
odied | +0.341 |
attled | +0.323 |
Neg logit contributions | |
Parenthood | -0.333 |
mination | -0.330 |
ILA | -0.320 |
FTA | -0.304 |
buster | -0.298 |
Token | Sh |
Token ID | 911 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
cffff | +0.013 |
jri | +0.012 |
uberty | +0.011 |
odied | +0.011 |
attled | +0.010 |
Neg logit contributions | |
Parenthood | -0.011 |
mination | -0.011 |
ILA | -0.011 |
FTA | -0.010 |
buster | -0.010 |
Token | red |
Token ID | 445 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Parenthood | +0.216 |
mination | +0.214 |
ILA | +0.209 |
FTA | +0.198 |
buster | +0.194 |
Neg logit contributions | |
cffff | -0.249 |
jri | -0.222 |
uberty | -0.213 |
odied | -0.205 |
attled | -0.194 |
Token | der |
Token ID | 1082 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Parenthood | +0.523 |
mination | +0.518 |
ILA | +0.509 |
FTA | +0.482 |
buster | +0.471 |
Neg logit contributions | |
cffff | -0.532 |
jri | -0.471 |
uberty | -0.450 |
odied | -0.433 |
attled | -0.406 |
Token | falls |
Token ID | 8953 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
cffff | +2.051 |
jri | +1.834 |
uberty | +1.746 |
odied | +1.703 |
urses | +1.629 |
Neg logit contributions | |
Parenthood | -1.789 |
mination | -1.767 |
ILA | -1.722 |
FTA | -1.619 |
buster | -1.565 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Parenthood | +0.031 |
mination | +0.031 |
ILA | +0.030 |
FTA | +0.029 |
buster | +0.028 |
Neg logit contributions | |
cffff | -0.042 |
jri | -0.038 |
uberty | -0.037 |
odied | -0.035 |
attled | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
cffff | +0.278 |
jri | +0.246 |
uberty | +0.237 |
odied | +0.228 |
attled | +0.216 |
Neg logit contributions | |
Parenthood | -0.236 |
mination | -0.234 |
ILA | -0.228 |
FTA | -0.216 |
buster | -0.212 |
Token | Turtles |
Token ID | 44356 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
cffff | +0.120 |
jri | +0.107 |
uberty | +0.103 |
odied | +0.099 |
attled | +0.094 |
Neg logit contributions | |
Parenthood | -0.101 |
mination | -0.101 |
ILA | -0.098 |
FTA | -0.093 |
buster | -0.091 |
Token | rush |
Token ID | 10484 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
Parenthood | +0.063 |
mination | +0.062 |
ILA | +0.061 |
FTA | +0.058 |
buster | +0.057 |
Neg logit contributions | |
cffff | -0.064 |
jri | -0.056 |
uberty | -0.054 |
odied | -0.052 |
attled | -0.049 |
Token | love |
Token ID | 1842 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Parenthood | +0.080 |
mination | +0.079 |
ILA | +0.077 |
FTA | +0.073 |
buster | +0.071 |
Neg logit contributions | |
cffff | -0.105 |
jri | -0.094 |
uberty | -0.091 |
odied | -0.087 |
attled | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Parenthood | +0.233 |
mination | +0.230 |
ILA | +0.224 |
FTA | +0.212 |
buster | +0.208 |
Neg logit contributions | |
cffff | -0.320 |
jri | -0.286 |
uberty | -0.276 |
odied | -0.265 |
attled | -0.252 |
Token | I |
Token ID | 314 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Parenthood | +0.347 |
mination | +0.346 |
ILA | +0.335 |
FTA | +0.316 |
buster | +0.311 |
Neg logit contributions | |
cffff | -0.455 |
jri | -0.407 |
uberty | -0.393 |
odied | -0.378 |
attled | -0.359 |
Token | leave |
Token ID | 2666 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
Parenthood | +0.211 |
mination | +0.210 |
ILA | +0.203 |
FTA | +0.192 |
buster | +0.189 |
Neg logit contributions | |
cffff | -0.260 |
jri | -0.232 |
uberty | -0.223 |
odied | -0.215 |
attled | -0.204 |
Token | you |
Token ID | 345 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Parenthood | +0.281 |
mination | +0.278 |
ILA | +0.270 |
FTA | +0.255 |
buster | +0.249 |
Neg logit contributions | |
cffff | -0.378 |
jri | -0.338 |
uberty | -0.326 |
odied | -0.314 |
attled | -0.298 |
Token | hope |
Token ID | 2911 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Parenthood | +0.214 |
mination | +0.212 |
ILA | +0.207 |
FTA | +0.197 |
buster | +0.193 |
Neg logit contributions | |
cffff | -0.227 |
jri | -0.200 |
uberty | -0.192 |
odied | -0.184 |
attled | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
cffff | +0.577 |
jri | +0.514 |
uberty | +0.496 |
odied | +0.477 |
attled | +0.452 |
Neg logit contributions | |
Parenthood | -0.458 |
mination | -0.454 |
ILA | -0.441 |
FTA | -0.418 |
buster | -0.410 |
Token | I |
Token ID | 314 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Parenthood | +0.284 |
mination | +0.283 |
ILA | +0.273 |
FTA | +0.258 |
buster | +0.253 |
Neg logit contributions | |
cffff | -0.397 |
jri | -0.356 |
uberty | -0.345 |
odied | -0.332 |
attled | -0.316 |
Token | leave |
Token ID | 2666 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Parenthood | +0.230 |
mination | +0.228 |
ILA | +0.221 |
FTA | +0.209 |
buster | +0.205 |
Neg logit contributions | |
cffff | -0.312 |
jri | -0.279 |
uberty | -0.269 |
odied | -0.260 |
attled | -0.247 |
Token | you |
Token ID | 345 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Parenthood | +0.201 |
mination | +0.199 |
ILA | +0.194 |
FTA | +0.183 |
buster | +0.179 |
Neg logit contributions | |
cffff | -0.274 |
jri | -0.246 |
uberty | -0.237 |
odied | -0.229 |
attled | -0.217 |
Token | the |
Token ID | 262 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
Parenthood | +0.301 |
mination | +0.298 |
ILA | +0.291 |
FTA | +0.277 |
buster | +0.273 |
Neg logit contributions | |
cffff | -0.303 |
jri | -0.266 |
uberty | -0.255 |
odied | -0.244 |
attled | -0.230 |
Token | , |
Token ID | 11 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
Parenthood | +0.439 |
mination | +0.435 |
ILA | +0.422 |
FTA | +0.400 |
buster | +0.393 |
Neg logit contributions | |
cffff | -0.562 |
jri | -0.501 |
uberty | -0.483 |
odied | -0.465 |
attled | -0.441 |
Token | by |
Token ID | 416 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Parenthood | +0.064 |
mination | +0.064 |
ILA | +0.062 |
FTA | +0.058 |
buster | +0.058 |
Neg logit contributions | |
cffff | -0.082 |
jri | -0.073 |
uberty | -0.070 |
odied | -0.067 |
attled | -0.064 |
Token | second |
Token ID | 1218 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
cffff | +0.176 |
jri | +0.155 |
uberty | +0.149 |
odied | +0.143 |
attled | +0.135 |
Neg logit contributions | |
Parenthood | -0.163 |
mination | -0.162 |
ILA | -0.158 |
FTA | -0.149 |
buster | -0.148 |
Token | or |
Token ID | 393 |
Feature activation | -9.16e-03 |
Pos logit contributions | |
cffff | +0.935 |
jri | +0.829 |
uberty | +0.803 |
odied | +0.772 |
attled | +0.731 |
Neg logit contributions | |
Parenthood | -0.783 |
mination | -0.778 |
ILA | -0.760 |
FTA | -0.711 |
buster | -0.706 |
Token | third |
Token ID | 2368 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
Parenthood | +0.010 |
mination | +0.010 |
ILA | +0.009 |
FTA | +0.009 |
buster | +0.009 |
Neg logit contributions | |
cffff | -0.009 |
jri | -0.008 |
uberty | -0.008 |
odied | -0.007 |
attled | -0.007 |
Token | race |
Token ID | 3234 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
cffff | +0.673 |
jri | +0.598 |
uberty | +0.579 |
odied | +0.555 |
attled | +0.526 |
Neg logit contributions | |
Parenthood | -0.556 |
mination | -0.554 |
ILA | -0.543 |
FTA | -0.505 |
buster | -0.502 |
Token | we |
Token ID | 356 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
cffff | +0.759 |
jri | +0.678 |
uberty | +0.654 |
odied | +0.628 |
attled | +0.594 |
Neg logit contributions | |
Parenthood | -0.611 |
mination | -0.608 |
ILA | -0.594 |
FTA | -0.556 |
buster | -0.549 |
Token | should |
Token ID | 815 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
Parenthood | +0.572 |
mination | +0.568 |
ILA | +0.552 |
FTA | +0.521 |
buster | +0.513 |
Neg logit contributions | |
cffff | -0.667 |
jri | -0.593 |
uberty | -0.569 |
odied | -0.546 |
attled | -0.519 |
Token | be |
Token ID | 307 |
Feature activation | -8.96e-03 |
Pos logit contributions | |
cffff | +0.539 |
jri | +0.480 |
uberty | +0.462 |
odied | +0.442 |
attled | +0.423 |
Neg logit contributions | |
mination | -0.450 |
Parenthood | -0.450 |
ILA | -0.438 |
FTA | -0.408 |
buster | -0.401 |
Token | already |
Token ID | 1541 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
mination | +0.010 |
Parenthood | +0.010 |
ILA | +0.009 |
FTA | +0.009 |
buster | +0.009 |
Neg logit contributions | |
cffff | -0.009 |
jri | -0.008 |
uberty | -0.007 |
odied | -0.007 |
attled | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
cffff | +0.233 |
jri | +0.207 |
uberty | +0.199 |
odied | +0.191 |
attled | +0.182 |
Neg logit contributions | |
mination | -0.194 |
Parenthood | -0.194 |
ILA | -0.189 |
FTA | -0.176 |
buster | -0.175 |
Token | city |
Token ID | 1748 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
cffff | +0.088 |
jri | +0.078 |
uberty | +0.075 |
odied | +0.071 |
attled | +0.067 |
Neg logit contributions | |
Parenthood | -0.084 |
mination | -0.084 |
ILA | -0.082 |
FTA | -0.077 |
buster | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
cffff | +1.590 |
jri | +1.423 |
uberty | +1.369 |
odied | +1.320 |
attled | +1.260 |
Neg logit contributions | |
Parenthood | -1.172 |
mination | -1.160 |
ILA | -1.131 |
FTA | -1.060 |
buster | -1.039 |
Token | a |
Token ID | 257 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
cffff | +0.092 |
jri | +0.082 |
uberty | +0.079 |
odied | +0.076 |
attled | +0.072 |
Neg logit contributions | |
Parenthood | -0.072 |
mination | -0.072 |
ILA | -0.069 |
FTA | -0.065 |
buster | -0.064 |
Token | tragically |
Token ID | 49866 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
cffff | +0.198 |
jri | +0.175 |
uberty | +0.168 |
odied | +0.161 |
attled | +0.153 |
Neg logit contributions | |
Parenthood | -0.184 |
mination | -0.183 |
ILA | -0.178 |
FTA | -0.168 |
buster | -0.166 |
Token | in |
Token ID | 287 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
cffff | +0.292 |
jri | +0.260 |
uberty | +0.250 |
odied | +0.241 |
attled | +0.228 |
Neg logit contributions | |
Parenthood | -0.246 |
mination | -0.244 |
ILA | -0.237 |
FTA | -0.224 |
buster | -0.221 |
Token | effect |
Token ID | 10760 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Parenthood | +0.096 |
mination | +0.096 |
ILA | +0.093 |
FTA | +0.088 |
buster | +0.087 |
Neg logit contributions | |
cffff | -0.108 |
jri | -0.096 |
uberty | -0.092 |
odied | -0.088 |
attled | -0.083 |
Token | ual |
Token ID | 723 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
cffff | +0.489 |
jri | +0.431 |
uberty | +0.414 |
odied | +0.398 |
attled | +0.374 |
Neg logit contributions | |
Parenthood | -0.461 |
mination | -0.458 |
ILA | -0.446 |
FTA | -0.424 |
buster | -0.417 |
Token | public |
Token ID | 1171 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
cffff | +0.151 |
jri | +0.133 |
uberty | +0.127 |
odied | +0.122 |
attled | +0.115 |
Neg logit contributions | |
Parenthood | -0.155 |
mination | -0.155 |
ILA | -0.151 |
FTA | -0.143 |
buster | -0.141 |
Token | transit |
Token ID | 11168 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
cffff | +0.426 |
jri | +0.371 |
uberty | +0.355 |
odied | +0.339 |
attled | +0.317 |
Neg logit contributions | |
Parenthood | -0.479 |
mination | -0.476 |
ILA | -0.464 |
FTA | -0.444 |
buster | -0.437 |
Token | system |
Token ID | 1080 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
cffff | +1.011 |
jri | +0.891 |
uberty | +0.853 |
odied | +0.818 |
attled | +0.771 |
Neg logit contributions | |
Parenthood | -0.999 |
mination | -0.992 |
ILA | -0.966 |
FTA | -0.915 |
buster | -0.905 |
Token | ? |
Token ID | 30 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
Parenthood | +0.019 |
mination | +0.019 |
ILA | +0.018 |
FTA | +0.017 |
buster | +0.017 |
Neg logit contributions | |
cffff | -0.029 |
jri | -0.026 |
uberty | -0.025 |
odied | -0.024 |
attled | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
cffff | +0.244 |
jri | +0.219 |
uberty | +0.209 |
odied | +0.203 |
urses | +0.193 |
Neg logit contributions | |
mination | -0.214 |
Parenthood | -0.214 |
ILA | -0.209 |
FTA | -0.195 |
buster | -0.191 |
Token | T |
Token ID | 51 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
cffff | +0.234 |
jri | +0.211 |
uberty | +0.203 |
odied | +0.196 |
attled | +0.186 |
Neg logit contributions | |
Parenthood | -0.168 |
mination | -0.167 |
ILA | -0.161 |
FTA | -0.153 |
buster | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
cffff | +0.236 |
jri | +0.209 |
uberty | +0.201 |
odied | +0.193 |
attled | +0.182 |
Neg logit contributions | |
Parenthood | -0.218 |
mination | -0.216 |
ILA | -0.210 |
FTA | -0.200 |
buster | -0.197 |
Token | J |
Token ID | 41 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
cffff | +0.167 |
jri | +0.152 |
uberty | +0.147 |
odied | +0.142 |
attled | +0.136 |
Neg logit contributions | |
Parenthood | -0.105 |
mination | -0.105 |
ILA | -0.100 |
FTA | -0.095 |
buster | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
cffff | +0.067 |
jri | +0.060 |
uberty | +0.058 |
odied | +0.055 |
attled | +0.052 |
Neg logit contributions | |
Parenthood | -0.059 |
mination | -0.059 |
ILA | -0.057 |
FTA | -0.055 |
buster | -0.054 |
Token | Osh |
Token ID | 46614 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
cffff | +0.157 |
jri | +0.140 |
uberty | +0.134 |
odied | +0.128 |
attled | +0.120 |
Neg logit contributions | |
mination | -0.167 |
Parenthood | -0.166 |
ILA | -0.161 |
FTA | -0.154 |
buster | -0.153 |
Token | ie |
Token ID | 494 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
cffff | +0.851 |
jri | +0.765 |
uberty | +0.738 |
odied | +0.714 |
attled | +0.678 |
Neg logit contributions | |
Parenthood | -0.586 |
mination | -0.579 |
ILA | -0.565 |
FTA | -0.528 |
buster | -0.519 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
cffff | +0.127 |
jri | +0.114 |
uberty | +0.110 |
odied | +0.106 |
attled | +0.101 |
Neg logit contributions | |
Parenthood | -0.093 |
mination | -0.092 |
ILA | -0.089 |
FTA | -0.084 |
buster | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
cffff | +0.268 |
jri | +0.240 |
uberty | +0.230 |
odied | +0.223 |
urses | +0.212 |
Neg logit contributions | |
mination | -0.235 |
Parenthood | -0.234 |
ILA | -0.228 |
FTA | -0.213 |
buster | -0.209 |
Token | Nick |
Token ID | 23609 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
cffff | +0.254 |
jri | +0.229 |
uberty | +0.220 |
odied | +0.213 |
attled | +0.202 |
Neg logit contributions | |
Parenthood | -0.183 |
mination | -0.181 |
ILA | -0.174 |
FTA | -0.166 |
buster | -0.162 |
Token | las |
Token ID | 21921 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
cffff | +0.511 |
jri | +0.460 |
uberty | +0.443 |
odied | +0.427 |
urses | +0.405 |
Neg logit contributions | |
Parenthood | -0.394 |
mination | -0.390 |
ILA | -0.380 |
FTA | -0.357 |
buster | -0.352 |
Token | to |
Token ID | 284 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
cffff | +0.229 |
jri | +0.207 |
uberty | +0.201 |
odied | +0.194 |
attled | +0.185 |
Neg logit contributions | |
Parenthood | -0.134 |
mination | -0.133 |
ILA | -0.128 |
FTA | -0.120 |
buster | -0.118 |
Token | make |
Token ID | 787 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
Parenthood | +0.209 |
mination | +0.208 |
ILA | +0.202 |
FTA | +0.190 |
buster | +0.188 |
Neg logit contributions | |
cffff | -0.236 |
jri | -0.209 |
uberty | -0.201 |
odied | -0.193 |
attled | -0.183 |
Token | them |
Token ID | 606 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
cffff | +0.890 |
jri | +0.793 |
uberty | +0.760 |
odied | +0.733 |
attled | +0.693 |
Neg logit contributions | |
Parenthood | -0.771 |
mination | -0.766 |
ILA | -0.747 |
FTA | -0.700 |
buster | -0.697 |
Token | worse |
Token ID | 4785 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
cffff | +0.760 |
jri | +0.678 |
uberty | +0.651 |
odied | +0.630 |
attled | +0.597 |
Neg logit contributions | |
Parenthood | -0.638 |
mination | -0.635 |
ILA | -0.618 |
FTA | -0.582 |
buster | -0.574 |
Token | than |
Token ID | 621 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
cffff | +1.198 |
jri | +1.075 |
uberty | +1.032 |
odied | +1.001 |
attled | +0.951 |
Neg logit contributions | |
mination | -0.923 |
Parenthood | -0.921 |
ILA | -0.902 |
FTA | -0.836 |
buster | -0.827 |
Token | better |
Token ID | 1365 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Parenthood | +0.184 |
mination | +0.183 |
ILA | +0.178 |
FTA | +0.168 |
buster | +0.165 |
Neg logit contributions | |
cffff | -0.227 |
jri | -0.203 |
uberty | -0.195 |
odied | -0.188 |
attled | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
cffff | +1.169 |
jri | +1.045 |
uberty | +1.003 |
odied | +0.973 |
attled | +0.921 |
Neg logit contributions | |
Parenthood | -0.941 |
mination | -0.937 |
ILA | -0.918 |
FTA | -0.856 |
buster | -0.842 |
Token |
|
Token ID | 198 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
cffff | +0.193 |
jri | +0.171 |
uberty | +0.167 |
odied | +0.160 |
attled | +0.151 |
Neg logit contributions | |
mination | -0.158 |
Parenthood | -0.158 |
ILA | -0.153 |
FTA | -0.144 |
buster | -0.142 |
Token |
|
Token ID | 198 |
Feature activation | +9.61e-02 |
Pos logit contributions | |
cffff | +0.074 |
jri | +0.066 |
uberty | +0.063 |
odied | +0.061 |
urses | +0.058 |
Neg logit contributions | |
mination | -0.062 |
Parenthood | -0.062 |
ILA | -0.061 |
FTA | -0.057 |
buster | -0.056 |
Token | Why |
Token ID | 5195 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
cffff | +0.123 |
jri | +0.111 |
uberty | +0.108 |
odied | +0.104 |
attled | +0.099 |
Neg logit contributions | |
Parenthood | -0.074 |
mination | -0.072 |
ILA | -0.070 |
FTA | -0.066 |
buster | -0.064 |
Token | then |
Token ID | 788 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
mination | +0.405 |
Parenthood | +0.405 |
ILA | +0.393 |
FTA | +0.370 |
buster | +0.364 |
Neg logit contributions | |
cffff | -0.516 |
jri | -0.459 |
uberty | -0.446 |
odied | -0.428 |
attled | -0.405 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
cffff | +0.341 |
jri | +0.304 |
uberty | +0.294 |
odied | +0.282 |
attled | +0.269 |
Neg logit contributions | |
Parenthood | -0.260 |
mination | -0.259 |
ILA | -0.251 |
FTA | -0.236 |
buster | -0.232 |
Token | perhaps |
Token ID | 3737 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
mination | +0.019 |
Parenthood | +0.019 |
ILA | +0.019 |
FTA | +0.018 |
buster | +0.017 |
Neg logit contributions | |
cffff | -0.024 |
jri | -0.022 |
uberty | -0.021 |
odied | -0.020 |
attled | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Parenthood | +0.142 |
mination | +0.142 |
ILA | +0.138 |
FTA | +0.130 |
buster | +0.128 |
Neg logit contributions | |
cffff | -0.185 |
jri | -0.165 |
uberty | -0.160 |
odied | -0.154 |
attled | -0.146 |
Token | " |
Token ID | 366 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Parenthood | +0.102 |
mination | +0.102 |
ILA | +0.099 |
FTA | +0.094 |
buster | +0.093 |
Neg logit contributions | |
cffff | -0.105 |
jri | -0.092 |
uberty | -0.089 |
odied | -0.085 |
attled | -0.080 |
Token | anim |
Token ID | 11227 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
cffff | +0.229 |
jri | +0.206 |
uberty | +0.199 |
odied | +0.192 |
attled | +0.183 |
Neg logit contributions | |
Parenthood | -0.157 |
mination | -0.155 |
ILA | -0.151 |
FTA | -0.142 |
buster | -0.138 |
Token | ated |
Token ID | 515 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
cffff | +1.009 |
jri | +0.887 |
uberty | +0.854 |
odied | +0.819 |
attled | +0.770 |
Neg logit contributions | |
Parenthood | -0.982 |
mination | -0.975 |
ILA | -0.952 |
FTA | -0.906 |
buster | -0.892 |
Token | with |
Token ID | 351 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
cffff | +0.008 |
jri | +0.007 |
uberty | +0.006 |
odied | +0.006 |
attled | +0.006 |
Neg logit contributions | |
mination | -0.007 |
Parenthood | -0.007 |
ILA | -0.006 |
FTA | -0.006 |
buster | -0.006 |
Token | magic |
Token ID | 5536 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
cffff | +0.005 |
jri | +0.004 |
uberty | +0.004 |
odied | +0.004 |
attled | +0.004 |
Neg logit contributions | |
Parenthood | -0.005 |
mination | -0.005 |
ILA | -0.005 |
FTA | -0.004 |
buster | -0.004 |
Token | marker |
Token ID | 18364 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
cffff | +1.421 |
jri | +1.274 |
uberty | +1.235 |
odied | +1.194 |
attled | +1.135 |
Neg logit contributions | |
Parenthood | -0.965 |
mination | -0.959 |
ILA | -0.929 |
FTA | -0.871 |
buster | -0.852 |
Token | and |
Token ID | 290 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
cffff | +0.760 |
jri | +0.683 |
uberty | +0.663 |
odied | +0.639 |
attled | +0.610 |
Neg logit contributions | |
Parenthood | -0.526 |
mination | -0.521 |
ILA | -0.508 |
FTA | -0.477 |
buster | -0.466 |
Token | typing |
Token ID | 19720 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
cffff | +0.012 |
jri | +0.011 |
uberty | +0.011 |
odied | +0.010 |
attled | +0.010 |
Neg logit contributions | |
Parenthood | -0.012 |
mination | -0.012 |
ILA | -0.011 |
FTA | -0.011 |
buster | -0.011 |
Token | why |
Token ID | 1521 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
cffff | +0.281 |
jri | +0.249 |
uberty | +0.239 |
odied | +0.230 |
attled | +0.217 |
Neg logit contributions | |
Parenthood | -0.250 |
mination | -0.248 |
ILA | -0.242 |
FTA | -0.229 |
buster | -0.226 |
Token | there |
Token ID | 612 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Parenthood | +0.782 |
mination | +0.774 |
ILA | +0.754 |
FTA | +0.717 |
buster | +0.704 |
Neg logit contributions | |
cffff | -0.884 |
jri | -0.783 |
uberty | -0.753 |
odied | -0.723 |
attled | -0.682 |
Token | had |
Token ID | 550 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
Parenthood | +0.410 |
mination | +0.407 |
ILA | +0.397 |
FTA | +0.374 |
buster | +0.368 |
Neg logit contributions | |
cffff | -0.511 |
jri | -0.457 |
uberty | -0.442 |
odied | -0.425 |
attled | -0.403 |
Token | been |
Token ID | 587 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
Parenthood | +0.445 |
mination | +0.442 |
ILA | +0.431 |
FTA | +0.410 |
buster | +0.403 |
Neg logit contributions | |
cffff | -0.466 |
jri | -0.411 |
uberty | -0.395 |
odied | -0.378 |
attled | -0.357 |
Token | a |
Token ID | 257 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Parenthood | +0.507 |
mination | +0.504 |
ILA | +0.489 |
FTA | +0.461 |
buster | +0.454 |
Neg logit contributions | |
cffff | -0.674 |
jri | -0.603 |
uberty | -0.583 |
odied | -0.561 |
attled | -0.533 |
Token | Civil |
Token ID | 7511 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Parenthood | +0.194 |
mination | +0.193 |
ILA | +0.188 |
FTA | +0.178 |
buster | +0.176 |
Neg logit contributions | |
cffff | -0.203 |
jri | -0.180 |
uberty | -0.173 |
odied | -0.165 |
attled | -0.156 |
Token | War |
Token ID | 1810 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
Parenthood | +0.115 |
mination | +0.113 |
ILA | +0.109 |
FTA | +0.103 |
buster | +0.101 |
Neg logit contributions | |
cffff | -0.184 |
jri | -0.165 |
uberty | -0.160 |
odied | -0.154 |
attled | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Parenthood | +0.656 |
mination | +0.651 |
ILA | +0.630 |
FTA | +0.597 |
buster | +0.589 |
Neg logit contributions | |
cffff | -0.896 |
jri | -0.800 |
uberty | -0.773 |
odied | -0.745 |
attled | -0.705 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
cffff | +0.022 |
jri | +0.019 |
uberty | +0.019 |
odied | +0.018 |
attled | +0.017 |
Neg logit contributions | |
mination | -0.018 |
Parenthood | -0.018 |
ILA | -0.017 |
FTA | -0.016 |
buster | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
mination | +0.110 |
Parenthood | +0.110 |
ILA | +0.107 |
FTA | +0.100 |
buster | +0.098 |
Neg logit contributions | |
cffff | -0.129 |
jri | -0.115 |
uberty | -0.110 |
odied | -0.107 |
urses | -0.101 |
Token | According |
Token ID | 4821 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Parenthood | +0.042 |
mination | +0.042 |
ILA | +0.040 |
FTA | +0.038 |
buster | +0.037 |
Neg logit contributions | |
cffff | -0.067 |
jri | -0.061 |
uberty | -0.059 |
odied | -0.057 |
attled | -0.054 |
Token | spying |
Token ID | 23649 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Parenthood | +1.107 |
mination | +1.103 |
ILA | +1.073 |
FTA | +1.017 |
buster | +1.003 |
Neg logit contributions | |
cffff | -1.118 |
jri | -0.985 |
uberty | -0.945 |
odied | -0.904 |
attled | -0.856 |
Token | legislation |
Token ID | 5520 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
Parenthood | +1.173 |
mination | +1.164 |
ILA | +1.131 |
FTA | +1.068 |
buster | +1.051 |
Neg logit contributions | |
cffff | -1.470 |
jri | -1.311 |
uberty | -1.262 |
odied | -1.216 |
attled | -1.154 |
Token | and |
Token ID | 290 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
Parenthood | +0.075 |
mination | +0.074 |
ILA | +0.072 |
FTA | +0.068 |
buster | +0.066 |
Neg logit contributions | |
cffff | -0.109 |
jri | -0.097 |
uberty | -0.094 |
odied | -0.091 |
attled | -0.086 |
Token | other |
Token ID | 584 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
Parenthood | +0.028 |
mination | +0.028 |
ILA | +0.027 |
FTA | +0.026 |
buster | +0.025 |
Neg logit contributions | |
cffff | -0.030 |
jri | -0.026 |
uberty | -0.025 |
odied | -0.024 |
attled | -0.023 |
Token | issues |
Token ID | 2428 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
cffff | +0.171 |
jri | +0.150 |
uberty | +0.144 |
odied | +0.138 |
attled | +0.131 |
Neg logit contributions | |
Parenthood | -0.166 |
mination | -0.165 |
ILA | -0.160 |
FTA | -0.152 |
buster | -0.150 |
Token | ." |
Token ID | 526 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
cffff | +0.039 |
jri | +0.035 |
uberty | +0.034 |
odied | +0.032 |
attled | +0.031 |
Neg logit contributions | |
Parenthood | -0.027 |
mination | -0.026 |
ILA | -0.026 |
FTA | -0.024 |
buster | -0.024 |
Token | To |
Token ID | 1675 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
mination | +0.456 |
Parenthood | +0.455 |
ILA | +0.438 |
FTA | +0.412 |
buster | +0.410 |
Neg logit contributions | |
cffff | -0.524 |
jri | -0.467 |
uberty | -0.452 |
odied | -0.433 |
attled | -0.412 |
Token | put |
Token ID | 1234 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
cffff | +0.215 |
jri | +0.193 |
uberty | +0.186 |
odied | +0.178 |
attled | +0.169 |
Neg logit contributions | |
Parenthood | -0.176 |
mination | -0.176 |
ILA | -0.169 |
FTA | -0.160 |
buster | -0.158 |
Token | this |
Token ID | 428 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
cffff | +0.079 |
jri | +0.070 |
uberty | +0.067 |
odied | +0.064 |
attled | +0.061 |
Neg logit contributions | |
Parenthood | -0.069 |
mination | -0.069 |
ILA | -0.067 |
FTA | -0.063 |
buster | -0.063 |
Token | into |
Token ID | 656 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
mination | +0.094 |
Parenthood | +0.094 |
ILA | +0.091 |
FTA | +0.085 |
buster | +0.084 |
Neg logit contributions | |
cffff | -0.124 |
jri | -0.111 |
uberty | -0.106 |
odied | -0.103 |
attled | -0.098 |
Token | perspective |
Token ID | 6650 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
Parenthood | +0.008 |
mination | +0.008 |
ILA | +0.008 |
FTA | +0.007 |
buster | +0.007 |
Neg logit contributions | |
cffff | -0.010 |
jri | -0.009 |
uberty | -0.009 |
odied | -0.008 |
attled | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -9.46e-02 |
Pos logit contributions | |
Parenthood | +0.089 |
mination | +0.088 |
ILA | +0.086 |
FTA | +0.082 |
buster | +0.081 |
Neg logit contributions | |
cffff | -0.090 |
jri | -0.079 |
uberty | -0.076 |
odied | -0.073 |
attled | -0.069 |
Token | Carolina |
Token ID | 5913 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Parenthood | +0.089 |
mination | +0.088 |
ILA | +0.086 |
FTA | +0.082 |
buster | +0.080 |
Neg logit contributions | |
cffff | -0.105 |
jri | -0.093 |
uberty | -0.089 |
odied | -0.086 |
attled | -0.081 |
Token | 's |
Token ID | 338 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
cffff | +0.516 |
jri | +0.462 |
uberty | +0.446 |
odied | +0.430 |
attled | +0.408 |
Neg logit contributions | |
Parenthood | -0.376 |
mination | -0.373 |
ILA | -0.362 |
FTA | -0.342 |
buster | -0.336 |
Token | offensive |
Token ID | 5859 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
cffff | +0.274 |
jri | +0.239 |
uberty | +0.229 |
odied | +0.219 |
attled | +0.205 |
Neg logit contributions | |
Parenthood | -0.292 |
mination | -0.289 |
ILA | -0.282 |
FTA | -0.270 |
buster | -0.266 |
Token | linemen |
Token ID | 41683 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
cffff | +0.190 |
jri | +0.166 |
uberty | +0.160 |
odied | +0.152 |
attled | +0.144 |
Neg logit contributions | |
Parenthood | -0.183 |
mination | -0.182 |
ILA | -0.177 |
FTA | -0.169 |
buster | -0.166 |
Token | have |
Token ID | 423 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
Parenthood | +0.705 |
mination | +0.699 |
ILA | +0.680 |
FTA | +0.649 |
buster | +0.638 |
Neg logit contributions | |
cffff | -0.789 |
jri | -0.698 |
uberty | -0.671 |
odied | -0.643 |
attled | -0.607 |
Token | -- |
Token ID | 1377 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Parenthood | +0.061 |
mination | +0.061 |
ILA | +0.059 |
FTA | +0.056 |
buster | +0.055 |
Neg logit contributions | |
cffff | -0.076 |
jri | -0.067 |
uberty | -0.065 |
odied | -0.063 |
attled | -0.059 |
Token | he |
Token ID | 339 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Parenthood | +0.571 |
mination | +0.566 |
ILA | +0.551 |
FTA | +0.524 |
buster | +0.515 |
Neg logit contributions | |
cffff | -0.628 |
jri | -0.556 |
uberty | -0.534 |
odied | -0.512 |
attled | -0.484 |
Token | can |
Token ID | 460 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
cffff | +0.312 |
jri | +0.279 |
uberty | +0.269 |
odied | +0.260 |
attled | +0.248 |
Neg logit contributions | |
Parenthood | -0.237 |
mination | -0.235 |
ILA | -0.228 |
FTA | -0.214 |
buster | -0.210 |
Token | 't |
Token ID | 470 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Parenthood | +0.066 |
mination | +0.065 |
ILA | +0.063 |
FTA | +0.059 |
buster | +0.057 |
Neg logit contributions | |
cffff | -0.088 |
jri | -0.079 |
uberty | -0.076 |
odied | -0.073 |
attled | -0.071 |
Token | pass |
Token ID | 1208 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Parenthood | +0.124 |
mination | +0.123 |
ILA | +0.120 |
FTA | +0.113 |
buster | +0.111 |
Neg logit contributions | |
cffff | -0.128 |
jri | -0.113 |
uberty | -0.109 |
odied | -0.104 |
attled | -0.099 |
Token | valued |
Token ID | 17560 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
cffff | +0.234 |
jri | +0.208 |
uberty | +0.200 |
odied | +0.194 |
attled | +0.182 |
Neg logit contributions | |
Parenthood | -0.201 |
mination | -0.201 |
ILA | -0.195 |
FTA | -0.185 |
buster | -0.182 |
Token | as |
Token ID | 355 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
cffff | +0.302 |
jri | +0.271 |
uberty | +0.260 |
odied | +0.253 |
attled | +0.239 |
Neg logit contributions | |
mination | -0.226 |
Parenthood | -0.226 |
ILA | -0.220 |
FTA | -0.206 |
buster | -0.203 |
Token | � |
Token ID | 564 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Parenthood | +0.082 |
mination | +0.082 |
ILA | +0.080 |
FTA | +0.075 |
buster | +0.074 |
Neg logit contributions | |
cffff | -0.112 |
jri | -0.100 |
uberty | -0.097 |
odied | -0.094 |
attled | -0.089 |
Token | � |
Token ID | 246 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
cffff | +0.218 |
jri | +0.200 |
uberty | +0.194 |
odied | +0.189 |
attled | +0.181 |
Neg logit contributions | |
Parenthood | -0.086 |
mination | -0.085 |
ILA | -0.082 |
FTA | -0.075 |
buster | -0.072 |
Token | good |
Token ID | 11274 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
cffff | +0.468 |
jri | +0.423 |
uberty | +0.409 |
odied | +0.396 |
attled | +0.378 |
Neg logit contributions | |
Parenthood | -0.278 |
mination | -0.275 |
ILA | -0.266 |
FTA | -0.250 |
buster | -0.243 |
Token | � |
Token ID | 447 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
cffff | +0.078 |
jri | +0.070 |
uberty | +0.067 |
odied | +0.065 |
attled | +0.062 |
Neg logit contributions | |
Parenthood | -0.056 |
mination | -0.055 |
ILA | -0.054 |
FTA | -0.051 |
buster | -0.050 |
Token | � |
Token ID | 247 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Parenthood | +0.089 |
mination | +0.088 |
ILA | +0.085 |
FTA | +0.080 |
buster | +0.078 |
Neg logit contributions | |
cffff | -0.148 |
jri | -0.134 |
uberty | -0.130 |
odied | -0.126 |
attled | -0.120 |
Token | became |
Token ID | 2627 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
cffff | +0.208 |
jri | +0.186 |
uberty | +0.179 |
odied | +0.174 |
attled | +0.164 |
Neg logit contributions | |
Parenthood | -0.160 |
mination | -0.159 |
ILA | -0.156 |
FTA | -0.147 |
buster | -0.143 |
Token | � |
Token ID | 564 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
cffff | +0.426 |
jri | +0.379 |
uberty | +0.363 |
odied | +0.353 |
attled | +0.333 |
Neg logit contributions | |
Parenthood | -0.350 |
mination | -0.349 |
ILA | -0.339 |
FTA | -0.320 |
buster | -0.316 |
Token | � |
Token ID | 246 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
cffff | +0.416 |
jri | +0.381 |
uberty | +0.370 |
odied | +0.360 |
attled | +0.346 |
Neg logit contributions | |
Parenthood | -0.162 |
mination | -0.161 |
ILA | -0.154 |
FTA | -0.141 |
buster | -0.136 |
Token | evil |
Token ID | 23542 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
cffff | +0.780 |
jri | +0.703 |
uberty | +0.677 |
odied | +0.659 |
attled | +0.627 |
Neg logit contributions | |
Parenthood | -0.495 |
mination | -0.488 |
ILA | -0.473 |
FTA | -0.446 |
buster | -0.433 |
Token | Kenneth |
Token ID | 23632 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
cffff | +0.125 |
jri | +0.112 |
uberty | +0.108 |
odied | +0.104 |
attled | +0.098 |
Neg logit contributions | |
Parenthood | -0.100 |
mination | -0.100 |
ILA | -0.097 |
FTA | -0.092 |
buster | -0.090 |
Token | B |
Token ID | 347 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
Parenthood | +1.576 |
mination | +1.552 |
ILA | +1.486 |
FTA | +1.421 |
buster | +1.397 |
Neg logit contributions | |
cffff | -2.105 |
jri | -1.877 |
uberty | -1.806 |
odied | -1.732 |
attled | -1.646 |
Token | ae |
Token ID | 3609 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
cffff | +0.478 |
jri | +0.421 |
uberty | +0.405 |
odied | +0.387 |
attled | +0.364 |
Neg logit contributions | |
Parenthood | -0.498 |
mination | -0.493 |
ILA | -0.483 |
FTA | -0.460 |
buster | -0.451 |
Token | who |
Token ID | 508 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
Parenthood | +0.292 |
mination | +0.290 |
ILA | +0.282 |
FTA | +0.266 |
buster | +0.261 |
Neg logit contributions | |
cffff | -0.379 |
jri | -0.340 |
uberty | -0.328 |
odied | -0.315 |
attled | -0.299 |
Token | was |
Token ID | 373 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Parenthood | +0.385 |
mination | +0.381 |
ILA | +0.372 |
FTA | +0.352 |
buster | +0.346 |
Neg logit contributions | |
cffff | -0.433 |
jri | -0.384 |
uberty | -0.369 |
odied | -0.356 |
attled | -0.336 |
Token | allegedly |
Token ID | 7910 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
cffff | +0.342 |
jri | +0.297 |
uberty | +0.284 |
odied | +0.273 |
attled | +0.255 |
Neg logit contributions | |
Parenthood | -0.388 |
mination | -0.386 |
ILA | -0.377 |
FTA | -0.358 |
buster | -0.354 |
Token | involved |
Token ID | 2950 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Parenthood | +1.696 |
mination | +1.682 |
ILA | +1.643 |
FTA | +1.576 |
buster | +1.551 |
Neg logit contributions | |
cffff | -1.476 |
jri | -1.283 |
uberty | -1.227 |
odied | -1.164 |
attled | -1.090 |
Token | in |
Token ID | 287 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Parenthood | +0.961 |
mination | +0.948 |
ILA | +0.913 |
FTA | +0.872 |
buster | +0.855 |
Neg logit contributions | |
cffff | -1.381 |
jri | -1.237 |
uberty | -1.193 |
odied | -1.146 |
attled | -1.095 |
Token | religious |
Token ID | 4158 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
Parenthood | +0.357 |
mination | +0.354 |
ILA | +0.345 |
FTA | +0.327 |
buster | +0.322 |
Neg logit contributions | |
cffff | -0.396 |
jri | -0.351 |
uberty | -0.337 |
odied | -0.324 |
attled | -0.306 |
Token | activities |
Token ID | 4568 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Parenthood | +0.513 |
mination | +0.509 |
ILA | +0.496 |
FTA | +0.473 |
buster | +0.466 |
Neg logit contributions | |
cffff | -0.507 |
jri | -0.445 |
uberty | -0.426 |
odied | -0.408 |
attled | -0.383 |
Token | and |
Token ID | 290 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Parenthood | +1.060 |
mination | +1.045 |
ILA | +1.012 |
FTA | +0.962 |
buster | +0.940 |
Neg logit contributions | |
cffff | -1.481 |
jri | -1.325 |
uberty | -1.282 |
odied | -1.232 |
attled | -1.172 |
Token | minute |
Token ID | 11374 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Parenthood | +0.005 |
mination | +0.005 |
ILA | +0.004 |
FTA | +0.004 |
buster | +0.004 |
Neg logit contributions | |
cffff | -0.007 |
jri | -0.007 |
uberty | -0.006 |
odied | -0.006 |
attled | -0.006 |
Token | scene |
Token ID | 3715 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Parenthood | +0.423 |
mination | +0.421 |
ILA | +0.409 |
FTA | +0.386 |
buster | +0.379 |
Neg logit contributions | |
cffff | -0.538 |
jri | -0.479 |
uberty | -0.463 |
odied | -0.446 |
attled | -0.423 |
Token | that |
Token ID | 326 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
cffff | +0.171 |
jri | +0.153 |
uberty | +0.148 |
odied | +0.143 |
attled | +0.136 |
Neg logit contributions | |
Parenthood | -0.119 |
mination | -0.119 |
ILA | -0.115 |
FTA | -0.108 |
buster | -0.106 |
Token | ends |
Token ID | 5645 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
cffff | +0.170 |
jri | +0.151 |
uberty | +0.146 |
odied | +0.140 |
attled | +0.132 |
Neg logit contributions | |
Parenthood | -0.143 |
mination | -0.143 |
ILA | -0.139 |
FTA | -0.131 |
buster | -0.129 |
Token | with |
Token ID | 351 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Parenthood | +0.195 |
mination | +0.193 |
ILA | +0.188 |
FTA | +0.177 |
buster | +0.174 |
Neg logit contributions | |
cffff | -0.263 |
jri | -0.235 |
uberty | -0.227 |
odied | -0.219 |
attled | -0.208 |
Token | Sed |
Token ID | 22710 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Parenthood | +0.183 |
mination | +0.181 |
ILA | +0.176 |
FTA | +0.167 |
buster | +0.164 |
Neg logit contributions | |
cffff | -0.218 |
jri | -0.194 |
uberty | -0.187 |
odied | -0.179 |
attled | -0.170 |
Token | aris |
Token ID | 20066 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Parenthood | +0.936 |
mination | +0.922 |
ILA | +0.887 |
FTA | +0.812 |
buster | +0.789 |
Neg logit contributions | |
cffff | -2.264 |
jri | -2.074 |
uberty | -2.014 |
odied | -1.958 |
attled | -1.881 |
Token | covered |
Token ID | 5017 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
Parenthood | +1.179 |
mination | +1.170 |
ILA | +1.141 |
FTA | +1.087 |
buster | +1.070 |
Neg logit contributions | |
cffff | -1.185 |
jri | -1.042 |
uberty | -0.999 |
odied | -0.956 |
attled | -0.900 |
Token | in |
Token ID | 287 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
Parenthood | +0.746 |
mination | +0.740 |
ILA | +0.718 |
FTA | +0.678 |
buster | +0.666 |
Neg logit contributions | |
cffff | -0.996 |
jri | -0.890 |
uberty | -0.859 |
odied | -0.828 |
attled | -0.786 |
Token | blood |
Token ID | 2910 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Parenthood | +0.413 |
mination | +0.411 |
ILA | +0.401 |
FTA | +0.381 |
buster | +0.375 |
Neg logit contributions | |
cffff | -0.426 |
jri | -0.375 |
uberty | -0.360 |
odied | -0.346 |
attled | -0.325 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
cffff | +0.317 |
jri | +0.288 |
uberty | +0.279 |
odied | +0.271 |
attled | +0.260 |
Neg logit contributions | |
Parenthood | -0.162 |
mination | -0.160 |
ILA | -0.155 |
FTA | -0.143 |
buster | -0.140 |
Token | ium |
Token ID | 1505 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
cffff | +0.464 |
jri | +0.424 |
uberty | +0.413 |
odied | +0.405 |
attled | +0.390 |
Neg logit contributions | |
Parenthood | -0.167 |
mination | -0.163 |
ILA | -0.157 |
FTA | -0.142 |
buster | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
Parenthood | +1.260 |
mination | +1.247 |
ILA | +1.211 |
FTA | +1.148 |
buster | +1.129 |
Neg logit contributions | |
cffff | -1.607 |
jri | -1.433 |
uberty | -1.383 |
odied | -1.328 |
attled | -1.260 |
Token | plutonium |
Token ID | 47901 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
Parenthood | +0.014 |
mination | +0.014 |
ILA | +0.014 |
FTA | +0.013 |
buster | +0.013 |
Neg logit contributions | |
cffff | -0.020 |
jri | -0.018 |
uberty | -0.017 |
odied | -0.017 |
attled | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
Parenthood | +0.690 |
mination | +0.684 |
ILA | +0.663 |
FTA | +0.625 |
buster | +0.613 |
Neg logit contributions | |
cffff | -0.971 |
jri | -0.870 |
uberty | -0.840 |
odied | -0.810 |
attled | -0.771 |
Token | americ |
Token ID | 45630 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Parenthood | +0.003 |
mination | +0.003 |
ILA | +0.002 |
FTA | +0.002 |
buster | +0.002 |
Neg logit contributions | |
cffff | -0.003 |
jri | -0.003 |
uberty | -0.003 |
odied | -0.003 |
attled | -0.003 |
Token | ium |
Token ID | 1505 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Parenthood | +0.572 |
mination | +0.563 |
ILA | +0.536 |
FTA | +0.485 |
buster | +0.467 |
Neg logit contributions | |
cffff | -1.690 |
jri | -1.554 |
uberty | -1.510 |
odied | -1.473 |
attled | -1.419 |
Token | . |
Token ID | 13 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Parenthood | +1.407 |
mination | +1.393 |
ILA | +1.352 |
FTA | +1.281 |
buster | +1.259 |
Neg logit contributions | |
cffff | -1.814 |
jri | -1.618 |
uberty | -1.561 |
odied | -1.501 |
attled | -1.424 |
Token |
|
Token ID | 198 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
Parenthood | +0.077 |
mination | +0.076 |
ILA | +0.074 |
FTA | +0.070 |
buster | +0.069 |
Neg logit contributions | |
cffff | -0.100 |
jri | -0.089 |
uberty | -0.086 |
odied | -0.083 |
attled | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
Parenthood | +0.069 |
mination | +0.069 |
ILA | +0.067 |
FTA | +0.063 |
buster | +0.061 |
Neg logit contributions | |
cffff | -0.083 |
jri | -0.074 |
uberty | -0.071 |
odied | -0.069 |
urses | -0.065 |
Token | � |
Token ID | 447 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
Parenthood | +0.070 |
mination | +0.069 |
ILA | +0.067 |
FTA | +0.063 |
buster | +0.062 |
Neg logit contributions | |
cffff | -0.105 |
jri | -0.094 |
uberty | -0.091 |
odied | -0.088 |
attled | -0.084 |
Token | � |
Token ID | 250 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Parenthood | +0.029 |
mination | +0.029 |
ILA | +0.028 |
FTA | +0.025 |
buster | +0.025 |
Neg logit contributions | |
cffff | -0.077 |
jri | -0.071 |
uberty | -0.069 |
odied | -0.067 |
attled | -0.065 |
Token | blackout |
Token ID | 45939 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
Parenthood | +0.030 |
mination | +0.029 |
ILA | +0.029 |
FTA | +0.027 |
buster | +0.027 |
Neg logit contributions | |
cffff | -0.035 |
jri | -0.031 |
uberty | -0.030 |
odied | -0.029 |
attled | -0.028 |
Token | curtains |
Token ID | 41160 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
Parenthood | +0.971 |
mination | +0.966 |
ILA | +0.939 |
FTA | +0.895 |
buster | +0.882 |
Neg logit contributions | |
cffff | -1.030 |
jri | -0.907 |
uberty | -0.872 |
odied | -0.835 |
attled | -0.787 |
Token | over |
Token ID | 625 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
Parenthood | +0.620 |
mination | +0.616 |
ILA | +0.598 |
FTA | +0.568 |
buster | +0.558 |
Neg logit contributions | |
cffff | -0.742 |
jri | -0.660 |
uberty | -0.635 |
odied | -0.610 |
attled | -0.578 |
Token | windows |
Token ID | 9168 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
cffff | +0.021 |
jri | +0.018 |
uberty | +0.018 |
odied | +0.017 |
attled | +0.016 |
Neg logit contributions | |
Parenthood | -0.018 |
mination | -0.018 |
ILA | -0.017 |
FTA | -0.016 |
buster | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
Parenthood | +0.632 |
mination | +0.628 |
ILA | +0.608 |
FTA | +0.576 |
buster | +0.567 |
Neg logit contributions | |
cffff | -0.832 |
jri | -0.742 |
uberty | -0.717 |
odied | -0.689 |
attled | -0.654 |
Token | walls |
Token ID | 7714 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Parenthood | +0.075 |
mination | +0.074 |
ILA | +0.073 |
FTA | +0.068 |
buster | +0.068 |
Neg logit contributions | |
cffff | -0.089 |
jri | -0.080 |
uberty | -0.076 |
odied | -0.074 |
attled | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +5.34e-03 |
Pos logit contributions | |
Parenthood | +1.098 |
mination | +1.093 |
ILA | +1.055 |
FTA | +0.996 |
buster | +0.979 |
Neg logit contributions | |
cffff | -1.619 |
jri | -1.449 |
uberty | -1.404 |
odied | -1.354 |
attled | -1.287 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
cffff | +0.006 |
jri | +0.005 |
uberty | +0.005 |
odied | +0.004 |
attled | +0.004 |
Neg logit contributions | |
Parenthood | -0.005 |
mination | -0.005 |
ILA | -0.005 |
FTA | -0.005 |
buster | -0.005 |
Token | door |
Token ID | 3420 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Parenthood | +0.193 |
mination | +0.191 |
ILA | +0.187 |
FTA | +0.177 |
buster | +0.175 |
Neg logit contributions | |
cffff | -0.191 |
jri | -0.168 |
uberty | -0.160 |
odied | -0.154 |
attled | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Parenthood | +0.609 |
mination | +0.600 |
ILA | +0.586 |
FTA | +0.554 |
buster | +0.542 |
Neg logit contributions | |
cffff | -0.747 |
jri | -0.667 |
uberty | -0.641 |
odied | -0.617 |
attled | -0.586 |
Token | The |
Token ID | 383 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Parenthood | +0.314 |
mination | +0.313 |
ILA | +0.307 |
FTA | +0.288 |
buster | +0.286 |
Neg logit contributions | |
cffff | -0.328 |
jri | -0.289 |
uberty | -0.279 |
odied | -0.268 |
attled | -0.252 |
Token | the |
Token ID | 262 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Parenthood | +0.332 |
mination | +0.330 |
ILA | +0.320 |
FTA | +0.304 |
buster | +0.300 |
Neg logit contributions | |
cffff | -0.336 |
jri | -0.298 |
uberty | -0.285 |
odied | -0.274 |
attled | -0.258 |
Token | company |
Token ID | 1664 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
Parenthood | +0.136 |
mination | +0.135 |
ILA | +0.131 |
FTA | +0.123 |
buster | +0.122 |
Neg logit contributions | |
cffff | -0.165 |
jri | -0.147 |
uberty | -0.142 |
odied | -0.136 |
attled | -0.130 |
Token | with |
Token ID | 351 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
cffff | +0.182 |
jri | +0.163 |
uberty | +0.156 |
odied | +0.152 |
attled | +0.144 |
Neg logit contributions | |
Parenthood | -0.142 |
mination | -0.141 |
ILA | -0.137 |
FTA | -0.129 |
buster | -0.127 |
Token | a |
Token ID | 257 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Parenthood | +0.208 |
mination | +0.207 |
ILA | +0.201 |
FTA | +0.190 |
buster | +0.188 |
Neg logit contributions | |
cffff | -0.207 |
jri | -0.182 |
uberty | -0.175 |
odied | -0.168 |
attled | -0.158 |
Token | civil |
Token ID | 3026 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Parenthood | +0.111 |
mination | +0.111 |
ILA | +0.107 |
FTA | +0.101 |
buster | +0.100 |
Neg logit contributions | |
cffff | -0.122 |
jri | -0.109 |
uberty | -0.104 |
odied | -0.100 |
attled | -0.095 |
Token | subpoena |
Token ID | 33262 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Parenthood | +0.168 |
mination | +0.167 |
ILA | +0.162 |
FTA | +0.152 |
buster | +0.150 |
Neg logit contributions | |
cffff | -0.197 |
jri | -0.176 |
uberty | -0.169 |
odied | -0.163 |
attled | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
Parenthood | +1.110 |
mination | +1.100 |
ILA | +1.069 |
FTA | +1.007 |
buster | +0.989 |
Neg logit contributions | |
cffff | -1.500 |
jri | -1.343 |
uberty | -1.295 |
odied | -1.249 |
attled | -1.187 |
Token | Last |
Token ID | 4586 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
Parenthood | +0.086 |
mination | +0.086 |
ILA | +0.084 |
FTA | +0.078 |
buster | +0.078 |
Neg logit contributions | |
cffff | -0.091 |
jri | -0.081 |
uberty | -0.078 |
odied | -0.075 |
attled | -0.071 |
Token | month |
Token ID | 1227 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
Parenthood | +0.581 |
mination | +0.577 |
ILA | +0.562 |
FTA | +0.535 |
buster | +0.526 |
Neg logit contributions | |
cffff | -0.616 |
jri | -0.543 |
uberty | -0.522 |
odied | -0.500 |
attled | -0.472 |
Token | , |
Token ID | 11 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
cffff | +1.004 |
jri | +0.896 |
uberty | +0.863 |
odied | +0.829 |
attled | +0.788 |
Neg logit contributions | |
Parenthood | -0.825 |
mination | -0.819 |
ILA | -0.795 |
FTA | -0.748 |
buster | -0.739 |
Token | The |
Token ID | 383 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Parenthood | +0.206 |
mination | +0.205 |
ILA | +0.199 |
FTA | +0.187 |
buster | +0.186 |
Neg logit contributions | |
cffff | -0.241 |
jri | -0.215 |
uberty | -0.207 |
odied | -0.199 |
attled | -0.188 |