Token | � |
Token ID | 447 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
HDL | +0.197 |
glacier | +0.178 |
LDL | +0.160 |
nir | +0.158 |
Greenland | +0.151 |
Neg logit contributions | |
toget | -0.153 |
dere | -0.153 |
ettings | -0.148 |
solicit | -0.146 |
•• | -0.145 |
Token | � |
Token ID | 247 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
HDL | +0.143 |
glacier | +0.126 |
LDL | +0.111 |
nir | +0.110 |
Esk | +0.103 |
Neg logit contributions | |
dere | -0.157 |
toget | -0.157 |
ettings | -0.153 |
solicit | -0.152 |
outlaw | -0.150 |
Token | s |
Token ID | 82 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
dere | +0.083 |
toget | +0.083 |
ettings | +0.080 |
solicit | +0.079 |
outlaw | +0.078 |
Neg logit contributions | |
HDL | -0.106 |
glacier | -0.095 |
LDL | -0.087 |
nir | -0.085 |
Greenland | -0.081 |
Token | US |
Token ID | 1294 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
HDL | +0.122 |
glacier | +0.110 |
LDL | +0.099 |
nir | +0.097 |
Greenland | +0.092 |
Neg logit contributions | |
toget | -0.103 |
dere | -0.102 |
ettings | -0.100 |
solicit | -0.099 |
•• | -0.098 |
Token | Cons |
Token ID | 3515 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
toget | +0.355 |
dere | +0.350 |
ettings | +0.340 |
solicit | +0.337 |
•• | +0.335 |
Neg logit contributions | |
HDL | -0.351 |
glacier | -0.313 |
LDL | -0.278 |
nir | -0.270 |
Greenland | -0.259 |
Token | ulate |
Token ID | 5039 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
HDL | +0.825 |
glacier | +0.733 |
LDL | +0.656 |
nir | +0.645 |
Greenland | +0.608 |
Neg logit contributions | |
dere | -0.811 |
toget | -0.810 |
ettings | -0.786 |
solicit | -0.781 |
outlaw | -0.772 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
dere | +1.629 |
toget | +1.614 |
solicit | +1.563 |
ettings | +1.551 |
outlaw | +1.541 |
Neg logit contributions | |
HDL | -2.129 |
glacier | -1.913 |
LDL | -1.746 |
nir | -1.739 |
uckles | -1.637 |
Token | protest |
Token ID | 5402 |
Feature activation | -6.91e-02 |
Pos logit contributions | |
toget | +0.071 |
dere | +0.071 |
ettings | +0.070 |
•• | +0.067 |
solicit | +0.067 |
Neg logit contributions | |
HDL | -0.104 |
glacier | -0.094 |
LDL | -0.086 |
nir | -0.084 |
Greenland | -0.081 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
HDL | +0.055 |
glacier | +0.050 |
LDL | +0.045 |
nir | +0.044 |
Greenland | +0.042 |
Neg logit contributions | |
toget | -0.046 |
dere | -0.046 |
ettings | -0.044 |
solicit | -0.044 |
•• | -0.043 |
Token | � |
Token ID | 447 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
dere | +0.132 |
toget | +0.132 |
ettings | +0.128 |
solicit | +0.127 |
outlaw | +0.125 |
Neg logit contributions | |
HDL | -0.170 |
glacier | -0.153 |
LDL | -0.139 |
nir | -0.137 |
Greenland | -0.130 |
Token | � |
Token ID | 247 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
HDL | +0.080 |
glacier | +0.070 |
LDL | +0.061 |
nir | +0.060 |
Esk | +0.055 |
Neg logit contributions | |
dere | -0.107 |
toget | -0.107 |
ettings | -0.104 |
solicit | -0.104 |
•• | -0.103 |
Token | More |
Token ID | 5167 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
dere | +0.139 |
toget | +0.139 |
ettings | +0.134 |
solicit | +0.133 |
•• | +0.131 |
Neg logit contributions | |
HDL | -0.180 |
glacier | -0.162 |
LDL | -0.147 |
nir | -0.145 |
Greenland | -0.138 |
Token | shots |
Token ID | 6934 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
HDL | +0.131 |
glacier | +0.118 |
LDL | +0.108 |
nir | +0.106 |
Greenland | +0.101 |
Neg logit contributions | |
dere | -0.100 |
toget | -0.100 |
ettings | -0.097 |
solicit | -0.096 |
outlaw | -0.095 |
Token | available |
Token ID | 1695 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
toget | +0.824 |
dere | +0.822 |
ettings | +0.791 |
solicit | +0.789 |
outlaw | +0.776 |
Neg logit contributions | |
HDL | -1.034 |
glacier | -0.927 |
LDL | -0.843 |
nir | -0.829 |
uckles | -0.789 |
Token | at |
Token ID | 379 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
dere | +0.560 |
toget | +0.560 |
ettings | +0.541 |
solicit | +0.537 |
outlaw | +0.530 |
Neg logit contributions | |
HDL | -0.700 |
glacier | -0.630 |
LDL | -0.570 |
nir | -0.562 |
Greenland | -0.533 |
Token | the |
Token ID | 262 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
toget | +0.304 |
dere | +0.304 |
ettings | +0.296 |
solicit | +0.293 |
outlaw | +0.290 |
Neg logit contributions | |
HDL | -0.334 |
glacier | -0.299 |
LDL | -0.268 |
nir | -0.265 |
Esk | -0.251 |
Token | gallery |
Token ID | 15604 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
toget | +0.200 |
dere | +0.200 |
ettings | +0.194 |
outlaw | +0.190 |
solicit | +0.190 |
Neg logit contributions | |
HDL | -0.278 |
glacier | -0.251 |
LDL | -0.228 |
nir | -0.227 |
Esk | -0.216 |
Token | .) |
Token ID | 2014 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
toget | +1.634 |
dere | +1.632 |
ettings | +1.576 |
solicit | +1.573 |
•• | +1.547 |
Neg logit contributions | |
HDL | -2.105 |
glacier | -1.885 |
LDL | -1.721 |
nir | -1.687 |
Esk | -1.605 |
Token | ■ |
Token ID | 34252 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
dere | +0.908 |
toget | +0.906 |
ettings | +0.876 |
solicit | +0.872 |
•• | +0.862 |
Neg logit contributions | |
HDL | -1.086 |
glacier | -0.976 |
LDL | -0.880 |
nir | -0.868 |
uckles | -0.822 |
Token | Event |
Token ID | 8558 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
dere | +0.891 |
toget | +0.890 |
ettings | +0.861 |
solicit | +0.856 |
outlaw | +0.844 |
Neg logit contributions | |
HDL | -1.065 |
glacier | -0.956 |
LDL | -0.863 |
nir | -0.850 |
Greenland | -0.806 |
Token | Qu |
Token ID | 2264 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
dere | +0.162 |
toget | +0.162 |
ettings | +0.156 |
solicit | +0.155 |
outlaw | +0.153 |
Neg logit contributions | |
HDL | -0.238 |
glacier | -0.215 |
LDL | -0.197 |
nir | -0.194 |
Greenland | -0.185 |
Token | ests |
Token ID | 3558 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
HDL | +0.056 |
glacier | +0.051 |
LDL | +0.046 |
nir | +0.046 |
Esk | +0.044 |
Neg logit contributions | |
dere | -0.035 |
toget | -0.035 |
ettings | -0.034 |
solicit | -0.034 |
•• | -0.033 |
Token | . |
Token ID | 764 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
dere | +0.735 |
toget | +0.733 |
ettings | +0.708 |
solicit | +0.706 |
outlaw | +0.696 |
Neg logit contributions | |
HDL | -0.901 |
glacier | -0.809 |
LDL | -0.732 |
nir | -0.723 |
uckles | -0.684 |
Token | y |
Token ID | 331 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
HDL | +0.415 |
glacier | +0.373 |
LDL | +0.338 |
nir | +0.333 |
Greenland | +0.316 |
Neg logit contributions | |
dere | -0.334 |
toget | -0.334 |
ettings | -0.323 |
solicit | -0.320 |
outlaw | -0.316 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
HDL | +0.380 |
glacier | +0.339 |
LDL | +0.305 |
nir | +0.301 |
Greenland | +0.284 |
Neg logit contributions | |
toget | -0.343 |
dere | -0.342 |
ettings | -0.331 |
solicit | -0.330 |
outlaw | -0.325 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
dere | +0.323 |
toget | +0.323 |
ettings | +0.312 |
solicit | +0.310 |
outlaw | +0.306 |
Neg logit contributions | |
HDL | -0.371 |
glacier | -0.332 |
LDL | -0.299 |
nir | -0.295 |
Greenland | -0.279 |
Token | return |
Token ID | 1441 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
HDL | +0.121 |
glacier | +0.108 |
LDL | +0.098 |
nir | +0.096 |
Greenland | +0.092 |
Neg logit contributions | |
dere | -0.094 |
toget | -0.094 |
ettings | -0.091 |
solicit | -0.090 |
•• | -0.090 |
Token | normal |
Token ID | 3487 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
dere | +0.457 |
toget | +0.456 |
ettings | +0.440 |
solicit | +0.438 |
outlaw | +0.432 |
Neg logit contributions | |
HDL | -0.584 |
glacier | -0.526 |
LDL | -0.476 |
nir | -0.470 |
uckles | -0.447 |
Token | ; |
Token ID | 2162 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
toget | +1.782 |
dere | +1.774 |
ettings | +1.720 |
solicit | +1.712 |
outlaw | +1.689 |
Neg logit contributions | |
HDL | -1.882 |
glacier | -1.674 |
LDL | -1.500 |
nir | -1.479 |
uckles | -1.397 |
Token | # |
Token ID | 1303 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
dere | +0.060 |
toget | +0.060 |
ettings | +0.058 |
solicit | +0.058 |
•• | +0.057 |
Neg logit contributions | |
HDL | -0.074 |
glacier | -0.066 |
LDL | -0.060 |
nir | -0.059 |
Greenland | -0.056 |
Token | endif |
Token ID | 32088 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
dere | +0.376 |
toget | +0.375 |
ettings | +0.361 |
solicit | +0.357 |
•• | +0.352 |
Neg logit contributions | |
HDL | -0.606 |
glacier | -0.551 |
LDL | -0.504 |
nir | -0.498 |
Esk | -0.475 |
Token | } |
Token ID | 1782 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
dere | +0.716 |
toget | +0.715 |
ettings | +0.690 |
solicit | +0.686 |
outlaw | +0.677 |
Neg logit contributions | |
HDL | -0.941 |
glacier | -0.848 |
LDL | -0.769 |
nir | -0.760 |
uckles | -0.723 |
Token | If |
Token ID | 1002 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
dere | +0.155 |
toget | +0.155 |
ettings | +0.150 |
solicit | +0.149 |
•• | +0.147 |
Neg logit contributions | |
HDL | -0.205 |
glacier | -0.185 |
LDL | -0.168 |
nir | -0.166 |
Greenland | -0.157 |
Token |
|
Token ID | 198 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
toget | +0.102 |
dere | +0.101 |
ettings | +0.098 |
solicit | +0.097 |
outlaw | +0.096 |
Neg logit contributions | |
HDL | -0.114 |
glacier | -0.101 |
LDL | -0.091 |
nir | -0.090 |
Greenland | -0.085 |
Token | impl |
Token ID | 23928 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
toget | +0.055 |
dere | +0.055 |
ettings | +0.053 |
solicit | +0.052 |
outlaw | +0.052 |
Neg logit contributions | |
HDL | -0.074 |
glacier | -0.067 |
LDL | -0.061 |
nir | -0.060 |
uckles | -0.057 |
Token | Board |
Token ID | 5926 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
dere | +0.641 |
toget | +0.641 |
ettings | +0.620 |
solicit | +0.616 |
outlaw | +0.608 |
Neg logit contributions | |
HDL | -0.757 |
glacier | -0.678 |
LDL | -0.612 |
nir | -0.603 |
Greenland | -0.571 |
Token | { |
Token ID | 1391 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
dere | +0.757 |
toget | +0.756 |
ettings | +0.731 |
solicit | +0.726 |
outlaw | +0.716 |
Neg logit contributions | |
HDL | -0.930 |
glacier | -0.835 |
LDL | -0.755 |
nir | -0.745 |
Greenland | -0.706 |
Token | pub |
Token ID | 2240 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
HDL | +0.185 |
glacier | +0.166 |
LDL | +0.149 |
nir | +0.146 |
Esk | +0.139 |
Neg logit contributions | |
toget | -0.166 |
dere | -0.166 |
ettings | -0.161 |
solicit | -0.160 |
•• | -0.158 |
Token | fn |
Token ID | 24714 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
dere | +0.539 |
toget | +0.538 |
ettings | +0.521 |
solicit | +0.517 |
outlaw | +0.511 |
Neg logit contributions | |
HDL | -0.633 |
glacier | -0.568 |
LDL | -0.512 |
nir | -0.505 |
Greenland | -0.478 |
Token | copy |
Token ID | 4866 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
dere | +1.200 |
toget | +1.195 |
ettings | +1.137 |
solicit | +1.136 |
outlaw | +1.116 |
Neg logit contributions | |
HDL | -2.361 |
glacier | -2.158 |
LDL | -1.992 |
nir | -1.973 |
Greenland | -1.889 |
Token | _ |
Token ID | 62 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
HDL | +0.101 |
glacier | +0.090 |
LDL | +0.080 |
nir | +0.079 |
uckles | +0.074 |
Neg logit contributions | |
dere | -0.098 |
toget | -0.098 |
ettings | -0.095 |
solicit | -0.095 |
outlaw | -0.093 |
Token | board |
Token ID | 3526 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
dere | +0.149 |
toget | +0.149 |
ettings | +0.144 |
solicit | +0.143 |
outlaw | +0.141 |
Neg logit contributions | |
HDL | -0.190 |
glacier | -0.171 |
LDL | -0.155 |
nir | -0.153 |
Greenland | -0.145 |
Token | ( |
Token ID | 357 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
dere | +0.002 |
toget | +0.002 |
ettings | +0.002 |
solicit | +0.001 |
•• | +0.001 |
Neg logit contributions | |
HDL | -0.002 |
glacier | -0.002 |
LDL | -0.001 |
nir | -0.001 |
uckles | -0.001 |
Token | & |
Token ID | 1222 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
dere | +0.332 |
toget | +0.332 |
ettings | +0.319 |
solicit | +0.317 |
outlaw | +0.312 |
Neg logit contributions | |
HDL | -0.524 |
glacier | -0.475 |
LDL | -0.435 |
nir | -0.429 |
Greenland | -0.411 |
Token | U |
Token ID | 471 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
toget | +0.066 |
dere | +0.065 |
ettings | +0.064 |
solicit | +0.063 |
•• | +0.063 |
Neg logit contributions | |
HDL | -0.059 |
glacier | -0.052 |
LDL | -0.046 |
nir | -0.045 |
Greenland | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
HDL | +0.106 |
glacier | +0.095 |
LDL | +0.085 |
nir | +0.084 |
Greenland | +0.080 |
Neg logit contributions | |
dere | -0.090 |
toget | -0.089 |
ettings | -0.087 |
solicit | -0.086 |
•• | -0.085 |
Token | S |
Token ID | 50 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
HDL | +0.190 |
glacier | +0.170 |
LDL | +0.154 |
nir | +0.152 |
Greenland | +0.144 |
Neg logit contributions | |
dere | -0.157 |
toget | -0.157 |
ettings | -0.152 |
solicit | -0.151 |
outlaw | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
toget | +0.136 |
dere | +0.136 |
ettings | +0.131 |
solicit | +0.131 |
•• | +0.129 |
Neg logit contributions | |
HDL | -0.173 |
glacier | -0.155 |
LDL | -0.141 |
nir | -0.139 |
Greenland | -0.132 |
Token | Cons |
Token ID | 3515 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
HDL | +0.177 |
glacier | +0.158 |
LDL | +0.141 |
nir | +0.137 |
Greenland | +0.132 |
Neg logit contributions | |
toget | -0.170 |
dere | -0.168 |
ettings | -0.164 |
solicit | -0.162 |
•• | -0.161 |
Token | ulate |
Token ID | 5039 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
HDL | +0.789 |
glacier | +0.701 |
LDL | +0.627 |
nir | +0.616 |
Greenland | +0.581 |
Neg logit contributions | |
toget | -0.786 |
dere | -0.785 |
ettings | -0.761 |
solicit | -0.756 |
outlaw | -0.748 |
Token | in |
Token ID | 287 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
dere | +1.527 |
toget | +1.496 |
solicit | +1.464 |
ettings | +1.447 |
outlaw | +1.442 |
Neg logit contributions | |
HDL | -2.004 |
glacier | -1.803 |
LDL | -1.643 |
nir | -1.637 |
uckles | -1.553 |
Token | Ad |
Token ID | 1215 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
HDL | +0.105 |
glacier | +0.092 |
LDL | +0.081 |
nir | +0.079 |
Greenland | +0.074 |
Neg logit contributions | |
toget | -0.133 |
dere | -0.131 |
ettings | -0.129 |
solicit | -0.127 |
•• | -0.126 |
Token | ana |
Token ID | 2271 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
dere | +0.327 |
toget | +0.323 |
ettings | +0.316 |
solicit | +0.315 |
outlaw | +0.311 |
Neg logit contributions | |
HDL | -0.256 |
glacier | -0.223 |
LDL | -0.196 |
nir | -0.191 |
� | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
toget | +0.336 |
dere | +0.335 |
ettings | +0.325 |
solicit | +0.322 |
•• | +0.318 |
Neg logit contributions | |
HDL | -0.420 |
glacier | -0.378 |
LDL | -0.341 |
nir | -0.336 |
Greenland | -0.320 |
Token | the |
Token ID | 262 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
toget | +0.033 |
dere | +0.033 |
ettings | +0.032 |
solicit | +0.032 |
•• | +0.032 |
Neg logit contributions | |
HDL | -0.041 |
glacier | -0.037 |
LDL | -0.033 |
nir | -0.033 |
Greenland | -0.031 |
Token | Guard |
Token ID | 4932 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
toget | +0.286 |
dere | +0.284 |
ettings | +0.275 |
solicit | +0.271 |
•• | +0.269 |
Neg logit contributions | |
HDL | -0.414 |
glacier | -0.374 |
LDL | -0.342 |
nir | -0.336 |
Esk | -0.322 |
Token | { |
Token ID | 1391 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
dere | +0.472 |
toget | +0.471 |
ettings | +0.457 |
solicit | +0.454 |
outlaw | +0.449 |
Neg logit contributions | |
HDL | -0.503 |
glacier | -0.448 |
LDL | -0.402 |
nir | -0.396 |
Greenland | -0.374 |
Token | ... |
Token ID | 2644 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
HDL | +0.555 |
glacier | +0.501 |
LDL | +0.457 |
nir | +0.447 |
Greenland | +0.426 |
Neg logit contributions | |
toget | -0.409 |
dere | -0.406 |
ettings | -0.394 |
solicit | -0.387 |
•• | -0.385 |
Token | } |
Token ID | 1782 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
dere | +0.916 |
toget | +0.912 |
ettings | +0.882 |
solicit | +0.878 |
outlaw | +0.867 |
Neg logit contributions | |
HDL | -1.200 |
glacier | -1.081 |
LDL | -0.979 |
nir | -0.969 |
uckles | -0.919 |
Token | pub |
Token ID | 2240 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
toget | +0.204 |
dere | +0.203 |
ettings | +0.196 |
solicit | +0.195 |
•• | +0.193 |
Neg logit contributions | |
HDL | -0.250 |
glacier | -0.224 |
LDL | -0.203 |
nir | -0.200 |
Greenland | -0.190 |
Token | fn |
Token ID | 24714 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
toget | +0.371 |
dere | +0.370 |
ettings | +0.358 |
solicit | +0.353 |
•• | +0.349 |
Neg logit contributions | |
HDL | -0.536 |
glacier | -0.485 |
LDL | -0.443 |
nir | -0.436 |
Esk | -0.415 |
Token | pin |
Token ID | 6757 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
dere | +1.513 |
toget | +1.508 |
solicit | +1.453 |
ettings | +1.449 |
outlaw | +1.432 |
Neg logit contributions | |
HDL | -1.995 |
glacier | -1.796 |
LDL | -1.633 |
nir | -1.613 |
� | -1.536 |
Token | () |
Token ID | 7499 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
dere | +0.394 |
toget | +0.394 |
ettings | +0.381 |
solicit | +0.379 |
outlaw | +0.374 |
Neg logit contributions | |
HDL | -0.424 |
glacier | -0.378 |
LDL | -0.340 |
nir | -0.334 |
Greenland | -0.316 |
Token | -> |
Token ID | 4613 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
dere | +0.516 |
toget | +0.514 |
ettings | +0.497 |
solicit | +0.496 |
outlaw | +0.490 |
Neg logit contributions | |
HDL | -0.616 |
glacier | -0.552 |
LDL | -0.498 |
nir | -0.493 |
Greenland | -0.467 |
Token | Guard |
Token ID | 4932 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
toget | +0.247 |
dere | +0.244 |
ettings | +0.239 |
solicit | +0.233 |
•• | +0.232 |
Neg logit contributions | |
HDL | -0.342 |
glacier | -0.310 |
LDL | -0.282 |
nir | -0.275 |
Greenland | -0.265 |
Token | ; |
Token ID | 2162 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
dere | +0.466 |
toget | +0.466 |
ettings | +0.451 |
solicit | +0.448 |
outlaw | +0.442 |
Neg logit contributions | |
HDL | -0.509 |
glacier | -0.454 |
LDL | -0.408 |
nir | -0.402 |
Greenland | -0.380 |
Token | many |
Token ID | 867 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
toget | +0.185 |
dere | +0.185 |
ettings | +0.179 |
solicit | +0.177 |
outlaw | +0.175 |
Neg logit contributions | |
HDL | -0.221 |
glacier | -0.199 |
LDL | -0.180 |
nir | -0.177 |
Greenland | -0.168 |
Token | ways |
Token ID | 2842 |
Feature activation | +8.95e-01 |
Pos logit contributions | |
toget | +0.642 |
dere | +0.642 |
ettings | +0.620 |
solicit | +0.615 |
outlaw | +0.607 |
Neg logit contributions | |
HDL | -0.823 |
glacier | -0.741 |
LDL | -0.672 |
nir | -0.662 |
Greenland | -0.630 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
dere | +0.561 |
toget | +0.560 |
ettings | +0.541 |
solicit | +0.537 |
outlaw | +0.529 |
Neg logit contributions | |
HDL | -0.751 |
glacier | -0.677 |
LDL | -0.615 |
nir | -0.607 |
Greenland | -0.577 |
Token | a |
Token ID | 257 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
HDL | +0.101 |
glacier | +0.090 |
LDL | +0.082 |
nir | +0.080 |
Greenland | +0.077 |
Neg logit contributions | |
dere | -0.083 |
toget | -0.083 |
ettings | -0.080 |
solicit | -0.080 |
WARN | -0.078 |
Token | college |
Token ID | 4152 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
toget | +0.139 |
dere | +0.138 |
ettings | +0.134 |
solicit | +0.133 |
outlaw | +0.132 |
Neg logit contributions | |
HDL | -0.169 |
glacier | -0.152 |
LDL | -0.137 |
nir | -0.135 |
Greenland | -0.128 |
Token | degree |
Token ID | 4922 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
dere | +0.539 |
toget | +0.539 |
ettings | +0.515 |
solicit | +0.515 |
outlaw | +0.508 |
Neg logit contributions | |
HDL | -0.737 |
glacier | -0.665 |
LDL | -0.605 |
nir | -0.598 |
uckles | -0.570 |
Token | is |
Token ID | 318 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
dere | +1.405 |
toget | +1.400 |
ettings | +1.341 |
solicit | +1.338 |
outlaw | +1.323 |
Neg logit contributions | |
HDL | -2.075 |
glacier | -1.877 |
LDL | -1.716 |
nir | -1.696 |
uckles | -1.614 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
HDL | +0.009 |
glacier | +0.008 |
LDL | +0.007 |
nir | +0.007 |
Greenland | +0.006 |
Neg logit contributions | |
dere | -0.008 |
toget | -0.008 |
ettings | -0.008 |
solicit | -0.008 |
outlaw | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
toget | +0.444 |
dere | +0.441 |
ettings | +0.424 |
solicit | +0.423 |
outlaw | +0.420 |
Neg logit contributions | |
HDL | -0.534 |
glacier | -0.479 |
LDL | -0.433 |
nir | -0.427 |
Greenland | -0.404 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
HDL | +0.281 |
glacier | +0.250 |
LDL | +0.225 |
nir | +0.220 |
Greenland | +0.209 |
Neg logit contributions | |
toget | -0.266 |
dere | -0.265 |
ettings | -0.259 |
solicit | -0.256 |
•• | -0.252 |
Token | high |
Token ID | 1029 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
toget | +0.019 |
dere | +0.019 |
ettings | +0.018 |
solicit | +0.018 |
•• | +0.018 |
Neg logit contributions | |
HDL | -0.025 |
glacier | -0.023 |
LDL | -0.021 |
nir | -0.020 |
Greenland | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
toget | +0.115 |
dere | +0.115 |
ettings | +0.111 |
solicit | +0.110 |
•• | +0.108 |
Neg logit contributions | |
HDL | -0.160 |
glacier | -0.145 |
LDL | -0.132 |
nir | -0.130 |
Greenland | -0.124 |
Token | decision |
Token ID | 2551 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
toget | +0.115 |
dere | +0.113 |
ettings | +0.110 |
solicit | +0.108 |
•• | +0.108 |
Neg logit contributions | |
HDL | -0.154 |
glacier | -0.140 |
LDL | -0.127 |
nir | -0.124 |
Greenland | -0.119 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
HDL | +0.199 |
glacier | +0.179 |
LDL | +0.162 |
nir | +0.159 |
Greenland | +0.151 |
Neg logit contributions | |
dere | -0.163 |
toget | -0.163 |
ettings | -0.157 |
solicit | -0.157 |
outlaw | -0.154 |
Token | several |
Token ID | 1811 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
toget | +0.072 |
dere | +0.071 |
ettings | +0.069 |
solicit | +0.068 |
•• | +0.067 |
Neg logit contributions | |
HDL | -0.093 |
glacier | -0.084 |
LDL | -0.076 |
nir | -0.075 |
Greenland | -0.071 |
Token | Silicon |
Token ID | 18210 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
toget | +0.435 |
dere | +0.433 |
ettings | +0.420 |
solicit | +0.414 |
•• | +0.409 |
Neg logit contributions | |
HDL | -0.605 |
glacier | -0.546 |
LDL | -0.497 |
nir | -0.489 |
Greenland | -0.467 |
Token | Valley |
Token ID | 6916 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
dere | +0.604 |
toget | +0.601 |
ettings | +0.576 |
solicit | +0.574 |
outlaw | +0.565 |
Neg logit contributions | |
HDL | -1.093 |
glacier | -0.997 |
LDL | -0.918 |
nir | -0.909 |
Greenland | -0.867 |
Token | mog |
Token ID | 32985 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
dere | +1.876 |
toget | +1.870 |
solicit | +1.821 |
ettings | +1.805 |
outlaw | +1.796 |
Neg logit contributions | |
HDL | -1.598 |
glacier | -1.403 |
LDL | -1.239 |
nir | -1.220 |
� | -1.140 |
Token | uls |
Token ID | 5753 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
HDL | +1.301 |
glacier | +1.183 |
nir | +1.081 |
LDL | +1.080 |
uckles | +1.035 |
Neg logit contributions | |
dere | -0.859 |
toget | -0.856 |
•• | -0.821 |
WARN | -0.816 |
ettings | -0.816 |
Token | to |
Token ID | 284 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
dere | +0.009 |
toget | +0.009 |
ettings | +0.009 |
solicit | +0.008 |
•• | +0.008 |
Neg logit contributions | |
HDL | -0.010 |
glacier | -0.009 |
LDL | -0.008 |
nir | -0.008 |
Greenland | -0.008 |
Token | pour |
Token ID | 12797 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
toget | +0.132 |
dere | +0.131 |
ettings | +0.128 |
•• | +0.126 |
solicit | +0.124 |
Neg logit contributions | |
HDL | -0.176 |
glacier | -0.160 |
LDL | -0.144 |
nir | -0.142 |
Greenland | -0.136 |
Token | millions |
Token ID | 5242 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
dere | +0.417 |
toget | +0.416 |
ettings | +0.403 |
solicit | +0.401 |
outlaw | +0.396 |
Neg logit contributions | |
HDL | -0.439 |
glacier | -0.391 |
LDL | -0.350 |
nir | -0.345 |
Greenland | -0.325 |
Token | < |
Token ID | 1279 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
dere | +0.362 |
toget | +0.362 |
ettings | +0.353 |
solicit | +0.351 |
outlaw | +0.347 |
Neg logit contributions | |
HDL | -0.274 |
glacier | -0.238 |
LDL | -0.208 |
nir | -0.204 |
Greenland | -0.189 |
Token | T |
Token ID | 309 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
HDL | +0.376 |
glacier | +0.335 |
LDL | +0.305 |
nir | +0.297 |
Esk | +0.283 |
Neg logit contributions | |
toget | -0.325 |
dere | -0.324 |
ettings | -0.313 |
solicit | -0.311 |
outlaw | -0.307 |
Token | > |
Token ID | 1875 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
dere | +0.061 |
toget | +0.060 |
ettings | +0.059 |
solicit | +0.059 |
outlaw | +0.058 |
Neg logit contributions | |
HDL | -0.049 |
glacier | -0.043 |
LDL | -0.037 |
nir | -0.037 |
Greenland | -0.034 |
Token | { |
Token ID | 1391 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
HDL | +0.254 |
glacier | +0.227 |
LDL | +0.206 |
nir | +0.202 |
Greenland | +0.192 |
Neg logit contributions | |
toget | -0.207 |
dere | -0.207 |
ettings | -0.200 |
solicit | -0.198 |
•• | -0.196 |
Token | pub |
Token ID | 2240 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
HDL | +0.083 |
glacier | +0.074 |
LDL | +0.068 |
nir | +0.066 |
Greenland | +0.063 |
Neg logit contributions | |
toget | -0.063 |
dere | -0.062 |
ettings | -0.061 |
solicit | -0.060 |
•• | -0.059 |
Token | fn |
Token ID | 24714 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
dere | +0.567 |
toget | +0.566 |
ettings | +0.548 |
solicit | +0.545 |
outlaw | +0.538 |
Neg logit contributions | |
HDL | -0.634 |
glacier | -0.567 |
LDL | -0.509 |
nir | -0.503 |
Greenland | -0.475 |
Token | load |
Token ID | 3440 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
dere | +1.672 |
toget | +1.667 |
solicit | +1.609 |
ettings | +1.607 |
outlaw | +1.589 |
Neg logit contributions | |
HDL | -1.783 |
glacier | -1.589 |
LDL | -1.425 |
nir | -1.408 |
uckles | -1.331 |
Token | < |
Token ID | 1279 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
toget | +0.224 |
dere | +0.224 |
ettings | +0.217 |
solicit | +0.216 |
•• | +0.213 |
Neg logit contributions | |
HDL | -0.253 |
glacier | -0.226 |
LDL | -0.204 |
nir | -0.201 |
Greenland | -0.190 |
Token | ' |
Token ID | 705 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
HDL | +0.276 |
glacier | +0.245 |
LDL | +0.221 |
nir | +0.217 |
Greenland | +0.205 |
Neg logit contributions | |
toget | -0.258 |
dere | -0.257 |
ettings | -0.249 |
solicit | -0.247 |
outlaw | -0.244 |
Token | a |
Token ID | 64 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
HDL | +0.251 |
glacier | +0.219 |
LDL | +0.193 |
nir | +0.189 |
uckles | +0.176 |
Neg logit contributions | |
toget | -0.315 |
dere | -0.314 |
ettings | -0.305 |
solicit | -0.304 |
outlaw | -0.300 |
Token | > |
Token ID | 1875 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
toget | +0.149 |
dere | +0.148 |
ettings | +0.144 |
solicit | +0.143 |
outlaw | +0.142 |
Neg logit contributions | |
HDL | -0.140 |
glacier | -0.124 |
LDL | -0.110 |
nir | -0.108 |
Greenland | -0.102 |
Token | < |
Token ID | 1279 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
HDL | +0.128 |
glacier | +0.113 |
LDL | +0.100 |
nir | +0.098 |
Greenland | +0.092 |
Neg logit contributions | |
dere | -0.146 |
toget | -0.146 |
ettings | -0.141 |
solicit | -0.141 |
outlaw | -0.139 |
Token | T |
Token ID | 309 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
HDL | +0.689 |
glacier | +0.612 |
LDL | +0.559 |
nir | +0.540 |
Esk | +0.516 |
Neg logit contributions | |
toget | -0.609 |
dere | -0.600 |
ettings | -0.583 |
solicit | -0.577 |
outlaw | -0.569 |
Token | > |
Token ID | 1875 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
HDL | +0.282 |
glacier | +0.247 |
LDL | +0.217 |
nir | +0.213 |
Greenland | +0.198 |
Neg logit contributions | |
dere | -0.352 |
toget | -0.352 |
ettings | -0.342 |
solicit | -0.340 |
outlaw | -0.336 |
Token | { |
Token ID | 1391 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
HDL | +0.534 |
glacier | +0.480 |
LDL | +0.437 |
nir | +0.429 |
Greenland | +0.408 |
Neg logit contributions | |
toget | -0.410 |
dere | -0.408 |
ettings | -0.394 |
solicit | -0.391 |
•• | -0.386 |
Token | pub |
Token ID | 2240 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
HDL | +0.530 |
glacier | +0.473 |
LDL | +0.427 |
nir | +0.415 |
Greenland | +0.395 |
Neg logit contributions | |
toget | -0.483 |
dere | -0.480 |
ettings | -0.467 |
solicit | -0.462 |
•• | -0.458 |
Token | fn |
Token ID | 24714 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
dere | +0.392 |
toget | +0.392 |
ettings | +0.379 |
solicit | +0.377 |
outlaw | +0.372 |
Neg logit contributions | |
HDL | -0.473 |
glacier | -0.424 |
LDL | -0.383 |
nir | -0.378 |
Greenland | -0.358 |
Token | new |
Token ID | 649 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
dere | +1.403 |
toget | +1.395 |
solicit | +1.346 |
ettings | +1.334 |
outlaw | +1.324 |
Neg logit contributions | |
HDL | -1.957 |
glacier | -1.768 |
LDL | -1.607 |
nir | -1.596 |
� | -1.524 |
Token | ( |
Token ID | 357 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
dere | +0.457 |
toget | +0.456 |
ettings | +0.442 |
solicit | +0.439 |
outlaw | +0.434 |
Neg logit contributions | |
HDL | -0.501 |
glacier | -0.447 |
LDL | -0.402 |
nir | -0.396 |
Greenland | -0.374 |
Token | t |
Token ID | 256 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
dere | +0.361 |
toget | +0.360 |
ettings | +0.346 |
solicit | +0.344 |
outlaw | +0.338 |
Neg logit contributions | |
HDL | -0.573 |
glacier | -0.520 |
LDL | -0.476 |
nir | -0.470 |
Greenland | -0.449 |
Token | : |
Token ID | 1058 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
HDL | +0.093 |
glacier | +0.081 |
LDL | +0.072 |
nir | +0.071 |
Greenland | +0.066 |
Neg logit contributions | |
dere | -0.107 |
toget | -0.106 |
ettings | -0.104 |
solicit | -0.103 |
outlaw | -0.102 |
Token | T |
Token ID | 309 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
toget | +0.554 |
dere | +0.551 |
ettings | +0.535 |
solicit | +0.529 |
•• | +0.523 |
Neg logit contributions | |
HDL | -0.705 |
glacier | -0.633 |
LDL | -0.576 |
nir | -0.563 |
Greenland | -0.538 |
Token | Spending |
Token ID | 43902 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
HDL | +0.045 |
glacier | +0.041 |
LDL | +0.037 |
nir | +0.036 |
Greenland | +0.035 |
Neg logit contributions | |
toget | -0.036 |
dere | -0.036 |
ettings | -0.035 |
solicit | -0.035 |
•• | -0.034 |
Token | C |
Token ID | 327 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
dere | +0.484 |
toget | +0.484 |
ettings | +0.467 |
solicit | +0.464 |
outlaw | +0.457 |
Neg logit contributions | |
HDL | -0.621 |
glacier | -0.559 |
LDL | -0.507 |
nir | -0.500 |
Greenland | -0.475 |
Token | uts |
Token ID | 5500 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
HDL | +0.023 |
glacier | +0.021 |
LDL | +0.019 |
nir | +0.019 |
uckles | +0.018 |
Neg logit contributions | |
toget | -0.015 |
dere | -0.015 |
ettings | -0.014 |
solicit | -0.014 |
outlaw | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
dere | +0.312 |
toget | +0.312 |
ettings | +0.301 |
solicit | +0.298 |
outlaw | +0.294 |
Neg logit contributions | |
HDL | -0.451 |
glacier | -0.408 |
LDL | -0.372 |
nir | -0.367 |
Greenland | -0.350 |
Token | Def |
Token ID | 2896 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
dere | +0.198 |
toget | +0.196 |
ettings | +0.188 |
solicit | +0.187 |
outlaw | +0.182 |
Neg logit contributions | |
HDL | -0.422 |
glacier | -0.387 |
LDL | -0.358 |
nir | -0.354 |
uckles | -0.340 |
Token | icit |
Token ID | 3628 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
HDL | +0.507 |
glacier | +0.475 |
LDL | +0.447 |
nir | +0.444 |
Greenland | +0.431 |
Neg logit contributions | |
dere | -0.071 |
toget | -0.071 |
ettings | -0.062 |
solicit | -0.060 |
outlaw | -0.057 |
Token | Reduction |
Token ID | 33396 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
dere | +1.411 |
toget | +1.410 |
solicit | +1.361 |
ettings | +1.355 |
outlaw | +1.343 |
Neg logit contributions | |
HDL | -1.858 |
glacier | -1.681 |
LDL | -1.521 |
nir | -1.502 |
uckles | -1.436 |
Token | Working |
Token ID | 14594 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
dere | +0.324 |
toget | +0.324 |
ettings | +0.312 |
solicit | +0.311 |
outlaw | +0.307 |
Neg logit contributions | |
HDL | -0.436 |
glacier | -0.393 |
LDL | -0.357 |
nir | -0.353 |
uckles | -0.335 |
Token | Group |
Token ID | 4912 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
toget | +0.013 |
dere | +0.013 |
solicit | +0.012 |
ettings | +0.012 |
outlaw | +0.012 |
Neg logit contributions | |
HDL | -0.015 |
glacier | -0.013 |
LDL | -0.012 |
nir | -0.012 |
uckles | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
dere | +0.115 |
toget | +0.114 |
ettings | +0.111 |
solicit | +0.110 |
outlaw | +0.108 |
Neg logit contributions | |
HDL | -0.143 |
glacier | -0.129 |
LDL | -0.117 |
nir | -0.115 |
Greenland | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
HDL | +0.216 |
glacier | +0.192 |
LDL | +0.174 |
nir | +0.171 |
Greenland | +0.163 |
Neg logit contributions | |
toget | -0.183 |
dere | -0.183 |
ettings | -0.177 |
solicit | -0.175 |
outlaw | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
dere | +0.210 |
toget | +0.209 |
ettings | +0.202 |
solicit | +0.200 |
outlaw | +0.198 |
Neg logit contributions | |
HDL | -0.293 |
glacier | -0.265 |
LDL | -0.241 |
nir | -0.238 |
Greenland | -0.226 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
dere | +0.207 |
toget | +0.207 |
ettings | +0.200 |
solicit | +0.199 |
outlaw | +0.196 |
Neg logit contributions | |
HDL | -0.247 |
glacier | -0.221 |
LDL | -0.200 |
nir | -0.197 |
Greenland | -0.187 |
Token |
|
Token ID | 198 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
toget | +0.165 |
dere | +0.164 |
ettings | +0.159 |
solicit | +0.158 |
outlaw | +0.156 |
Neg logit contributions | |
HDL | -0.185 |
glacier | -0.165 |
LDL | -0.149 |
nir | -0.147 |
Greenland | -0.139 |
Token | For |
Token ID | 1890 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
dere | +0.089 |
toget | +0.089 |
ettings | +0.086 |
solicit | +0.085 |
•• | +0.084 |
Neg logit contributions | |
HDL | -0.114 |
glacier | -0.103 |
LDL | -0.093 |
nir | -0.092 |
Greenland | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
toget | +0.189 |
dere | +0.189 |
ettings | +0.183 |
solicit | +0.181 |
•• | +0.179 |
Neg logit contributions | |
HDL | -0.224 |
glacier | -0.201 |
LDL | -0.181 |
nir | -0.178 |
Greenland | -0.169 |
Token | gallery |
Token ID | 15604 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
toget | +0.118 |
dere | +0.118 |
ettings | +0.114 |
solicit | +0.113 |
•• | +0.112 |
Neg logit contributions | |
HDL | -0.150 |
glacier | -0.136 |
LDL | -0.123 |
nir | -0.120 |
Greenland | -0.115 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
dere | +1.282 |
toget | +1.278 |
ettings | +1.231 |
solicit | +1.230 |
outlaw | +1.208 |
Neg logit contributions | |
HDL | -1.974 |
glacier | -1.782 |
LDL | -1.637 |
nir | -1.621 |
Esk | -1.541 |
Token | today |
Token ID | 1909 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
toget | +0.084 |
dere | +0.084 |
ettings | +0.082 |
solicit | +0.081 |
•• | +0.080 |
Neg logit contributions | |
HDL | -0.099 |
glacier | -0.089 |
LDL | -0.080 |
nir | -0.079 |
Greenland | -0.075 |
Token | 's |
Token ID | 338 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
dere | +0.033 |
toget | +0.033 |
ettings | +0.031 |
solicit | +0.031 |
outlaw | +0.031 |
Neg logit contributions | |
HDL | -0.045 |
glacier | -0.040 |
LDL | -0.037 |
nir | -0.036 |
Greenland | -0.034 |
Token | photos |
Token ID | 5205 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
toget | +0.079 |
dere | +0.078 |
ettings | +0.076 |
solicit | +0.075 |
•• | +0.074 |
Neg logit contributions | |
HDL | -0.105 |
glacier | -0.095 |
LDL | -0.086 |
nir | -0.085 |
Greenland | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
HDL | +0.184 |
glacier | +0.166 |
LDL | +0.150 |
nir | +0.146 |
Greenland | +0.142 |
Neg logit contributions | |
toget | -0.146 |
dere | -0.145 |
ettings | -0.139 |
•• | -0.138 |
solicit | -0.138 |
Token | Much |
Token ID | 13111 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
dere | +0.024 |
toget | +0.024 |
ettings | +0.023 |
solicit | +0.023 |
outlaw | +0.022 |
Neg logit contributions | |
HDL | -0.028 |
glacier | -0.025 |
LDL | -0.023 |
nir | -0.022 |
Greenland | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
HDL | +0.053 |
glacier | +0.048 |
LDL | +0.043 |
nir | +0.043 |
Greenland | +0.040 |
Neg logit contributions | |
dere | -0.042 |
toget | -0.042 |
solicit | -0.040 |
ettings | -0.040 |
outlaw | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
dere | +0.047 |
toget | +0.047 |
ettings | +0.046 |
solicit | +0.045 |
outlaw | +0.045 |
Neg logit contributions | |
HDL | -0.053 |
glacier | -0.047 |
LDL | -0.043 |
nir | -0.042 |
uckles | -0.040 |
Token | commentary |
Token ID | 14604 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
toget | +0.092 |
dere | +0.092 |
ettings | +0.089 |
solicit | +0.088 |
outlaw | +0.087 |
Neg logit contributions | |
HDL | -0.098 |
glacier | -0.088 |
LDL | -0.079 |
nir | -0.077 |
Greenland | -0.073 |
Token | rev |
Token ID | 2710 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
HDL | +0.116 |
glacier | +0.104 |
LDL | +0.094 |
nir | +0.092 |
Greenland | +0.087 |
Neg logit contributions | |
toget | -0.098 |
dere | -0.098 |
ettings | -0.095 |
solicit | -0.094 |
•• | -0.093 |
Token | olved |
Token ID | 5634 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
HDL | +0.003 |
glacier | +0.003 |
LDL | +0.002 |
nir | +0.002 |
� | +0.002 |
Neg logit contributions | |
toget | -0.003 |
dere | -0.003 |
ettings | -0.003 |
solicit | -0.003 |
•• | -0.003 |
Token | around |
Token ID | 1088 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
dere | +1.399 |
toget | +1.371 |
solicit | +1.336 |
outlaw | +1.319 |
ettings | +1.301 |
Neg logit contributions | |
HDL | -1.814 |
glacier | -1.638 |
LDL | -1.493 |
nir | -1.476 |
Esk | -1.392 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
dere | +0.230 |
toget | +0.229 |
ettings | +0.222 |
solicit | +0.221 |
outlaw | +0.218 |
Neg logit contributions | |
HDL | -0.262 |
glacier | -0.234 |
LDL | -0.211 |
nir | -0.209 |
uckles | -0.197 |
Token | aesthetics |
Token ID | 35431 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
toget | +0.118 |
dere | +0.117 |
ettings | +0.114 |
solicit | +0.113 |
•• | +0.112 |
Neg logit contributions | |
HDL | -0.145 |
glacier | -0.130 |
LDL | -0.117 |
nir | -0.115 |
Greenland | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
HDL | +0.323 |
glacier | +0.292 |
LDL | +0.266 |
nir | +0.263 |
Greenland | +0.250 |
Neg logit contributions | |
dere | -0.228 |
toget | -0.227 |
ettings | -0.219 |
solicit | -0.217 |
outlaw | -0.214 |
Token | design |
Token ID | 1486 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
toget | +0.074 |
dere | +0.074 |
ettings | +0.071 |
solicit | +0.071 |
•• | +0.070 |
Neg logit contributions | |
HDL | -0.079 |
glacier | -0.071 |
LDL | -0.063 |
nir | -0.062 |
Greenland | -0.059 |
Token | popular |
Token ID | 2968 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
dere | +0.224 |
toget | +0.223 |
ettings | +0.214 |
solicit | +0.213 |
outlaw | +0.210 |
Neg logit contributions | |
HDL | -0.336 |
glacier | -0.305 |
LDL | -0.278 |
nir | -0.276 |
uckles | -0.263 |
Token | Asus |
Token ID | 46301 |
Feature activation | +3.91e-03 |
Pos logit contributions | |
dere | +0.159 |
toget | +0.159 |
ettings | +0.154 |
solicit | +0.153 |
outlaw | +0.151 |
Neg logit contributions | |
HDL | -0.166 |
glacier | -0.148 |
LDL | -0.132 |
nir | -0.130 |
uckles | -0.123 |
Token | R |
Token ID | 371 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
dere | +0.003 |
toget | +0.003 |
ettings | +0.003 |
solicit | +0.003 |
outlaw | +0.003 |
Neg logit contributions | |
HDL | -0.003 |
glacier | -0.003 |
nir | -0.002 |
LDL | -0.002 |
uckles | -0.002 |
Token | OG |
Token ID | 7730 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
toget | +0.113 |
dere | +0.112 |
ettings | +0.109 |
solicit | +0.109 |
outlaw | +0.107 |
Neg logit contributions | |
HDL | -0.124 |
glacier | -0.111 |
LDL | -0.099 |
nir | -0.098 |
Esk | -0.092 |
Token | Swift |
Token ID | 15608 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
dere | +0.131 |
toget | +0.130 |
ettings | +0.126 |
solicit | +0.125 |
outlaw | +0.124 |
Neg logit contributions | |
HDL | -0.172 |
glacier | -0.155 |
LDL | -0.141 |
nir | -0.140 |
uckles | -0.133 |
Token | PG |
Token ID | 23842 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
dere | +0.227 |
ettings | +0.221 |
toget | +0.221 |
solicit | +0.220 |
Wy | +0.218 |
Neg logit contributions | |
HDL | -0.143 |
glacier | -0.119 |
LDL | -0.103 |
nir | -0.102 |
� | -0.097 |
Token | 278 |
Token ID | 25870 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
dere | +1.465 |
toget | +1.463 |
ettings | +1.425 |
solicit | +1.423 |
•• | +1.393 |
Neg logit contributions | |
HDL | -1.690 |
glacier | -1.509 |
LDL | -1.363 |
nir | -1.339 |
uckles | -1.273 |
Token | Q |
Token ID | 48 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
toget | +0.308 |
dere | +0.305 |
ettings | +0.298 |
solicit | +0.294 |
outlaw | +0.290 |
Neg logit contributions | |
HDL | -0.382 |
glacier | -0.345 |
LDL | -0.311 |
nir | -0.307 |
Esk | -0.291 |
Token | with |
Token ID | 351 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
dere | +0.383 |
toget | +0.383 |
ettings | +0.372 |
solicit | +0.369 |
outlaw | +0.364 |
Neg logit contributions | |
HDL | -0.436 |
glacier | -0.392 |
LDL | -0.351 |
nir | -0.347 |
uckles | -0.330 |
Token | its |
Token ID | 663 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
HDL | +0.006 |
glacier | +0.006 |
LDL | +0.005 |
nir | +0.005 |
uckles | +0.005 |
Neg logit contributions | |
dere | -0.005 |
toget | -0.005 |
ettings | -0.005 |
solicit | -0.005 |
outlaw | -0.005 |
Token | 144 |
Token ID | 20224 |
Feature activation | +7.38e-04 |
Pos logit contributions | |
HDL | +0.046 |
glacier | +0.041 |
LDL | +0.037 |
nir | +0.037 |
uckles | +0.035 |
Neg logit contributions | |
dere | -0.040 |
toget | -0.039 |
ettings | -0.038 |
solicit | -0.038 |
outlaw | -0.037 |
Token | 4 |
Token ID | 604 |
Feature activation | +5.53e-02 |
Pos logit contributions | |
HDL | +0.126 |
glacier | +0.113 |
LDL | +0.101 |
nir | +0.100 |
Greenland | +0.094 |
Neg logit contributions | |
dere | -0.115 |
toget | -0.115 |
ettings | -0.111 |
solicit | -0.111 |
outlaw | -0.109 |
Token | ms |
Token ID | 907 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
dere | +0.027 |
toget | +0.027 |
ettings | +0.026 |
solicit | +0.026 |
•• | +0.025 |
Neg logit contributions | |
HDL | -0.054 |
glacier | -0.049 |
LDL | -0.046 |
nir | -0.045 |
Greenland | -0.043 |
Token | G |
Token ID | 402 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
dere | +0.324 |
toget | +0.323 |
ettings | +0.315 |
solicit | +0.312 |
•• | +0.309 |
Neg logit contributions | |
HDL | -0.288 |
glacier | -0.256 |
LDL | -0.225 |
nir | -0.224 |
uckles | -0.209 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
dere | +0.465 |
toget | +0.462 |
ettings | +0.448 |
solicit | +0.440 |
•• | +0.432 |
Neg logit contributions | |
HDL | -0.915 |
glacier | -0.839 |
LDL | -0.771 |
nir | -0.763 |
Esk | -0.734 |
Token | G |
Token ID | 38 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
dere | +0.452 |
toget | +0.449 |
ettings | +0.438 |
solicit | +0.435 |
•• | +0.431 |
Neg logit contributions | |
HDL | -0.462 |
glacier | -0.413 |
LDL | -0.368 |
nir | -0.363 |
uckles | -0.342 |
Token | AU |
Token ID | 27548 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
dere | +0.411 |
toget | +0.408 |
ettings | +0.398 |
solicit | +0.396 |
WARN | +0.390 |
Neg logit contributions | |
HDL | -0.409 |
glacier | -0.366 |
LDL | -0.324 |
nir | -0.322 |
uckles | -0.303 |
Token | Opt |
Token ID | 13123 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
dere | +1.848 |
toget | +1.823 |
solicit | +1.802 |
ettings | +1.795 |
WARN | +1.789 |
Neg logit contributions | |
HDL | -1.272 |
glacier | -1.128 |
nir | -0.954 |
LDL | -0.953 |
uckles | -0.886 |
Token | ronics |
Token ID | 20844 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
HDL | +0.001 |
glacier | +0.001 |
LDL | +0.001 |
nir | +0.001 |
uckles | +0.001 |
Neg logit contributions | |
toget | -0.001 |
dere | -0.001 |
solicit | -0.001 |
ettings | -0.001 |
outlaw | -0.001 |
Token | AH |
Token ID | 28159 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
dere | +0.299 |
toget | +0.297 |
ettings | +0.292 |
solicit | +0.290 |
WARN | +0.288 |
Neg logit contributions | |
HDL | -0.187 |
glacier | -0.162 |
LDL | -0.137 |
nir | -0.137 |
uckles | -0.125 |
Token | VA |
Token ID | 11731 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
dere | +0.042 |
toget | +0.042 |
ettings | +0.041 |
solicit | +0.041 |
•• | +0.040 |
Neg logit contributions | |
HDL | -0.032 |
glacier | -0.029 |
LDL | -0.025 |
nir | -0.024 |
Esk | -0.023 |
Token | ( |
Token ID | 357 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
dere | +0.080 |
toget | +0.080 |
ettings | +0.078 |
solicit | +0.077 |
•• | +0.076 |
Neg logit contributions | |
HDL | -0.103 |
glacier | -0.094 |
LDL | -0.084 |
nir | -0.084 |
uckles | -0.079 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
HDL | +0.121 |
glacier | +0.108 |
LDL | +0.097 |
nir | +0.096 |
Greenland | +0.091 |
Neg logit contributions | |
dere | -0.109 |
toget | -0.109 |
ettings | -0.106 |
solicit | -0.105 |
outlaw | -0.104 |
Token | ms |
Token ID | 907 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
toget | +0.060 |
dere | +0.060 |
ettings | +0.057 |
solicit | +0.057 |
outlaw | +0.056 |
Neg logit contributions | |
HDL | -0.117 |
glacier | -0.107 |
LDL | -0.099 |
nir | -0.098 |
Greenland | -0.093 |
Token | G |
Token ID | 402 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
dere | +0.365 |
toget | +0.362 |
ettings | +0.354 |
solicit | +0.351 |
•• | +0.347 |
Neg logit contributions | |
HDL | -0.326 |
glacier | -0.291 |
LDL | -0.255 |
nir | -0.255 |
uckles | -0.237 |
Token | 2 |
Token ID | 17 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
toget | +0.497 |
dere | +0.496 |
ettings | +0.474 |
solicit | +0.470 |
outlaw | +0.462 |
Neg logit contributions | |
HDL | -0.927 |
glacier | -0.847 |
LDL | -0.780 |
nir | -0.771 |
Greenland | -0.739 |
Token | G |
Token ID | 38 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
dere | +0.461 |
toget | +0.459 |
ettings | +0.447 |
solicit | +0.444 |
•• | +0.439 |
Neg logit contributions | |
HDL | -0.468 |
glacier | -0.417 |
LDL | -0.372 |
nir | -0.367 |
uckles | -0.345 |
Token | AU |
Token ID | 27548 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
dere | +0.469 |
toget | +0.466 |
ettings | +0.455 |
solicit | +0.452 |
outlaw | +0.447 |
Neg logit contributions | |
HDL | -0.433 |
glacier | -0.384 |
LDL | -0.339 |
nir | -0.335 |
uckles | -0.314 |
Token | Opt |
Token ID | 13123 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
dere | +1.850 |
toget | +1.825 |
solicit | +1.802 |
ettings | +1.797 |
WARN | +1.785 |
Neg logit contributions | |
HDL | -1.254 |
glacier | -1.103 |
LDL | -0.936 |
nir | -0.933 |
uckles | -0.864 |
Token | ronics |
Token ID | 20844 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
HDL | +0.049 |
glacier | +0.042 |
LDL | +0.037 |
nir | +0.037 |
uckles | +0.034 |
Neg logit contributions | |
toget | -0.061 |
dere | -0.060 |
solicit | -0.058 |
ettings | -0.058 |
outlaw | -0.058 |
Token | AH |
Token ID | 28159 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
dere | +0.266 |
toget | +0.264 |
ettings | +0.259 |
solicit | +0.257 |
WARN | +0.256 |
Neg logit contributions | |
HDL | -0.165 |
glacier | -0.144 |
LDL | -0.121 |
nir | -0.121 |
uckles | -0.110 |
Token | VA |
Token ID | 11731 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
dere | +0.029 |
toget | +0.029 |
ettings | +0.028 |
solicit | +0.028 |
•• | +0.028 |
Neg logit contributions | |
HDL | -0.023 |
glacier | -0.020 |
LDL | -0.017 |
nir | -0.017 |
Esk | -0.016 |
Token | ( |
Token ID | 357 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
toget | +0.023 |
dere | +0.023 |
ettings | +0.022 |
solicit | +0.022 |
outlaw | +0.021 |
Neg logit contributions | |
HDL | -0.028 |
glacier | -0.025 |
LDL | -0.022 |
nir | -0.022 |
Greenland | -0.021 |
Token | But |
Token ID | 887 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
HDL | +0.205 |
glacier | +0.181 |
LDL | +0.166 |
nir | +0.162 |
Greenland | +0.154 |
Neg logit contributions | |
toget | -0.182 |
dere | -0.181 |
ettings | -0.174 |
solicit | -0.173 |
outlaw | -0.171 |
Token | the |
Token ID | 262 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
dere | +0.093 |
toget | +0.092 |
ettings | +0.089 |
solicit | +0.088 |
•• | +0.088 |
Neg logit contributions | |
HDL | -0.109 |
glacier | -0.097 |
LDL | -0.088 |
nir | -0.086 |
Greenland | -0.082 |
Token | five |
Token ID | 1936 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
toget | +0.056 |
dere | +0.056 |
ettings | +0.054 |
solicit | +0.054 |
•• | +0.053 |
Neg logit contributions | |
HDL | -0.074 |
glacier | -0.067 |
LDL | -0.061 |
nir | -0.059 |
Greenland | -0.057 |
Token | Google |
Token ID | 3012 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
dere | +0.272 |
toget | +0.271 |
ettings | +0.262 |
solicit | +0.260 |
outlaw | +0.257 |
Neg logit contributions | |
HDL | -0.359 |
glacier | -0.324 |
LDL | -0.294 |
nir | -0.289 |
Greenland | -0.276 |
Token | Android |
Token ID | 5565 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
dere | +0.086 |
toget | +0.086 |
ettings | +0.082 |
solicit | +0.082 |
outlaw | +0.081 |
Neg logit contributions | |
HDL | -0.113 |
glacier | -0.102 |
LDL | -0.092 |
nir | -0.091 |
Greenland | -0.087 |
Token | Honey |
Token ID | 21788 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
toget | +0.795 |
dere | +0.795 |
ettings | +0.767 |
solicit | +0.762 |
outlaw | +0.752 |
Neg logit contributions | |
HDL | -0.955 |
glacier | -0.857 |
LDL | -0.774 |
nir | -0.762 |
Greenland | -0.723 |
Token | comb |
Token ID | 24011 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
dere | +1.199 |
toget | +1.189 |
ettings | +1.151 |
solicit | +1.150 |
outlaw | +1.121 |
Neg logit contributions | |
HDL | -1.928 |
glacier | -1.750 |
LDL | -1.609 |
nir | -1.585 |
� | -1.513 |
Token | tablets |
Token ID | 17255 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
dere | +0.575 |
toget | +0.574 |
ettings | +0.554 |
solicit | +0.550 |
outlaw | +0.543 |
Neg logit contributions | |
HDL | -0.705 |
glacier | -0.633 |
LDL | -0.572 |
nir | -0.564 |
Greenland | -0.535 |
Token | that |
Token ID | 326 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
dere | +0.328 |
toget | +0.328 |
ettings | +0.317 |
solicit | +0.315 |
•• | +0.311 |
Neg logit contributions | |
HDL | -0.382 |
glacier | -0.342 |
LDL | -0.308 |
nir | -0.303 |
Greenland | -0.288 |
Token | have |
Token ID | 423 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
dere | +0.119 |
toget | +0.119 |
ettings | +0.115 |
solicit | +0.114 |
•• | +0.113 |
Neg logit contributions | |
HDL | -0.135 |
glacier | -0.121 |
LDL | -0.109 |
nir | -0.107 |
Greenland | -0.102 |
Token | come |
Token ID | 1282 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
dere | +0.150 |
toget | +0.150 |
ettings | +0.145 |
solicit | +0.145 |
outlaw | +0.143 |
Neg logit contributions | |
HDL | -0.138 |
glacier | -0.122 |
LDL | -0.109 |
nir | -0.107 |
uckles | -0.100 |
Token | I |
Token ID | 314 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
HDL | +0.379 |
glacier | +0.342 |
LDL | +0.309 |
nir | +0.303 |
Greenland | +0.290 |
Neg logit contributions | |
toget | -0.291 |
dere | -0.291 |
ettings | -0.285 |
solicit | -0.280 |
•• | -0.278 |
Token | know |
Token ID | 760 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
HDL | +0.026 |
glacier | +0.023 |
LDL | +0.021 |
nir | +0.021 |
Greenland | +0.020 |
Neg logit contributions | |
toget | -0.023 |
dere | -0.023 |
ettings | -0.023 |
solicit | -0.022 |
•• | -0.022 |
Token | sending |
Token ID | 7216 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
toget | +0.177 |
dere | +0.177 |
ettings | +0.172 |
solicit | +0.170 |
outlaw | +0.168 |
Neg logit contributions | |
HDL | -0.242 |
glacier | -0.219 |
LDL | -0.199 |
nir | -0.195 |
Greenland | -0.187 |
Token | these |
Token ID | 777 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
HDL | +0.015 |
glacier | +0.013 |
LDL | +0.012 |
nir | +0.012 |
Esk | +0.011 |
Neg logit contributions | |
dere | -0.013 |
toget | -0.013 |
ettings | -0.013 |
solicit | -0.013 |
•• | -0.013 |
Token | m |
Token ID | 285 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
toget | +0.194 |
dere | +0.194 |
ettings | +0.188 |
solicit | +0.185 |
•• | +0.184 |
Neg logit contributions | |
HDL | -0.256 |
glacier | -0.230 |
LDL | -0.210 |
nir | -0.205 |
Esk | -0.196 |
Token | ails |
Token ID | 1768 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
HDL | +0.244 |
glacier | +0.217 |
LDL | +0.194 |
nir | +0.192 |
uckles | +0.181 |
Neg logit contributions | |
toget | -0.238 |
dere | -0.238 |
ettings | -0.230 |
solicit | -0.230 |
outlaw | -0.227 |
Token | does |
Token ID | 857 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
toget | +1.383 |
dere | +1.380 |
ettings | +1.330 |
solicit | +1.326 |
outlaw | +1.308 |
Neg logit contributions | |
HDL | -1.739 |
glacier | -1.559 |
LDL | -1.415 |
nir | -1.396 |
Greenland | -1.324 |
Token | not |
Token ID | 407 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
dere | +0.168 |
toget | +0.168 |
ettings | +0.163 |
solicit | +0.162 |
outlaw | +0.160 |
Neg logit contributions | |
HDL | -0.161 |
glacier | -0.143 |
LDL | -0.127 |
nir | -0.125 |
Greenland | -0.117 |
Token | change |
Token ID | 1487 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
toget | +0.337 |
dere | +0.337 |
ettings | +0.328 |
•• | +0.322 |
solicit | +0.321 |
Neg logit contributions | |
HDL | -0.423 |
glacier | -0.382 |
LDL | -0.345 |
nir | -0.340 |
Greenland | -0.323 |
Token | that |
Token ID | 326 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
dere | +0.745 |
toget | +0.744 |
ettings | +0.721 |
solicit | +0.717 |
outlaw | +0.708 |
Neg logit contributions | |
HDL | -0.727 |
glacier | -0.645 |
LDL | -0.575 |
nir | -0.567 |
uckles | -0.533 |
Token | , |
Token ID | 11 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
toget | +0.163 |
dere | +0.163 |
ettings | +0.158 |
solicit | +0.157 |
outlaw | +0.154 |
Neg logit contributions | |
HDL | -0.194 |
glacier | -0.174 |
LDL | -0.157 |
nir | -0.155 |
Greenland | -0.147 |
Token | was |
Token ID | 373 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
dere | +0.708 |
toget | +0.707 |
ettings | +0.684 |
solicit | +0.679 |
outlaw | +0.670 |
Neg logit contributions | |
HDL | -0.864 |
glacier | -0.776 |
LDL | -0.701 |
nir | -0.691 |
Greenland | -0.656 |
Token | also |
Token ID | 635 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
dere | +0.094 |
toget | +0.094 |
ettings | +0.092 |
solicit | +0.091 |
outlaw | +0.090 |
Neg logit contributions | |
HDL | -0.104 |
glacier | -0.093 |
LDL | -0.083 |
nir | -0.082 |
Greenland | -0.078 |
Token | taken |
Token ID | 2077 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
toget | +0.033 |
dere | +0.033 |
ettings | +0.032 |
solicit | +0.032 |
•• | +0.032 |
Neg logit contributions | |
HDL | -0.035 |
glacier | -0.032 |
LDL | -0.028 |
nir | -0.028 |
Greenland | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
dere | +0.680 |
toget | +0.678 |
ettings | +0.657 |
solicit | +0.652 |
outlaw | +0.643 |
Neg logit contributions | |
HDL | -0.820 |
glacier | -0.737 |
LDL | -0.665 |
nir | -0.654 |
Greenland | -0.622 |
Token | another |
Token ID | 1194 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
toget | +0.201 |
dere | +0.199 |
ettings | +0.194 |
solicit | +0.191 |
•• | +0.190 |
Neg logit contributions | |
HDL | -0.242 |
glacier | -0.217 |
LDL | -0.196 |
nir | -0.192 |
Greenland | -0.184 |
Token | jurisdiction |
Token ID | 12934 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
toget | +0.026 |
dere | +0.026 |
ettings | +0.025 |
solicit | +0.025 |
•• | +0.025 |
Neg logit contributions | |
HDL | -0.036 |
glacier | -0.033 |
LDL | -0.030 |
nir | -0.029 |
Greenland | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
dere | +1.402 |
toget | +1.401 |
ettings | +1.350 |
solicit | +1.345 |
outlaw | +1.330 |
Neg logit contributions | |
HDL | -1.716 |
glacier | -1.538 |
LDL | -1.395 |
nir | -1.377 |
uckles | -1.304 |
Token | a |
Token ID | 257 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
toget | +0.184 |
dere | +0.179 |
ettings | +0.177 |
solicit | +0.173 |
WARN | +0.172 |
Neg logit contributions | |
HDL | -0.246 |
glacier | -0.221 |
LDL | -0.202 |
nir | -0.196 |
Greenland | -0.189 |
Token | traffic |
Token ID | 4979 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
toget | +0.052 |
dere | +0.051 |
ettings | +0.050 |
solicit | +0.049 |
outlaw | +0.048 |
Neg logit contributions | |
HDL | -0.081 |
glacier | -0.073 |
LDL | -0.067 |
nir | -0.065 |
Greenland | -0.063 |
Token | offense |
Token ID | 6907 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
HDL | +1.187 |
glacier | +1.073 |
LDL | +0.986 |
nir | +0.961 |
Greenland | +0.926 |
Neg logit contributions | |
toget | -0.771 |
dere | -0.748 |
ettings | -0.742 |
solicit | -0.717 |
•• | -0.713 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
toget | +0.100 |
dere | +0.100 |
ettings | +0.097 |
solicit | +0.096 |
•• | +0.095 |
Neg logit contributions | |
HDL | -0.119 |
glacier | -0.107 |
LDL | -0.096 |
nir | -0.095 |
Greenland | -0.090 |
Token | 3 |
Token ID | 513 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
dere | +0.365 |
toget | +0.364 |
ettings | +0.352 |
solicit | +0.351 |
outlaw | +0.347 |
Neg logit contributions | |
HDL | -0.414 |
glacier | -0.370 |
LDL | -0.333 |
nir | -0.329 |
Greenland | -0.311 |
Token | : |
Token ID | 25 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
dere | +0.109 |
toget | +0.108 |
ettings | +0.105 |
solicit | +0.104 |
•• | +0.104 |
Neg logit contributions | |
HDL | -0.101 |
glacier | -0.090 |
LDL | -0.079 |
nir | -0.079 |
uckles | -0.074 |
Token | F |
Token ID | 376 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
HDL | +0.033 |
glacier | +0.029 |
LDL | +0.026 |
nir | +0.026 |
Greenland | +0.025 |
Neg logit contributions | |
toget | -0.029 |
dere | -0.029 |
ettings | -0.028 |
solicit | -0.028 |
outlaw | -0.028 |
Token | ocal |
Token ID | 4374 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
dere | +0.227 |
toget | +0.227 |
ettings | +0.220 |
solicit | +0.219 |
outlaw | +0.215 |
Neg logit contributions | |
HDL | -0.279 |
glacier | -0.251 |
LDL | -0.226 |
nir | -0.223 |
Greenland | -0.212 |
Token | ac |
Token ID | 936 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
dere | +0.339 |
toget | +0.338 |
ettings | +0.327 |
solicit | +0.325 |
outlaw | +0.321 |
Neg logit contributions | |
HDL | -0.394 |
glacier | -0.352 |
LDL | -0.318 |
nir | -0.313 |
Greenland | -0.297 |
Token | ral |
Token ID | 1373 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
dere | +0.517 |
toget | +0.517 |
ettings | +0.498 |
solicit | +0.494 |
•• | +0.487 |
Neg logit contributions | |
HDL | -0.751 |
glacier | -0.680 |
LDL | -0.620 |
nir | -0.611 |
Greenland | -0.583 |
Token | hyper |
Token ID | 8718 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
dere | +1.458 |
toget | +1.451 |
ettings | +1.399 |
solicit | +1.399 |
outlaw | +1.380 |
Neg logit contributions | |
HDL | -1.647 |
glacier | -1.465 |
LDL | -1.321 |
nir | -1.308 |
uckles | -1.233 |
Token | ker |
Token ID | 6122 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
dere | +0.703 |
toget | +0.702 |
ettings | +0.676 |
solicit | +0.672 |
outlaw | +0.662 |
Neg logit contributions | |
HDL | -0.990 |
glacier | -0.895 |
LDL | -0.815 |
nir | -0.803 |
Greenland | -0.766 |
Token | at |
Token ID | 265 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
HDL | +0.119 |
glacier | +0.108 |
LDL | +0.098 |
nir | +0.097 |
Greenland | +0.092 |
Neg logit contributions | |
dere | -0.086 |
toget | -0.086 |
ettings | -0.083 |
solicit | -0.083 |
outlaw | -0.081 |
Token | osis |
Token ID | 5958 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
dere | +0.242 |
toget | +0.241 |
ettings | +0.234 |
solicit | +0.232 |
outlaw | +0.229 |
Neg logit contributions | |
HDL | -0.303 |
glacier | -0.273 |
LDL | -0.246 |
nir | -0.243 |
Greenland | -0.231 |
Token | ( |
Token ID | 357 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
dere | +0.079 |
toget | +0.079 |
ettings | +0.076 |
solicit | +0.076 |
outlaw | +0.075 |
Neg logit contributions | |
HDL | -0.100 |
glacier | -0.090 |
LDL | -0.081 |
nir | -0.080 |
Greenland | -0.076 |
Token | � |
Token ID | 119 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
HDL | +0.172 |
glacier | +0.155 |
LDL | +0.142 |
nir | +0.140 |
Greenland | +0.134 |
Neg logit contributions | |
toget | -0.114 |
dere | -0.114 |
ettings | -0.110 |
solicit | -0.109 |
outlaw | -0.107 |
Token | o |
Token ID | 78 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
dere | +0.465 |
toget | +0.463 |
ettings | +0.448 |
solicit | +0.445 |
•• | +0.441 |
Neg logit contributions | |
HDL | -0.548 |
glacier | -0.491 |
LDL | -0.443 |
nir | -0.435 |
Greenland | -0.414 |
Token | Hal |
Token ID | 11023 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
HDL | +0.207 |
glacier | +0.185 |
LDL | +0.166 |
nir | +0.163 |
Greenland | +0.154 |
Neg logit contributions | |
dere | -0.191 |
toget | -0.191 |
ettings | -0.185 |
solicit | -0.184 |
outlaw | -0.182 |
Token | ep |
Token ID | 538 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
dere | +0.084 |
toget | +0.084 |
ettings | +0.080 |
solicit | +0.080 |
outlaw | +0.078 |
Neg logit contributions | |
HDL | -0.141 |
glacier | -0.129 |
LDL | -0.118 |
nir | -0.117 |
Greenland | -0.111 |
Token | ā |
Token ID | 10235 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
HDL | +0.163 |
glacier | +0.146 |
LDL | +0.131 |
nir | +0.129 |
Greenland | +0.123 |
Neg logit contributions | |
dere | -0.143 |
toget | -0.142 |
ettings | -0.138 |
solicit | -0.137 |
outlaw | -0.135 |
Token | nih |
Token ID | 37373 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
dere | +0.266 |
toget | +0.266 |
ettings | +0.257 |
solicit | +0.256 |
outlaw | +0.253 |
Neg logit contributions | |
HDL | -0.303 |
glacier | -0.271 |
LDL | -0.244 |
nir | -0.240 |
Greenland | -0.228 |
Token | o |
Token ID | 78 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
HDL | +2.044 |
glacier | +1.846 |
LDL | +1.667 |
nir | +1.657 |
uckles | +1.577 |
Neg logit contributions | |
toget | -1.692 |
dere | -1.671 |
ettings | -1.631 |
solicit | -1.606 |
WARN | -1.595 |
Token | m |
Token ID | 285 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
HDL | +0.159 |
glacier | +0.143 |
LDL | +0.129 |
nir | +0.127 |
Greenland | +0.120 |
Neg logit contributions | |
toget | -0.133 |
dere | -0.133 |
ettings | -0.128 |
solicit | -0.127 |
outlaw | -0.126 |
Token | ai |
Token ID | 1872 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
HDL | +0.271 |
glacier | +0.243 |
LDL | +0.219 |
nir | +0.216 |
uckles | +0.205 |
Neg logit contributions | |
toget | -0.231 |
dere | -0.230 |
ettings | -0.223 |
solicit | -0.221 |
outlaw | -0.218 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
dere | +0.653 |
toget | +0.648 |
solicit | +0.625 |
ettings | +0.624 |
outlaw | +0.617 |
Neg logit contributions | |
HDL | -0.735 |
glacier | -0.657 |
LDL | -0.590 |
nir | -0.582 |
Greenland | -0.550 |
Token | n |
Token ID | 299 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
dere | +0.073 |
toget | +0.073 |
ettings | +0.071 |
solicit | +0.070 |
outlaw | +0.070 |
Neg logit contributions | |
HDL | -0.079 |
glacier | -0.070 |
LDL | -0.063 |
nir | -0.062 |
Greenland | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
dere | +0.073 |
toget | +0.073 |
ettings | +0.070 |
solicit | +0.070 |
outlaw | +0.069 |
Neg logit contributions | |
HDL | -0.095 |
glacier | -0.085 |
LDL | -0.077 |
nir | -0.076 |
Greenland | -0.072 |
Token | David |
Token ID | 3271 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
toget | +0.108 |
dere | +0.108 |
ettings | +0.104 |
solicit | +0.103 |
•• | +0.102 |
Neg logit contributions | |
HDL | -0.128 |
glacier | -0.114 |
LDL | -0.103 |
nir | -0.102 |
Greenland | -0.097 |
Token | Brock |
Token ID | 20501 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
HDL | +0.271 |
glacier | +0.244 |
LDL | +0.223 |
nir | +0.219 |
Esk | +0.211 |
Neg logit contributions | |
toget | -0.184 |
dere | -0.183 |
ettings | -0.177 |
solicit | -0.174 |
outlaw | -0.172 |
Token | 's |
Token ID | 338 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
dere | +0.548 |
toget | +0.547 |
ettings | +0.531 |
solicit | +0.527 |
outlaw | +0.521 |
Neg logit contributions | |
HDL | -0.558 |
glacier | -0.496 |
LDL | -0.443 |
nir | -0.436 |
Greenland | -0.411 |
Token | Media |
Token ID | 6343 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
dere | +0.304 |
toget | +0.304 |
ettings | +0.295 |
solicit | +0.292 |
•• | +0.289 |
Neg logit contributions | |
HDL | -0.327 |
glacier | -0.291 |
LDL | -0.261 |
nir | -0.257 |
Greenland | -0.243 |
Token | Matters |
Token ID | 30587 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
HDL | +0.115 |
glacier | +0.106 |
LDL | +0.098 |
nir | +0.097 |
Greenland | +0.093 |
Neg logit contributions | |
dere | -0.054 |
toget | -0.053 |
ettings | -0.051 |
solicit | -0.050 |
•• | -0.049 |
Token | for |
Token ID | 329 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
HDL | +1.932 |
glacier | +1.749 |
LDL | +1.569 |
nir | +1.547 |
Greenland | +1.490 |
Neg logit contributions | |
dere | -1.472 |
toget | -1.468 |
ettings | -1.425 |
•• | -1.401 |
solicit | -1.393 |
Token | America |
Token ID | 2253 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
dere | +0.161 |
toget | +0.156 |
solicit | +0.154 |
outlaw | +0.154 |
•• | +0.153 |
Neg logit contributions | |
HDL | -0.168 |
glacier | -0.150 |
LDL | -0.135 |
nir | -0.132 |
� | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
HDL | +0.369 |
glacier | +0.331 |
LDL | +0.297 |
nir | +0.293 |
Greenland | +0.278 |
Neg logit contributions | |
dere | -0.321 |
toget | -0.321 |
ettings | -0.311 |
solicit | -0.307 |
•• | -0.304 |
Token |
|
Token ID | 198 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
dere | +0.126 |
toget | +0.126 |
ettings | +0.122 |
solicit | +0.122 |
outlaw | +0.120 |
Neg logit contributions | |
HDL | -0.149 |
glacier | -0.133 |
LDL | -0.120 |
nir | -0.118 |
Greenland | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
toget | +0.061 |
dere | +0.061 |
ettings | +0.059 |
solicit | +0.058 |
outlaw | +0.058 |
Neg logit contributions | |
HDL | -0.069 |
glacier | -0.061 |
LDL | -0.055 |
nir | -0.054 |
Greenland | -0.051 |
Token | was |
Token ID | 373 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
HDL | +0.161 |
glacier | +0.144 |
LDL | +0.128 |
nir | +0.126 |
Greenland | +0.120 |
Neg logit contributions | |
toget | -0.157 |
dere | -0.156 |
ettings | -0.152 |
solicit | -0.150 |
•• | -0.149 |
Token | involved |
Token ID | 2950 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
HDL | +0.041 |
glacier | +0.037 |
LDL | +0.033 |
nir | +0.033 |
Greenland | +0.031 |
Neg logit contributions | |
dere | -0.036 |
toget | -0.036 |
ettings | -0.035 |
solicit | -0.035 |
outlaw | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
dere | +0.199 |
toget | +0.199 |
ettings | +0.192 |
solicit | +0.191 |
outlaw | +0.188 |
Neg logit contributions | |
HDL | -0.246 |
glacier | -0.221 |
LDL | -0.200 |
nir | -0.197 |
Greenland | -0.187 |
Token | everything |
Token ID | 2279 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
HDL | +0.283 |
glacier | +0.254 |
LDL | +0.229 |
nir | +0.225 |
Greenland | +0.215 |
Neg logit contributions | |
toget | -0.239 |
dere | -0.238 |
ettings | -0.230 |
solicit | -0.229 |
•• | -0.226 |
Token | – |
Token ID | 784 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
dere | +0.364 |
toget | +0.364 |
ettings | +0.352 |
solicit | +0.349 |
outlaw | +0.345 |
Neg logit contributions | |
HDL | -0.447 |
glacier | -0.401 |
LDL | -0.363 |
nir | -0.358 |
Greenland | -0.340 |
Token | drib |
Token ID | 35003 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
HDL | +0.001 |
glacier | +0.001 |
LDL | +0.001 |
nir | +0.001 |
Greenland | +0.001 |
Neg logit contributions | |
dere | -0.001 |
toget | -0.001 |
ettings | -0.001 |
solicit | -0.001 |
•• | -0.001 |
Token | bling |
Token ID | 11108 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
HDL | +1.893 |
glacier | +1.711 |
LDL | +1.569 |
nir | +1.540 |
uckles | +1.484 |
Neg logit contributions | |
toget | -1.306 |
dere | -1.301 |
solicit | -1.243 |
ettings | -1.243 |
outlaw | -1.236 |
Token | with |
Token ID | 351 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
dere | +0.147 |
toget | +0.147 |
ettings | +0.142 |
solicit | +0.141 |
outlaw | +0.139 |
Neg logit contributions | |
HDL | -0.192 |
glacier | -0.173 |
LDL | -0.157 |
nir | -0.154 |
Greenland | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
toget | +0.034 |
dere | +0.034 |
ettings | +0.033 |
solicit | +0.032 |
•• | +0.032 |
Neg logit contributions | |
HDL | -0.040 |
glacier | -0.035 |
LDL | -0.032 |
nir | -0.031 |
Greenland | -0.030 |
Token | ball |
Token ID | 2613 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
HDL | +0.078 |
glacier | +0.069 |
LDL | +0.062 |
nir | +0.061 |
Greenland | +0.057 |
Neg logit contributions | |
dere | -0.077 |
toget | -0.077 |
ettings | -0.075 |
solicit | -0.074 |
outlaw | -0.074 |
Token | at |
Token ID | 379 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
HDL | +0.708 |
glacier | +0.636 |
LDL | +0.574 |
nir | +0.565 |
Greenland | +0.538 |
Neg logit contributions | |
dere | -0.565 |
toget | -0.563 |
ettings | -0.551 |
solicit | -0.539 |
WARN | -0.538 |
Token | in |
Token ID | 287 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
HDL | +0.835 |
glacier | +0.752 |
LDL | +0.673 |
nir | +0.661 |
Greenland | +0.635 |
Neg logit contributions | |
dere | -0.720 |
toget | -0.715 |
ettings | -0.703 |
solicit | -0.688 |
WARN | -0.684 |
Token | DC |
Token ID | 6257 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
toget | +0.003 |
dere | +0.003 |
ettings | +0.003 |
solicit | +0.003 |
•• | +0.003 |
Neg logit contributions | |
HDL | -0.005 |
glacier | -0.005 |
LDL | -0.004 |
nir | -0.004 |
Greenland | -0.004 |
Token | Entertainment |
Token ID | 11058 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
HDL | +1.027 |
glacier | +0.944 |
LDL | +0.873 |
nir | +0.863 |
Greenland | +0.835 |
Neg logit contributions | |
toget | -0.448 |
dere | -0.443 |
ettings | -0.420 |
solicit | -0.412 |
WARN | -0.406 |
Token | 's |
Token ID | 338 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
HDL | +0.877 |
glacier | +0.789 |
LDL | +0.711 |
nir | +0.698 |
Greenland | +0.668 |
Neg logit contributions | |
toget | -0.721 |
dere | -0.718 |
ettings | -0.697 |
solicit | -0.690 |
WARN | -0.681 |
Token | comic |
Token ID | 9048 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
HDL | +0.325 |
glacier | +0.295 |
LDL | +0.269 |
nir | +0.263 |
Greenland | +0.254 |
Neg logit contributions | |
toget | -0.217 |
dere | -0.212 |
ettings | -0.209 |
•• | -0.202 |
solicit | -0.201 |
Token | book |
Token ID | 1492 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
HDL | +0.892 |
glacier | +0.801 |
LDL | +0.725 |
nir | +0.710 |
Greenland | +0.680 |
Neg logit contributions | |
toget | -0.715 |
dere | -0.708 |
ettings | -0.691 |
solicit | -0.678 |
•• | -0.677 |
Token | mythology |
Token ID | 25871 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
HDL | +1.598 |
glacier | +1.422 |
LDL | +1.272 |
nir | +1.227 |
Greenland | +1.183 |
Neg logit contributions | |
toget | -1.536 |
dere | -1.505 |
ettings | -1.498 |
•• | -1.457 |
WARN | -1.445 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
HDL | +0.294 |
glacier | +0.264 |
LDL | +0.239 |
nir | +0.235 |
uckles | +0.223 |
Neg logit contributions | |
dere | -0.241 |
toget | -0.241 |
ettings | -0.232 |
solicit | -0.232 |
outlaw | -0.229 |
Token | Part |
Token ID | 2142 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
HDL | +0.189 |
glacier | +0.167 |
LDL | +0.153 |
nir | +0.149 |
Greenland | +0.143 |
Neg logit contributions | |
toget | -0.165 |
dere | -0.162 |
ettings | -0.158 |
solicit | -0.156 |
outlaw | -0.154 |
Token | of |
Token ID | 286 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
toget | +0.091 |
dere | +0.090 |
ettings | +0.087 |
solicit | +0.086 |
•• | +0.085 |
Neg logit contributions | |
HDL | -0.127 |
glacier | -0.115 |
LDL | -0.104 |
nir | -0.103 |
Esk | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
toget | +0.076 |
dere | +0.076 |
ettings | +0.073 |
solicit | +0.072 |
•• | +0.072 |
Neg logit contributions | |
HDL | -0.100 |
glacier | -0.090 |
LDL | -0.082 |
nir | -0.080 |
Greenland | -0.077 |
Token | which |
Token ID | 543 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
HDL | +0.155 |
glacier | +0.138 |
LDL | +0.125 |
nir | +0.122 |
Greenland | +0.116 |
Neg logit contributions | |
dere | -0.141 |
toget | -0.141 |
ettings | -0.137 |
solicit | -0.135 |
•• | -0.134 |
Token | increases |
Token ID | 5732 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
HDL | +0.167 |
glacier | +0.150 |
LDL | +0.136 |
nir | +0.133 |
Greenland | +0.128 |
Neg logit contributions | |
toget | -0.129 |
dere | -0.128 |
ettings | -0.125 |
solicit | -0.123 |
•• | -0.122 |
Token | levels |
Token ID | 2974 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
dere | +0.152 |
toget | +0.151 |
ettings | +0.146 |
solicit | +0.146 |
outlaw | +0.144 |
Neg logit contributions | |
HDL | -0.151 |
glacier | -0.135 |
LDL | -0.120 |
nir | -0.119 |
uckles | -0.112 |
Token | of |
Token ID | 286 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
HDL | +0.011 |
glacier | +0.010 |
LDL | +0.009 |
nir | +0.009 |
Greenland | +0.009 |
Neg logit contributions | |
toget | -0.008 |
dere | -0.008 |
ettings | -0.007 |
solicit | -0.007 |
outlaw | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
dere | +0.019 |
toget | +0.019 |
ettings | +0.018 |
solicit | +0.018 |
outlaw | +0.018 |
Neg logit contributions | |
HDL | -0.020 |
glacier | -0.017 |
LDL | -0.016 |
nir | -0.015 |
Greenland | -0.014 |
Token | neurotrans |
Token ID | 39307 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
HDL | +0.014 |
glacier | +0.012 |
LDL | +0.011 |
nir | +0.011 |
Greenland | +0.010 |
Neg logit contributions | |
toget | -0.014 |
dere | -0.014 |
ettings | -0.013 |
solicit | -0.013 |
•• | -0.013 |
Token | mitter |
Token ID | 37974 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
HDL | +1.210 |
glacier | +1.033 |
LDL | +0.892 |
nir | +0.867 |
Greenland | +0.799 |
Neg logit contributions | |
toget | -1.911 |
dere | -1.907 |
ettings | -1.856 |
solicit | -1.846 |
outlaw | -1.832 |
Token | acet |
Token ID | 25174 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
dere | +0.253 |
toget | +0.253 |
ettings | +0.246 |
solicit | +0.245 |
outlaw | +0.242 |
Neg logit contributions | |
HDL | -0.189 |
glacier | -0.164 |
LDL | -0.144 |
nir | -0.141 |
Greenland | -0.131 |
Token | yl |
Token ID | 2645 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
dere | +0.033 |
toget | +0.033 |
ettings | +0.030 |
solicit | +0.030 |
outlaw | +0.029 |
Neg logit contributions | |
HDL | -0.126 |
glacier | -0.117 |
LDL | -0.110 |
nir | -0.109 |
Greenland | -0.105 |
Token | ch |
Token ID | 354 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
dere | +0.332 |
toget | +0.329 |
solicit | +0.318 |
ettings | +0.316 |
•• | +0.313 |
Neg logit contributions | |
HDL | -0.443 |
glacier | -0.399 |
LDL | -0.362 |
nir | -0.360 |
Greenland | -0.340 |
Token | oline |
Token ID | 14453 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
dere | +0.368 |
toget | +0.364 |
ettings | +0.359 |
solicit | +0.358 |
•• | +0.354 |
Neg logit contributions | |
HDL | -0.315 |
glacier | -0.277 |
LDL | -0.244 |
nir | -0.239 |
Greenland | -0.224 |
Token | enemy |
Token ID | 4472 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
HDL | +0.422 |
glacier | +0.382 |
LDL | +0.345 |
nir | +0.340 |
Greenland | +0.324 |
Neg logit contributions | |
toget | -0.327 |
dere | -0.325 |
ettings | -0.318 |
solicit | -0.313 |
•• | -0.310 |
Token | minion |
Token ID | 28365 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
HDL | +0.486 |
glacier | +0.437 |
LDL | +0.392 |
nir | +0.386 |
Greenland | +0.366 |
Neg logit contributions | |
toget | -0.429 |
dere | -0.428 |
ettings | -0.416 |
solicit | -0.412 |
•• | -0.408 |
Token | and |
Token ID | 290 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
HDL | +0.128 |
glacier | +0.115 |
LDL | +0.103 |
nir | +0.102 |
Greenland | +0.097 |
Neg logit contributions | |
toget | -0.107 |
dere | -0.107 |
ettings | -0.104 |
solicit | -0.103 |
•• | -0.102 |
Token | it |
Token ID | 340 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
HDL | +0.162 |
glacier | +0.145 |
LDL | +0.129 |
nir | +0.127 |
Greenland | +0.121 |
Neg logit contributions | |
toget | -0.153 |
dere | -0.153 |
ettings | -0.149 |
solicit | -0.147 |
•• | -0.146 |
Token | was |
Token ID | 373 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
HDL | +0.183 |
glacier | +0.165 |
LDL | +0.146 |
nir | +0.145 |
Greenland | +0.136 |
Neg logit contributions | |
toget | -0.180 |
dere | -0.179 |
ettings | -0.175 |
solicit | -0.173 |
•• | -0.172 |
Token | Ragnar |
Token ID | 32797 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
HDL | +0.135 |
glacier | +0.121 |
LDL | +0.108 |
nir | +0.107 |
Greenland | +0.101 |
Neg logit contributions | |
toget | -0.122 |
dere | -0.122 |
ettings | -0.119 |
solicit | -0.118 |
•• | -0.116 |
Token | os |
Token ID | 418 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
HDL | +1.855 |
glacier | +1.689 |
LDL | +1.540 |
nir | +1.522 |
Greenland | +1.454 |
Neg logit contributions | |
toget | -1.216 |
dere | -1.215 |
ettings | -1.174 |
solicit | -1.159 |
•• | -1.145 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
HDL | +0.642 |
glacier | +0.578 |
LDL | +0.518 |
nir | +0.514 |
Greenland | +0.485 |
Neg logit contributions | |
toget | -0.557 |
dere | -0.557 |
ettings | -0.541 |
solicit | -0.537 |
•• | -0.529 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
dere | +0.008 |
toget | +0.008 |
ettings | +0.008 |
solicit | +0.008 |
outlaw | +0.008 |
Neg logit contributions | |
HDL | -0.010 |
glacier | -0.009 |
LDL | -0.008 |
nir | -0.008 |
uckles | -0.007 |
Token | super |
Token ID | 2208 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
HDL | +0.100 |
glacier | +0.089 |
LDL | +0.080 |
nir | +0.079 |
Greenland | +0.075 |
Neg logit contributions | |
toget | -0.085 |
dere | -0.085 |
ettings | -0.083 |
solicit | -0.082 |
•• | -0.081 |
Token | - |
Token ID | 12 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
HDL | +0.758 |
glacier | +0.684 |
LDL | +0.618 |
nir | +0.612 |
Greenland | +0.581 |
Neg logit contributions | |
toget | -0.591 |
dere | -0.590 |
ettings | -0.572 |
solicit | -0.567 |
•• | -0.560 |
Token | to |
Token ID | 284 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
HDL | +0.257 |
glacier | +0.230 |
LDL | +0.206 |
nir | +0.203 |
Greenland | +0.192 |
Neg logit contributions | |
dere | -0.232 |
toget | -0.231 |
ettings | -0.225 |
solicit | -0.223 |
•• | -0.220 |
Token | not |
Token ID | 407 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
HDL | +0.424 |
glacier | +0.382 |
LDL | +0.345 |
nir | +0.341 |
Greenland | +0.323 |
Neg logit contributions | |
dere | -0.325 |
toget | -0.322 |
ettings | -0.316 |
solicit | -0.307 |
•• | -0.307 |
Token | make |
Token ID | 787 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
HDL | +0.359 |
glacier | +0.323 |
LDL | +0.294 |
nir | +0.289 |
uckles | +0.275 |
Neg logit contributions | |
dere | -0.269 |
toget | -0.268 |
ettings | -0.262 |
•• | -0.256 |
solicit | -0.254 |
Token | it |
Token ID | 340 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
HDL | +0.558 |
glacier | +0.497 |
LDL | +0.445 |
nir | +0.436 |
Greenland | +0.415 |
Neg logit contributions | |
dere | -0.529 |
toget | -0.528 |
ettings | -0.513 |
solicit | -0.507 |
•• | -0.504 |
Token | too |
Token ID | 1165 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
HDL | +0.358 |
glacier | +0.321 |
LDL | +0.289 |
nir | +0.283 |
Greenland | +0.269 |
Neg logit contributions | |
dere | -0.310 |
toget | -0.308 |
ettings | -0.303 |
solicit | -0.297 |
•• | -0.296 |
Token | tight |
Token ID | 5381 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
HDL | +0.384 |
glacier | +0.351 |
LDL | +0.320 |
nir | +0.314 |
Esk | +0.303 |
Neg logit contributions | |
dere | -0.230 |
toget | -0.229 |
ettings | -0.224 |
•• | -0.217 |
solicit | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
HDL | +1.568 |
glacier | +1.399 |
LDL | +1.253 |
nir | +1.237 |
� | +1.168 |
Neg logit contributions | |
dere | -1.440 |
toget | -1.410 |
ettings | -1.404 |
solicit | -1.375 |
WARN | -1.369 |
Token | Leave |
Token ID | 17446 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
HDL | +0.354 |
glacier | +0.313 |
LDL | +0.287 |
nir | +0.278 |
Greenland | +0.269 |
Neg logit contributions | |
toget | -0.291 |
dere | -0.289 |
ettings | -0.280 |
solicit | -0.275 |
outlaw | -0.272 |
Token | it |
Token ID | 340 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
HDL | +0.537 |
glacier | +0.477 |
LDL | +0.429 |
nir | +0.419 |
uckles | +0.398 |
Neg logit contributions | |
dere | -0.502 |
toget | -0.502 |
ettings | -0.489 |
solicit | -0.483 |
•• | -0.479 |
Token | with |
Token ID | 351 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
HDL | +0.406 |
glacier | +0.365 |
LDL | +0.331 |
nir | +0.323 |
Greenland | +0.309 |
Neg logit contributions | |
dere | -0.318 |
toget | -0.316 |
ettings | -0.312 |
solicit | -0.306 |
•• | -0.305 |
Token | a |
Token ID | 257 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
HDL | +0.310 |
glacier | +0.276 |
LDL | +0.247 |
nir | +0.242 |
Greenland | +0.229 |
Neg logit contributions | |
dere | -0.301 |
toget | -0.300 |
ettings | -0.292 |
solicit | -0.289 |
•• | -0.286 |
Token | � |
Token ID | 251 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
HDL | +0.450 |
glacier | +0.397 |
LDL | +0.352 |
nir | +0.346 |
Greenland | +0.325 |
Neg logit contributions | |
toget | -0.495 |
dere | -0.495 |
ettings | -0.481 |
solicit | -0.477 |
outlaw | -0.472 |
Token |
|
Token ID | 198 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
HDL | +0.203 |
glacier | +0.183 |
LDL | +0.165 |
nir | +0.163 |
Greenland | +0.154 |
Neg logit contributions | |
dere | -0.166 |
toget | -0.165 |
ettings | -0.160 |
solicit | -0.159 |
outlaw | -0.157 |
Token |
|
Token ID | 198 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
HDL | +0.338 |
glacier | +0.304 |
LDL | +0.273 |
nir | +0.270 |
Greenland | +0.255 |
Neg logit contributions | |
dere | -0.284 |
toget | -0.283 |
ettings | -0.275 |
solicit | -0.273 |
•• | -0.271 |
Token | Facebook |
Token ID | 12025 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
HDL | +0.388 |
glacier | +0.349 |
LDL | +0.316 |
nir | +0.312 |
Greenland | +0.296 |
Neg logit contributions | |
dere | -0.300 |
toget | -0.300 |
ettings | -0.289 |
solicit | -0.287 |
outlaw | -0.283 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
HDL | +0.648 |
glacier | +0.573 |
LDL | +0.510 |
nir | +0.502 |
Greenland | +0.472 |
Neg logit contributions | |
dere | -0.678 |
toget | -0.678 |
ettings | -0.658 |
solicit | -0.653 |
outlaw | -0.646 |
Token | Pinterest |
Token ID | 17334 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
HDL | +0.322 |
glacier | +0.285 |
LDL | +0.253 |
nir | +0.246 |
Greenland | +0.235 |
Neg logit contributions | |
toget | -0.347 |
dere | -0.344 |
ettings | -0.335 |
solicit | -0.333 |
outlaw | -0.330 |
Token | Liverpool |
Token ID | 11761 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
HDL | +1.589 |
glacier | +1.408 |
LDL | +1.281 |
nir | +1.247 |
Esk | +1.204 |
Neg logit contributions | |
toget | -1.430 |
dere | -1.417 |
ettings | -1.375 |
solicit | -1.365 |
outlaw | -1.350 |
Token | � |
Token ID | 447 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
HDL | +0.199 |
glacier | +0.179 |
LDL | +0.162 |
nir | +0.160 |
Greenland | +0.152 |
Neg logit contributions | |
dere | -0.157 |
toget | -0.157 |
ettings | -0.151 |
solicit | -0.150 |
outlaw | -0.148 |
Token | � |
Token ID | 247 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
HDL | +0.067 |
glacier | +0.060 |
LDL | +0.054 |
nir | +0.053 |
Greenland | +0.050 |
Neg logit contributions | |
toget | -0.059 |
dere | -0.059 |
ettings | -0.057 |
solicit | -0.056 |
outlaw | -0.056 |
Token | s |
Token ID | 82 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
HDL | +0.188 |
glacier | +0.168 |
LDL | +0.152 |
nir | +0.149 |
Greenland | +0.142 |
Neg logit contributions | |
toget | -0.162 |
dere | -0.162 |
ettings | -0.156 |
solicit | -0.156 |
outlaw | -0.153 |
Token | Adam |
Token ID | 7244 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
HDL | +0.141 |
glacier | +0.126 |
LDL | +0.114 |
nir | +0.112 |
Greenland | +0.106 |
Neg logit contributions | |
toget | -0.119 |
dere | -0.119 |
ettings | -0.116 |
solicit | -0.115 |
•• | -0.113 |
Token | ). |
Token ID | 737 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
dere | +0.152 |
toget | +0.152 |
ettings | +0.147 |
solicit | +0.146 |
•• | +0.145 |
Neg logit contributions | |
HDL | -0.172 |
glacier | -0.154 |
LDL | -0.138 |
nir | -0.136 |
uckles | -0.129 |
Token |
|
Token ID | 198 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
dere | +0.048 |
toget | +0.048 |
ettings | +0.047 |
solicit | +0.047 |
•• | +0.046 |
Neg logit contributions | |
HDL | -0.056 |
glacier | -0.051 |
LDL | -0.046 |
nir | -0.045 |
uckles | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
HDL | +0.187 |
glacier | +0.167 |
LDL | +0.151 |
nir | +0.148 |
Greenland | +0.140 |
Neg logit contributions | |
toget | -0.172 |
dere | -0.169 |
ettings | -0.165 |
solicit | -0.163 |
outlaw | -0.161 |
Token | Facebook |
Token ID | 12025 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
HDL | +0.184 |
glacier | +0.165 |
LDL | +0.149 |
nir | +0.147 |
Greenland | +0.139 |
Neg logit contributions | |
dere | -0.149 |
toget | -0.149 |
ettings | -0.144 |
solicit | -0.143 |
•• | -0.142 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
HDL | +0.495 |
glacier | +0.437 |
LDL | +0.386 |
nir | +0.372 |
Greenland | +0.357 |
Neg logit contributions | |
toget | -0.593 |
dere | -0.577 |
ettings | -0.567 |
solicit | -0.554 |
outlaw | -0.552 |
Token | Pinterest |
Token ID | 17334 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
HDL | +0.150 |
glacier | +0.125 |
LDL | +0.104 |
nir | +0.101 |
Greenland | +0.091 |
Neg logit contributions | |
dere | -0.294 |
toget | -0.294 |
ettings | -0.287 |
solicit | -0.286 |
outlaw | -0.283 |
Token | Lake |
Token ID | 6233 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
HDL | +1.573 |
glacier | +1.415 |
LDL | +1.267 |
nir | +1.236 |
Greenland | +1.199 |
Neg logit contributions | |
toget | -1.441 |
dere | -1.413 |
ettings | -1.388 |
solicit | -1.374 |
outlaw | -1.354 |
Token | Ur |
Token ID | 8799 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
HDL | +0.435 |
glacier | +0.386 |
LDL | +0.346 |
nir | +0.340 |
uckles | +0.320 |
Neg logit contributions | |
dere | -0.427 |
toget | -0.426 |
ettings | -0.413 |
solicit | -0.411 |
outlaw | -0.406 |
Token | mia |
Token ID | 20730 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
HDL | +0.243 |
glacier | +0.215 |
LDL | +0.192 |
nir | +0.189 |
Greenland | +0.178 |
Neg logit contributions | |
toget | -0.250 |
dere | -0.249 |
ettings | -0.241 |
solicit | -0.240 |
outlaw | -0.237 |
Token | Photograph |
Token ID | 18903 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
HDL | +0.179 |
glacier | +0.161 |
LDL | +0.147 |
nir | +0.145 |
uckles | +0.137 |
Neg logit contributions | |
dere | -0.135 |
toget | -0.134 |
ettings | -0.130 |
solicit | -0.129 |
outlaw | -0.127 |
Token | : |
Token ID | 25 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
HDL | +0.697 |
glacier | +0.614 |
LDL | +0.540 |
nir | +0.525 |
Greenland | +0.496 |
Neg logit contributions | |
toget | -0.846 |
dere | -0.836 |
ettings | -0.817 |
solicit | -0.808 |
outlaw | -0.802 |
Token | , |
Token ID | 11 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
dere | +0.336 |
toget | +0.335 |
ettings | +0.324 |
solicit | +0.322 |
outlaw | +0.317 |
Neg logit contributions | |
HDL | -0.424 |
glacier | -0.381 |
LDL | -0.345 |
nir | -0.340 |
Greenland | -0.323 |
Token | born |
Token ID | 4642 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
dere | +0.035 |
toget | +0.035 |
ettings | +0.034 |
solicit | +0.034 |
outlaw | +0.033 |
Neg logit contributions | |
HDL | -0.045 |
glacier | -0.041 |
LDL | -0.037 |
nir | -0.036 |
Greenland | -0.034 |
Token | at |
Token ID | 379 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
dere | +0.618 |
toget | +0.617 |
ettings | +0.596 |
solicit | +0.592 |
outlaw | +0.583 |
Neg logit contributions | |
HDL | -0.816 |
glacier | -0.735 |
LDL | -0.667 |
nir | -0.658 |
Greenland | -0.626 |
Token | Gu |
Token ID | 1962 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
toget | +0.218 |
dere | +0.218 |
ettings | +0.211 |
solicit | +0.209 |
outlaw | +0.206 |
Neg logit contributions | |
HDL | -0.264 |
glacier | -0.236 |
LDL | -0.214 |
nir | -0.210 |
Greenland | -0.200 |
Token | adal |
Token ID | 31682 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
toget | +0.139 |
dere | +0.139 |
ettings | +0.134 |
solicit | +0.133 |
outlaw | +0.131 |
Neg logit contributions | |
HDL | -0.197 |
glacier | -0.179 |
LDL | -0.163 |
nir | -0.161 |
uckles | -0.153 |
Token | upe |
Token ID | 48722 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
HDL | +0.098 |
glacier | +0.088 |
LDL | +0.080 |
nir | +0.079 |
Greenland | +0.075 |
Neg logit contributions | |
dere | -0.073 |
toget | -0.073 |
ettings | -0.071 |
solicit | -0.070 |
outlaw | -0.069 |
Token | Valley |
Token ID | 6916 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
HDL | +1.671 |
glacier | +1.511 |
LDL | +1.364 |
nir | +1.331 |
Greenland | +1.290 |
Neg logit contributions | |
toget | -1.290 |
dere | -1.277 |
ettings | -1.254 |
solicit | -1.222 |
outlaw | -1.212 |
Token | Hospital |
Token ID | 9256 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
toget | +0.306 |
dere | +0.306 |
ettings | +0.296 |
solicit | +0.293 |
outlaw | +0.289 |
Neg logit contributions | |
HDL | -0.393 |
glacier | -0.354 |
LDL | -0.320 |
nir | -0.315 |
Greenland | -0.301 |
Token | on |
Token ID | 319 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
dere | +0.135 |
toget | +0.135 |
ettings | +0.130 |
solicit | +0.129 |
outlaw | +0.127 |
Neg logit contributions | |
HDL | -0.175 |
glacier | -0.157 |
LDL | -0.143 |
nir | -0.140 |
Greenland | -0.134 |
Token | July |
Token ID | 2901 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
toget | +0.020 |
dere | +0.020 |
ettings | +0.020 |
solicit | +0.019 |
outlaw | +0.019 |
Neg logit contributions | |
HDL | -0.027 |
glacier | -0.025 |
LDL | -0.022 |
nir | -0.022 |
Greenland | -0.021 |
Token | 23 |
Token ID | 2242 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
HDL | +0.475 |
glacier | +0.424 |
LDL | +0.383 |
nir | +0.376 |
Greenland | +0.358 |
Neg logit contributions | |
toget | -0.416 |
dere | -0.413 |
ettings | -0.402 |
solicit | -0.397 |
outlaw | -0.392 |
Token | one |
Token ID | 530 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
HDL | +0.265 |
glacier | +0.237 |
LDL | +0.216 |
nir | +0.210 |
Greenland | +0.202 |
Neg logit contributions | |
toget | -0.211 |
dere | -0.210 |
ettings | -0.206 |
solicit | -0.202 |
WARN | -0.199 |
Token | had |
Token ID | 550 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
HDL | +0.234 |
glacier | +0.209 |
LDL | +0.187 |
nir | +0.182 |
Greenland | +0.173 |
Neg logit contributions | |
toget | -0.232 |
dere | -0.231 |
ettings | -0.226 |
solicit | -0.223 |
•• | -0.220 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
HDL | +0.108 |
glacier | +0.096 |
LDL | +0.087 |
nir | +0.086 |
Greenland | +0.081 |
Neg logit contributions | |
dere | -0.095 |
toget | -0.095 |
ettings | -0.091 |
solicit | -0.091 |
outlaw | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
HDL | +0.935 |
glacier | +0.842 |
LDL | +0.757 |
nir | +0.743 |
Greenland | +0.712 |
Neg logit contributions | |
toget | -0.787 |
dere | -0.784 |
ettings | -0.766 |
solicit | -0.756 |
WARN | -0.746 |
Token | A |
Token ID | 317 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
HDL | +0.104 |
glacier | +0.092 |
LDL | +0.084 |
nir | +0.081 |
Esk | +0.078 |
Neg logit contributions | |
toget | -0.093 |
dere | -0.092 |
ettings | -0.090 |
solicit | -0.088 |
outlaw | -0.087 |
Token | Redd |
Token ID | 42734 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
HDL | +0.023 |
glacier | +0.021 |
LDL | +0.019 |
nir | +0.019 |
Greenland | +0.018 |
Neg logit contributions | |
toget | -0.019 |
dere | -0.019 |
ettings | -0.019 |
solicit | -0.018 |
outlaw | -0.018 |
Token | itor |
Token ID | 2072 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
HDL | +1.527 |
glacier | +1.369 |
LDL | +1.228 |
nir | +1.218 |
Greenland | +1.138 |
Neg logit contributions | |
toget | -1.428 |
dere | -1.423 |
ettings | -1.386 |
solicit | -1.368 |
WARN | -1.351 |
Token | posted |
Token ID | 4481 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
HDL | +0.829 |
glacier | +0.743 |
LDL | +0.668 |
nir | +0.656 |
Greenland | +0.625 |
Neg logit contributions | |
dere | -0.730 |
toget | -0.728 |
ettings | -0.717 |
solicit | -0.703 |
•• | -0.697 |
Token | what |
Token ID | 644 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
HDL | +0.288 |
glacier | +0.257 |
LDL | +0.232 |
nir | +0.227 |
Esk | +0.217 |
Neg logit contributions | |
toget | -0.255 |
dere | -0.255 |
ettings | -0.250 |
solicit | -0.245 |
•• | -0.242 |
Token | they |
Token ID | 484 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
HDL | +0.098 |
glacier | +0.088 |
LDL | +0.079 |
nir | +0.078 |
Greenland | +0.074 |
Neg logit contributions | |
dere | -0.086 |
toget | -0.086 |
ettings | -0.084 |
solicit | -0.083 |
outlaw | -0.082 |
Token | claimed |
Token ID | 4752 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
dere | +0.015 |
toget | +0.015 |
ettings | +0.015 |
solicit | +0.014 |
•• | +0.014 |
Neg logit contributions | |
HDL | -0.013 |
glacier | -0.011 |
LDL | -0.010 |
nir | -0.009 |
Greenland | -0.009 |
Token | prof |
Token ID | 1534 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
HDL | +0.320 |
glacier | +0.288 |
LDL | +0.259 |
nir | +0.252 |
Greenland | +0.243 |
Neg logit contributions | |
toget | -0.262 |
dere | -0.255 |
ettings | -0.252 |
•• | -0.244 |
solicit | -0.244 |
Token | use |
Token ID | 1904 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
HDL | +0.785 |
glacier | +0.707 |
nir | +0.636 |
LDL | +0.635 |
uckles | +0.606 |
Neg logit contributions | |
toget | -0.672 |
dere | -0.664 |
ettings | -0.637 |
outlaw | -0.636 |
solicit | -0.633 |
Token | apologies |
Token ID | 32920 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
dere | +0.859 |
toget | +0.856 |
ettings | +0.830 |
solicit | +0.826 |
outlaw | +0.815 |
Neg logit contributions | |
HDL | -0.964 |
glacier | -0.861 |
LDL | -0.775 |
nir | -0.765 |
Greenland | -0.722 |
Token | to |
Token ID | 284 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
dere | +0.337 |
toget | +0.336 |
ettings | +0.325 |
solicit | +0.323 |
outlaw | +0.318 |
Neg logit contributions | |
HDL | -0.431 |
glacier | -0.388 |
LDL | -0.351 |
nir | -0.346 |
Greenland | -0.329 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
HDL | +0.070 |
glacier | +0.062 |
LDL | +0.056 |
nir | +0.055 |
uckles | +0.052 |
Neg logit contributions | |
dere | -0.064 |
toget | -0.064 |
ettings | -0.062 |
solicit | -0.062 |
outlaw | -0.061 |
Token | Motion |
Token ID | 20843 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
HDL | +0.115 |
glacier | +0.103 |
LDL | +0.093 |
nir | +0.092 |
Greenland | +0.087 |
Neg logit contributions | |
toget | -0.095 |
dere | -0.094 |
ettings | -0.091 |
solicit | -0.090 |
•• | -0.089 |
Token | Picture |
Token ID | 17741 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
HDL | +1.659 |
glacier | +1.491 |
LDL | +1.352 |
nir | +1.337 |
Greenland | +1.270 |
Neg logit contributions | |
toget | -1.290 |
dere | -1.284 |
ettings | -1.260 |
solicit | -1.221 |
•• | -1.215 |
Token | Academy |
Token ID | 8581 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
dere | +0.124 |
toget | +0.124 |
ettings | +0.120 |
solicit | +0.119 |
outlaw | +0.118 |
Neg logit contributions | |
HDL | -0.148 |
glacier | -0.133 |
LDL | -0.120 |
nir | -0.119 |
uckles | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
HDL | +0.032 |
glacier | +0.029 |
LDL | +0.026 |
nir | +0.026 |
Esk | +0.025 |
Neg logit contributions | |
toget | -0.026 |
dere | -0.026 |
ettings | -0.025 |
solicit | -0.025 |
outlaw | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
HDL | +0.164 |
glacier | +0.147 |
LDL | +0.133 |
nir | +0.131 |
Esk | +0.125 |
Neg logit contributions | |
toget | -0.137 |
dere | -0.137 |
ettings | -0.133 |
solicit | -0.130 |
outlaw | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
HDL | +0.128 |
glacier | +0.115 |
LDL | +0.104 |
nir | +0.102 |
Greenland | +0.097 |
Neg logit contributions | |
toget | -0.111 |
dere | -0.110 |
ettings | -0.107 |
solicit | -0.106 |
•• | -0.105 |
Token | Bernie |
Token ID | 10477 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
toget | +0.095 |
dere | +0.095 |
ettings | +0.092 |
solicit | +0.091 |
•• | +0.090 |
Neg logit contributions | |
HDL | -0.114 |
glacier | -0.102 |
LDL | -0.092 |
nir | -0.091 |
Esk | -0.086 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
dere | +0.127 |
toget | +0.127 |
ettings | +0.123 |
solicit | +0.122 |
outlaw | +0.121 |
Neg logit contributions | |
HDL | -0.160 |
glacier | -0.144 |
LDL | -0.130 |
nir | -0.128 |
Greenland | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
dere | +0.227 |
toget | +0.227 |
ettings | +0.220 |
solicit | +0.218 |
outlaw | +0.215 |
Neg logit contributions | |
HDL | -0.261 |
glacier | -0.234 |
LDL | -0.211 |
nir | -0.208 |
Greenland | -0.197 |
Token | advocating |
Token ID | 24950 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
dere | +0.200 |
toget | +0.199 |
ettings | +0.194 |
solicit | +0.192 |
•• | +0.189 |
Neg logit contributions | |
HDL | -0.235 |
glacier | -0.211 |
LDL | -0.190 |
nir | -0.186 |
Greenland | -0.178 |
Token | for |
Token ID | 329 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
HDL | +0.043 |
glacier | +0.039 |
LDL | +0.035 |
nir | +0.035 |
Esk | +0.033 |
Neg logit contributions | |
dere | -0.033 |
toget | -0.033 |
ettings | -0.032 |
solicit | -0.031 |
•• | -0.031 |
Token | Medicare |
Token ID | 13771 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
HDL | +0.221 |
glacier | +0.198 |
LDL | +0.179 |
nir | +0.176 |
Greenland | +0.167 |
Neg logit contributions | |
toget | -0.184 |
dere | -0.184 |
ettings | -0.178 |
solicit | -0.177 |
•• | -0.175 |
Token | For |
Token ID | 1114 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
HDL | +1.689 |
glacier | +1.529 |
LDL | +1.392 |
nir | +1.364 |
Esk | +1.306 |
Neg logit contributions | |
dere | -1.243 |
toget | -1.233 |
ettings | -1.210 |
solicit | -1.186 |
•• | -1.163 |
Token | All |
Token ID | 1439 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
HDL | +0.179 |
glacier | +0.158 |
LDL | +0.138 |
nir | +0.136 |
uckles | +0.128 |
Neg logit contributions | |
dere | -0.210 |
toget | -0.208 |
ettings | -0.203 |
solicit | -0.203 |
•• | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
HDL | +0.516 |
glacier | +0.466 |
LDL | +0.422 |
nir | +0.416 |
Greenland | +0.396 |
Neg logit contributions | |
dere | -0.400 |
toget | -0.399 |
ettings | -0.387 |
solicit | -0.383 |
outlaw | -0.377 |
Token | free |
Token ID | 1479 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
dere | +0.063 |
toget | +0.063 |
ettings | +0.061 |
solicit | +0.060 |
•• | +0.060 |
Neg logit contributions | |
HDL | -0.074 |
glacier | -0.067 |
LDL | -0.060 |
nir | -0.059 |
Greenland | -0.056 |
Token | college |
Token ID | 4152 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
HDL | +0.588 |
glacier | +0.527 |
LDL | +0.476 |
nir | +0.466 |
Greenland | +0.444 |
Neg logit contributions | |
toget | -0.501 |
dere | -0.500 |
ettings | -0.486 |
solicit | -0.479 |
•• | -0.474 |
Token | were |
Token ID | 547 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
toget | +0.224 |
dere | +0.223 |
ettings | +0.219 |
•• | +0.215 |
solicit | +0.214 |
Neg logit contributions | |
HDL | -0.209 |
glacier | -0.187 |
LDL | -0.164 |
nir | -0.161 |
Greenland | -0.153 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
toget | +0.157 |
dere | +0.157 |
ettings | +0.153 |
solicit | +0.151 |
•• | +0.149 |
Neg logit contributions | |
HDL | -0.187 |
glacier | -0.168 |
LDL | -0.151 |
nir | -0.149 |
Greenland | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
HDL | +0.103 |
glacier | +0.092 |
LDL | +0.084 |
nir | +0.082 |
Greenland | +0.078 |
Neg logit contributions | |
toget | -0.088 |
dere | -0.087 |
ettings | -0.084 |
solicit | -0.083 |
outlaw | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
HDL | +0.082 |
glacier | +0.073 |
LDL | +0.066 |
nir | +0.064 |
Greenland | +0.061 |
Neg logit contributions | |
toget | -0.074 |
dere | -0.073 |
ettings | -0.071 |
solicit | -0.071 |
outlaw | -0.070 |
Token | SC |
Token ID | 6173 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
HDL | +0.125 |
glacier | +0.112 |
LDL | +0.101 |
nir | +0.100 |
Greenland | +0.094 |
Neg logit contributions | |
toget | -0.108 |
dere | -0.108 |
ettings | -0.105 |
solicit | -0.104 |
outlaw | -0.103 |
Token | OTT |
Token ID | 29089 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
dere | +0.087 |
toget | +0.087 |
ettings | +0.084 |
solicit | +0.084 |
outlaw | +0.083 |
Neg logit contributions | |
HDL | -0.101 |
glacier | -0.091 |
LDL | -0.082 |
nir | -0.081 |
uckles | -0.076 |
Token | MOR |
Token ID | 35208 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
HDL | +1.561 |
glacier | +1.384 |
LDL | +1.258 |
nir | +1.210 |
Greenland | +1.166 |
Neg logit contributions | |
toget | -1.391 |
dere | -1.389 |
ettings | -1.351 |
solicit | -1.332 |
outlaw | -1.312 |
Token | GAN |
Token ID | 45028 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
dere | +0.316 |
toget | +0.316 |
ettings | +0.307 |
solicit | +0.305 |
•• | +0.301 |
Neg logit contributions | |
HDL | -0.315 |
glacier | -0.280 |
LDL | -0.250 |
nir | -0.246 |
Greenland | -0.232 |
Token | / |
Token ID | 14 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
HDL | +0.412 |
glacier | +0.367 |
LDL | +0.330 |
nir | +0.323 |
Greenland | +0.307 |
Neg logit contributions | |
toget | -0.388 |
dere | -0.388 |
ettings | -0.376 |
solicit | -0.373 |
outlaw | -0.369 |
Token | RE |
Token ID | 2200 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
HDL | +0.282 |
glacier | +0.248 |
LDL | +0.220 |
nir | +0.216 |
Greenland | +0.204 |
Neg logit contributions | |
toget | -0.315 |
dere | -0.314 |
ettings | -0.306 |
solicit | -0.303 |
outlaw | -0.300 |
Token | UTERS |
Token ID | 14974 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
HDL | +0.343 |
glacier | +0.258 |
LDL | +0.198 |
nir | +0.176 |
Greenland | +0.163 |
Neg logit contributions | |
toget | -1.077 |
dere | -1.064 |
solicit | -1.040 |
ettings | -1.037 |
outlaw | -1.029 |
Token | Castle |
Token ID | 11312 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
HDL | +0.789 |
glacier | +0.695 |
LDL | +0.623 |
nir | +0.612 |
Greenland | +0.581 |
Neg logit contributions | |
toget | -0.803 |
dere | -0.792 |
ettings | -0.775 |
solicit | -0.766 |
WARN | -0.758 |
Token | , |
Token ID | 11 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
toget | +0.310 |
dere | +0.308 |
ettings | +0.299 |
solicit | +0.295 |
outlaw | +0.290 |
Neg logit contributions | |
HDL | -0.415 |
glacier | -0.374 |
LDL | -0.340 |
nir | -0.334 |
Greenland | -0.320 |
Token | some |
Token ID | 617 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
HDL | +0.022 |
glacier | +0.020 |
LDL | +0.018 |
nir | +0.018 |
Greenland | +0.017 |
Neg logit contributions | |
toget | -0.018 |
dere | -0.018 |
ettings | -0.018 |
solicit | -0.017 |
•• | -0.017 |
Token | see |
Token ID | 766 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
HDL | +0.549 |
glacier | +0.491 |
LDL | +0.442 |
nir | +0.429 |
Esk | +0.413 |
Neg logit contributions | |
toget | -0.496 |
dere | -0.488 |
ettings | -0.483 |
•• | -0.471 |
solicit | -0.469 |
Token | " |
Token ID | 366 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
toget | +0.028 |
dere | +0.027 |
ettings | +0.027 |
solicit | +0.026 |
•• | +0.026 |
Neg logit contributions | |
HDL | -0.035 |
glacier | -0.032 |
LDL | -0.029 |
nir | -0.028 |
Greenland | -0.027 |
Token | Pokémon |
Token ID | 46602 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
HDL | +0.023 |
glacier | +0.020 |
LDL | +0.018 |
nir | +0.018 |
uckles | +0.017 |
Neg logit contributions | |
toget | -0.017 |
dere | -0.017 |
ettings | -0.017 |
solicit | -0.017 |
outlaw | -0.016 |
Token | people |
Token ID | 661 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
HDL | +1.367 |
glacier | +1.209 |
LDL | +1.065 |
nir | +1.038 |
Greenland | +0.993 |
Neg logit contributions | |
toget | -1.551 |
dere | -1.538 |
ettings | -1.517 |
solicit | -1.493 |
•• | -1.488 |
Token | " |
Token ID | 1 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
dere | +0.442 |
toget | +0.442 |
ettings | +0.428 |
solicit | +0.426 |
outlaw | +0.421 |
Neg logit contributions | |
HDL | -0.449 |
glacier | -0.398 |
LDL | -0.356 |
nir | -0.351 |
Greenland | -0.330 |
Token | as |
Token ID | 355 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
HDL | +0.536 |
glacier | +0.480 |
LDL | +0.429 |
nir | +0.416 |
Greenland | +0.399 |
Neg logit contributions | |
toget | -0.518 |
dere | -0.514 |
ettings | -0.504 |
solicit | -0.495 |
•• | -0.495 |
Token | an |
Token ID | 281 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
toget | +0.443 |
dere | +0.441 |
ettings | +0.429 |
solicit | +0.423 |
•• | +0.419 |
Neg logit contributions | |
HDL | -0.583 |
glacier | -0.525 |
LDL | -0.477 |
nir | -0.468 |
Esk | -0.447 |
Token | invasive |
Token ID | 27376 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
toget | +0.280 |
dere | +0.278 |
ettings | +0.269 |
solicit | +0.267 |
•• | +0.264 |
Neg logit contributions | |
HDL | -0.389 |
glacier | -0.351 |
LDL | -0.321 |
nir | -0.314 |
Esk | -0.301 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
toget | +0.243 |
dere | +0.241 |
ettings | +0.234 |
solicit | +0.232 |
outlaw | +0.229 |
Neg logit contributions | |
HDL | -0.274 |
glacier | -0.244 |
LDL | -0.221 |
nir | -0.217 |
Greenland | -0.206 |
Token | Mind |
Token ID | 28478 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
toget | +0.242 |
dere | +0.242 |
ettings | +0.234 |
solicit | +0.232 |
outlaw | +0.229 |
Neg logit contributions | |
HDL | -0.292 |
glacier | -0.262 |
LDL | -0.237 |
nir | -0.234 |
Greenland | -0.221 |
Token | claw |
Token ID | 43143 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
toget | +0.063 |
dere | +0.063 |
ettings | +0.061 |
solicit | +0.060 |
outlaw | +0.060 |
Neg logit contributions | |
HDL | -0.080 |
glacier | -0.072 |
LDL | -0.065 |
nir | -0.065 |
Greenland | -0.061 |
Token | Shaman |
Token ID | 34805 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
HDL | +0.611 |
glacier | +0.553 |
LDL | +0.500 |
nir | +0.498 |
Esk | +0.471 |
Neg logit contributions | |
toget | -0.468 |
dere | -0.467 |
ettings | -0.451 |
solicit | -0.448 |
outlaw | -0.440 |
Token | vs |
Token ID | 3691 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
HDL | +0.307 |
glacier | +0.280 |
LDL | +0.256 |
nir | +0.253 |
Greenland | +0.242 |
Neg logit contributions | |
toget | -0.184 |
dere | -0.184 |
ettings | -0.176 |
solicit | -0.175 |
outlaw | -0.172 |
Token | Pyro |
Token ID | 44954 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
HDL | +0.147 |
glacier | +0.133 |
LDL | +0.120 |
nir | +0.118 |
Esk | +0.113 |
Neg logit contributions | |
toget | -0.119 |
dere | -0.118 |
ettings | -0.115 |
solicit | -0.114 |
•• | -0.112 |
Token | blast |
Token ID | 39806 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
HDL | +1.610 |
glacier | +1.474 |
LDL | +1.320 |
nir | +1.313 |
Greenland | +1.251 |
Neg logit contributions | |
toget | -1.316 |
dere | -1.289 |
ettings | -1.269 |
solicit | -1.241 |
WARN | -1.231 |
Token |
|
Token ID | 198 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
HDL | +0.345 |
glacier | +0.311 |
LDL | +0.280 |
nir | +0.277 |
Greenland | +0.262 |
Neg logit contributions | |
toget | -0.288 |
dere | -0.287 |
ettings | -0.278 |
solicit | -0.276 |
outlaw | -0.272 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
toget | +0.279 |
dere | +0.277 |
ettings | +0.269 |
solicit | +0.267 |
outlaw | +0.263 |
Neg logit contributions | |
HDL | -0.317 |
glacier | -0.283 |
LDL | -0.256 |
nir | -0.251 |
Greenland | -0.238 |
Token | Prim |
Token ID | 23828 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
toget | +0.260 |
dere | +0.259 |
ettings | +0.251 |
solicit | +0.249 |
outlaw | +0.246 |
Neg logit contributions | |
HDL | -0.312 |
glacier | -0.280 |
LDL | -0.253 |
nir | -0.250 |
Greenland | -0.237 |
Token | al |
Token ID | 282 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
toget | +0.102 |
dere | +0.101 |
ettings | +0.098 |
solicit | +0.097 |
outlaw | +0.096 |
Neg logit contributions | |
HDL | -0.101 |
glacier | -0.090 |
LDL | -0.080 |
nir | -0.079 |
Esk | -0.074 |
Token | 30 |
Token ID | 1542 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
HDL | +0.250 |
glacier | +0.223 |
LDL | +0.201 |
nir | +0.196 |
Greenland | +0.187 |
Neg logit contributions | |
toget | -0.228 |
dere | -0.227 |
ettings | -0.222 |
solicit | -0.217 |
•• | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
dere | +0.072 |
toget | +0.072 |
ettings | +0.069 |
solicit | +0.069 |
outlaw | +0.068 |
Neg logit contributions | |
HDL | -0.082 |
glacier | -0.073 |
LDL | -0.066 |
nir | -0.065 |
Greenland | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
HDL | +0.050 |
glacier | +0.044 |
LDL | +0.040 |
nir | +0.039 |
Greenland | +0.037 |
Neg logit contributions | |
dere | -0.042 |
toget | -0.042 |
ettings | -0.041 |
solicit | -0.040 |
outlaw | -0.040 |
Token | its |
Token ID | 663 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
HDL | +0.152 |
glacier | +0.136 |
LDL | +0.123 |
nir | +0.120 |
Esk | +0.115 |
Neg logit contributions | |
toget | -0.129 |
dere | -0.128 |
ettings | -0.125 |
solicit | -0.122 |
•• | -0.121 |
Token | web |
Token ID | 3992 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
HDL | +0.159 |
glacier | +0.143 |
LDL | +0.129 |
nir | +0.126 |
Greenland | +0.120 |
Neg logit contributions | |
toget | -0.134 |
dere | -0.133 |
ettings | -0.129 |
solicit | -0.127 |
•• | -0.126 |
Token | traffic |
Token ID | 4979 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
toget | +0.142 |
dere | +0.142 |
ettings | +0.137 |
solicit | +0.136 |
outlaw | +0.135 |
Neg logit contributions | |
HDL | -0.160 |
glacier | -0.143 |
LDL | -0.129 |
nir | -0.127 |
Greenland | -0.120 |
Token | jumped |
Token ID | 11687 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
HDL | +1.629 |
glacier | +1.475 |
LDL | +1.325 |
nir | +1.297 |
Greenland | +1.247 |
Neg logit contributions | |
toget | -1.286 |
dere | -1.280 |
ettings | -1.259 |
•• | -1.225 |
solicit | -1.220 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
HDL | +0.512 |
glacier | +0.459 |
LDL | +0.413 |
nir | +0.405 |
Greenland | +0.386 |
Neg logit contributions | |
dere | -0.445 |
toget | -0.445 |
ettings | -0.435 |
solicit | -0.426 |
•• | -0.422 |
Token | about |
Token ID | 546 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
HDL | +0.102 |
glacier | +0.091 |
LDL | +0.082 |
nir | +0.080 |
Greenland | +0.077 |
Neg logit contributions | |
toget | -0.084 |
dere | -0.084 |
ettings | -0.082 |
solicit | -0.080 |
•• | -0.080 |
Token | 16 |
Token ID | 1467 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
toget | +0.071 |
dere | +0.071 |
ettings | +0.069 |
solicit | +0.068 |
outlaw | +0.067 |
Neg logit contributions | |
HDL | -0.084 |
glacier | -0.075 |
LDL | -0.068 |
nir | -0.067 |
Greenland | -0.064 |
Token | million |
Token ID | 1510 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
dere | +0.148 |
toget | +0.148 |
ettings | +0.144 |
solicit | +0.144 |
•• | +0.142 |
Neg logit contributions | |
HDL | -0.121 |
glacier | -0.106 |
LDL | -0.094 |
nir | -0.092 |
Greenland | -0.086 |
Token | Source |
Token ID | 7416 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
HDL | +0.240 |
glacier | +0.216 |
LDL | +0.196 |
nir | +0.194 |
uckles | +0.184 |
Neg logit contributions | |
toget | -0.187 |
dere | -0.187 |
ettings | -0.180 |
solicit | -0.179 |
outlaw | -0.177 |
Token | : |
Token ID | 25 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
dere | +0.129 |
toget | +0.129 |
ettings | +0.125 |
solicit | +0.124 |
outlaw | +0.123 |
Neg logit contributions | |
HDL | -0.123 |
glacier | -0.109 |
LDL | -0.097 |
nir | -0.095 |
Greenland | -0.090 |
Token | The |
Token ID | 383 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
HDL | +0.198 |
glacier | +0.177 |
LDL | +0.160 |
nir | +0.157 |
Esk | +0.150 |
Neg logit contributions | |
toget | -0.167 |
dere | -0.166 |
ettings | -0.162 |
solicit | -0.160 |
•• | -0.158 |
Token | Great |
Token ID | 3878 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
HDL | +0.154 |
glacier | +0.139 |
LDL | +0.126 |
nir | +0.124 |
Greenland | +0.118 |
Neg logit contributions | |
toget | -0.116 |
dere | -0.116 |
ettings | -0.112 |
solicit | -0.111 |
•• | -0.109 |
Token | Corporate |
Token ID | 26040 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
HDL | +0.384 |
glacier | +0.345 |
LDL | +0.313 |
nir | +0.309 |
Esk | +0.295 |
Neg logit contributions | |
toget | -0.311 |
dere | -0.304 |
ettings | -0.297 |
solicit | -0.293 |
outlaw | -0.289 |
Token | Earn |
Token ID | 22535 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
HDL | +0.113 |
glacier | +0.102 |
LDL | +0.092 |
nir | +0.091 |
Esk | +0.087 |
Neg logit contributions | |
toget | -0.086 |
dere | -0.085 |
ettings | -0.082 |
solicit | -0.081 |
outlaw | -0.080 |
Token | ings |
Token ID | 654 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
HDL | +1.365 |
glacier | +1.201 |
LDL | +1.072 |
nir | +1.059 |
Esk | +0.993 |
Neg logit contributions | |
toget | -1.543 |
dere | -1.519 |
ettings | -1.481 |
solicit | -1.462 |
•• | -1.449 |
Token | Fraud |
Token ID | 39826 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
toget | +0.280 |
dere | +0.276 |
ettings | +0.269 |
solicit | +0.263 |
outlaw | +0.261 |
Neg logit contributions | |
HDL | -0.393 |
glacier | -0.355 |
LDL | -0.323 |
nir | -0.319 |
Greenland | -0.306 |
Token | - |
Token ID | 532 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
HDL | +0.393 |
glacier | +0.354 |
LDL | +0.319 |
nir | +0.315 |
Greenland | +0.300 |
Neg logit contributions | |
toget | -0.321 |
dere | -0.320 |
ettings | -0.310 |
solicit | -0.307 |
outlaw | -0.303 |
Token | The |
Token ID | 383 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
toget | +0.073 |
dere | +0.073 |
ettings | +0.070 |
solicit | +0.070 |
outlaw | +0.069 |
Neg logit contributions | |
HDL | -0.087 |
glacier | -0.077 |
LDL | -0.070 |
nir | -0.069 |
Greenland | -0.065 |
Token | Burning |
Token ID | 21460 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
HDL | +0.236 |
glacier | +0.212 |
LDL | +0.192 |
nir | +0.189 |
Greenland | +0.181 |
Neg logit contributions | |
toget | -0.188 |
dere | -0.185 |
ettings | -0.180 |
solicit | -0.177 |
•• | -0.175 |
Token | 19 |
Token ID | 678 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
HDL | +0.142 |
glacier | +0.128 |
LDL | +0.116 |
nir | +0.114 |
Greenland | +0.109 |
Neg logit contributions | |
toget | -0.107 |
dere | -0.107 |
ettings | -0.103 |
solicit | -0.102 |
outlaw | -0.101 |
Token | P |
Token ID | 47 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
dere | +0.340 |
toget | +0.339 |
ettings | +0.325 |
solicit | +0.323 |
•• | +0.319 |
Neg logit contributions | |
HDL | -0.563 |
glacier | -0.513 |
LDL | -0.470 |
nir | -0.464 |
uckles | -0.443 |
Token | / |
Token ID | 14 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
HDL | +0.042 |
glacier | +0.038 |
LDL | +0.034 |
nir | +0.034 |
uckles | +0.032 |
Neg logit contributions | |
dere | -0.038 |
toget | -0.038 |
ettings | -0.037 |
solicit | -0.037 |
outlaw | -0.036 |
Token | B |
Token ID | 33 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
HDL | +0.223 |
glacier | +0.200 |
LDL | +0.181 |
nir | +0.178 |
Greenland | +0.168 |
Neg logit contributions | |
dere | -0.188 |
toget | -0.188 |
ettings | -0.181 |
solicit | -0.180 |
•• | -0.178 |
Token | or |
Token ID | 273 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
HDL | +0.370 |
glacier | +0.327 |
LDL | +0.290 |
nir | +0.286 |
uckles | +0.268 |
Neg logit contributions | |
toget | -0.396 |
dere | -0.395 |
ettings | -0.383 |
solicit | -0.381 |
outlaw | -0.377 |
Token | rell |
Token ID | 11252 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
toget | +0.049 |
dere | +0.048 |
ettings | +0.046 |
solicit | +0.046 |
outlaw | +0.045 |
Neg logit contributions | |
HDL | -0.069 |
glacier | -0.063 |
LDL | -0.057 |
nir | -0.057 |
uckles | -0.054 |
Token | y |
Token ID | 88 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
HDL | +1.580 |
glacier | +1.411 |
nir | +1.296 |
LDL | +1.277 |
uckles | +1.200 |
Neg logit contributions | |
toget | -1.366 |
dere | -1.287 |
ettings | -1.253 |
solicit | -1.247 |
outlaw | -1.235 |
Token | , |
Token ID | 11 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
HDL | +0.374 |
glacier | +0.338 |
LDL | +0.306 |
nir | +0.302 |
Greenland | +0.288 |
Neg logit contributions | |
toget | -0.279 |
dere | -0.279 |
ettings | -0.272 |
solicit | -0.268 |
outlaw | -0.264 |
Token | which |
Token ID | 543 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
HDL | +0.197 |
glacier | +0.176 |
LDL | +0.158 |
nir | +0.155 |
Greenland | +0.148 |
Neg logit contributions | |
toget | -0.182 |
dere | -0.182 |
ettings | -0.177 |
solicit | -0.176 |
•• | -0.173 |
Token | was |
Token ID | 373 |
Feature activation | +8.63e-03 |
Pos logit contributions | |
HDL | +0.243 |
glacier | +0.217 |
LDL | +0.194 |
nir | +0.191 |
Greenland | +0.182 |
Neg logit contributions | |
toget | -0.224 |
dere | -0.223 |
ettings | -0.219 |
solicit | -0.216 |
•• | -0.214 |
Token | successful |
Token ID | 4388 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
toget | +0.006 |
dere | +0.006 |
ettings | +0.006 |
solicit | +0.006 |
•• | +0.006 |
Neg logit contributions | |
HDL | -0.007 |
glacier | -0.006 |
LDL | -0.005 |
nir | -0.005 |
Greenland | -0.005 |
Token | because |
Token ID | 780 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
dere | +0.267 |
toget | +0.267 |
ettings | +0.259 |
solicit | +0.257 |
outlaw | +0.253 |
Neg logit contributions | |
HDL | -0.305 |
glacier | -0.273 |
LDL | -0.246 |
nir | -0.242 |
Greenland | -0.230 |
Token | nothing |
Token ID | 2147 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
dere | +0.465 |
toget | +0.465 |
ettings | +0.450 |
solicit | +0.446 |
•• | +0.440 |
Neg logit contributions | |
HDL | -0.609 |
glacier | -0.548 |
LDL | -0.497 |
nir | -0.489 |
Greenland | -0.467 |
Token | says |
Token ID | 1139 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
dere | +0.539 |
toget | +0.539 |
ettings | +0.520 |
solicit | +0.516 |
outlaw | +0.509 |
Neg logit contributions | |
HDL | -0.725 |
glacier | -0.654 |
LDL | -0.595 |
nir | -0.586 |
Greenland | -0.558 |
Token | mad |
Token ID | 8805 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
toget | +0.134 |
dere | +0.134 |
ettings | +0.129 |
solicit | +0.128 |
•• | +0.126 |
Neg logit contributions | |
HDL | -0.179 |
glacier | -0.161 |
LDL | -0.147 |
nir | -0.144 |
Greenland | -0.138 |
Token | geek |
Token ID | 27314 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
dere | +0.112 |
toget | +0.111 |
ettings | +0.108 |
solicit | +0.107 |
outlaw | +0.106 |
Neg logit contributions | |
HDL | -0.141 |
glacier | -0.127 |
LDL | -0.115 |
nir | -0.114 |
Greenland | -0.108 |
Token | cred |
Token ID | 2600 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
toget | +0.369 |
dere | +0.368 |
ettings | +0.357 |
solicit | +0.354 |
•• | +0.350 |
Neg logit contributions | |
HDL | -0.433 |
glacier | -0.388 |
LDL | -0.350 |
nir | -0.345 |
Greenland | -0.327 |
Token | like |
Token ID | 588 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
HDL | +1.450 |
glacier | +1.284 |
LDL | +1.151 |
nir | +1.138 |
� | +1.070 |
Neg logit contributions | |
toget | -1.416 |
dere | -1.407 |
ettings | -1.376 |
solicit | -1.358 |
WARN | -1.344 |
Token | wearing |
Token ID | 5762 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
HDL | +0.280 |
glacier | +0.250 |
LDL | +0.224 |
nir | +0.220 |
Greenland | +0.208 |
Neg logit contributions | |
toget | -0.262 |
dere | -0.262 |
ettings | -0.255 |
solicit | -0.252 |
•• | -0.249 |
Token | a |
Token ID | 257 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
HDL | +0.725 |
glacier | +0.650 |
LDL | +0.579 |
nir | +0.564 |
Greenland | +0.541 |
Neg logit contributions | |
toget | -0.691 |
dere | -0.687 |
ettings | -0.676 |
solicit | -0.664 |
•• | -0.658 |
Token | TR |
Token ID | 7579 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
toget | +0.183 |
dere | +0.183 |
ettings | +0.177 |
solicit | +0.176 |
•• | +0.173 |
Neg logit contributions | |
HDL | -0.228 |
glacier | -0.206 |
LDL | -0.186 |
nir | -0.183 |
Greenland | -0.174 |
Token | ON |
Token ID | 1340 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
toget | +0.084 |
dere | +0.084 |
ettings | +0.081 |
solicit | +0.081 |
outlaw | +0.080 |
Neg logit contributions | |
HDL | -0.095 |
glacier | -0.084 |
LDL | -0.076 |
nir | -0.075 |
Greenland | -0.071 |
Token | . |
Token ID | 764 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
dere | +0.735 |
toget | +0.733 |
ettings | +0.708 |
solicit | +0.706 |
outlaw | +0.696 |
Neg logit contributions | |
HDL | -0.901 |
glacier | -0.809 |
LDL | -0.732 |
nir | -0.723 |
uckles | -0.684 |
Token | y |
Token ID | 331 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
HDL | +0.415 |
glacier | +0.373 |
LDL | +0.338 |
nir | +0.333 |
Greenland | +0.316 |
Neg logit contributions | |
dere | -0.334 |
toget | -0.334 |
ettings | -0.323 |
solicit | -0.320 |
outlaw | -0.316 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
HDL | +0.380 |
glacier | +0.339 |
LDL | +0.305 |
nir | +0.301 |
Greenland | +0.284 |
Neg logit contributions | |
toget | -0.343 |
dere | -0.342 |
ettings | -0.331 |
solicit | -0.330 |
outlaw | -0.325 |
Token | ; |
Token ID | 2162 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
dere | +0.323 |
toget | +0.323 |
ettings | +0.312 |
solicit | +0.310 |
outlaw | +0.306 |
Neg logit contributions | |
HDL | -0.371 |
glacier | -0.332 |
LDL | -0.299 |
nir | -0.295 |
Greenland | -0.279 |
Token | return |
Token ID | 1441 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
HDL | +0.121 |
glacier | +0.108 |
LDL | +0.098 |
nir | +0.096 |
Greenland | +0.092 |
Neg logit contributions | |
dere | -0.094 |
toget | -0.094 |
ettings | -0.091 |
solicit | -0.090 |
•• | -0.090 |
Token | normal |
Token ID | 3487 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
dere | +0.457 |
toget | +0.456 |
ettings | +0.440 |
solicit | +0.438 |
outlaw | +0.432 |
Neg logit contributions | |
HDL | -0.584 |
glacier | -0.526 |
LDL | -0.476 |
nir | -0.470 |
uckles | -0.447 |
Token | ; |
Token ID | 2162 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
toget | +1.782 |
dere | +1.774 |
ettings | +1.720 |
solicit | +1.712 |
outlaw | +1.689 |
Neg logit contributions | |
HDL | -1.882 |
glacier | -1.674 |
LDL | -1.500 |
nir | -1.479 |
uckles | -1.397 |
Token | # |
Token ID | 1303 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
dere | +0.060 |
toget | +0.060 |
ettings | +0.058 |
solicit | +0.058 |
•• | +0.057 |
Neg logit contributions | |
HDL | -0.074 |
glacier | -0.066 |
LDL | -0.060 |
nir | -0.059 |
Greenland | -0.056 |
Token | endif |
Token ID | 32088 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
dere | +0.376 |
toget | +0.375 |
ettings | +0.361 |
solicit | +0.357 |
•• | +0.352 |
Neg logit contributions | |
HDL | -0.606 |
glacier | -0.551 |
LDL | -0.504 |
nir | -0.498 |
Esk | -0.475 |
Token | } |
Token ID | 1782 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
dere | +0.716 |
toget | +0.715 |
ettings | +0.690 |
solicit | +0.686 |
outlaw | +0.677 |
Neg logit contributions | |
HDL | -0.941 |
glacier | -0.848 |
LDL | -0.769 |
nir | -0.760 |
uckles | -0.723 |
Token | If |
Token ID | 1002 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
dere | +0.155 |
toget | +0.155 |
ettings | +0.150 |
solicit | +0.149 |
•• | +0.147 |
Neg logit contributions | |
HDL | -0.205 |
glacier | -0.185 |
LDL | -0.168 |
nir | -0.166 |
Greenland | -0.157 |
Token | � |
Token ID | 251 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
toget | +0.195 |
dere | +0.195 |
ettings | +0.189 |
solicit | +0.188 |
outlaw | +0.186 |
Neg logit contributions | |
HDL | -0.199 |
glacier | -0.177 |
LDL | -0.159 |
nir | -0.156 |
Greenland | -0.147 |
Token | said |
Token ID | 531 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
dere | +0.314 |
toget | +0.313 |
ettings | +0.302 |
solicit | +0.301 |
•• | +0.299 |
Neg logit contributions | |
HDL | -0.350 |
glacier | -0.312 |
LDL | -0.282 |
nir | -0.278 |
Esk | -0.262 |
Token | Dr |
Token ID | 1583 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
dere | +0.047 |
toget | +0.047 |
ettings | +0.045 |
solicit | +0.045 |
outlaw | +0.045 |
Neg logit contributions | |
HDL | -0.045 |
glacier | -0.039 |
LDL | -0.035 |
nir | -0.035 |
uckles | -0.033 |
Token | Dum |
Token ID | 30933 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
HDL | +0.186 |
glacier | +0.166 |
LDL | +0.149 |
nir | +0.147 |
Greenland | +0.139 |
Neg logit contributions | |
dere | -0.169 |
toget | -0.169 |
ettings | -0.164 |
solicit | -0.163 |
outlaw | -0.161 |
Token | us |
Token ID | 385 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
dere | +0.640 |
toget | +0.639 |
ettings | +0.620 |
solicit | +0.617 |
outlaw | +0.609 |
Neg logit contributions | |
HDL | -0.674 |
glacier | -0.600 |
LDL | -0.538 |
nir | -0.529 |
Greenland | -0.499 |
Token | que |
Token ID | 4188 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
toget | +0.154 |
dere | +0.154 |
ettings | +0.145 |
solicit | +0.143 |
outlaw | +0.141 |
Neg logit contributions | |
HDL | -0.372 |
glacier | -0.343 |
LDL | -0.318 |
nir | -0.315 |
Greenland | -0.303 |
Token | , |
Token ID | 11 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
toget | +1.042 |
dere | +1.041 |
ettings | +1.004 |
solicit | +1.002 |
outlaw | +0.988 |
Neg logit contributions | |
HDL | -1.289 |
glacier | -1.158 |
LDL | -1.049 |
nir | -1.036 |
uckles | -0.982 |
Token | who |
Token ID | 508 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
dere | +0.255 |
toget | +0.255 |
ettings | +0.246 |
solicit | +0.245 |
outlaw | +0.241 |
Neg logit contributions | |
HDL | -0.320 |
glacier | -0.288 |
LDL | -0.261 |
nir | -0.258 |
uckles | -0.244 |
Token | is |
Token ID | 318 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
toget | +0.228 |
dere | +0.228 |
ettings | +0.222 |
solicit | +0.218 |
•• | +0.217 |
Neg logit contributions | |
HDL | -0.280 |
glacier | -0.253 |
LDL | -0.228 |
nir | -0.224 |
Greenland | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
dere | +0.080 |
toget | +0.080 |
solicit | +0.077 |
ettings | +0.077 |
outlaw | +0.076 |
Neg logit contributions | |
HDL | -0.093 |
glacier | -0.083 |
LDL | -0.075 |
nir | -0.074 |
uckles | -0.070 |
Token | lead |
Token ID | 1085 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
toget | +0.084 |
dere | +0.084 |
ettings | +0.081 |
solicit | +0.081 |
•• | +0.080 |
Neg logit contributions | |
HDL | -0.106 |
glacier | -0.096 |
LDL | -0.087 |
nir | -0.085 |
Greenland | -0.081 |
Token | mistake |
Token ID | 7457 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
HDL | +0.211 |
glacier | +0.189 |
LDL | +0.170 |
nir | +0.167 |
Greenland | +0.159 |
Neg logit contributions | |
toget | -0.188 |
dere | -0.187 |
ettings | -0.182 |
solicit | -0.180 |
outlaw | -0.178 |
Token | calls |
Token ID | 3848 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
dere | +0.053 |
toget | +0.053 |
ettings | +0.051 |
solicit | +0.051 |
outlaw | +0.050 |
Neg logit contributions | |
HDL | -0.066 |
glacier | -0.060 |
LDL | -0.054 |
nir | -0.053 |
Greenland | -0.051 |
Token | for |
Token ID | 329 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
dere | +0.456 |
toget | +0.454 |
ettings | +0.436 |
solicit | +0.435 |
•• | +0.428 |
Neg logit contributions | |
HDL | -0.665 |
glacier | -0.602 |
LDL | -0.551 |
nir | -0.543 |
uckles | -0.517 |
Token | the |
Token ID | 262 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
HDL | +0.103 |
glacier | +0.092 |
LDL | +0.083 |
nir | +0.082 |
Greenland | +0.078 |
Neg logit contributions | |
toget | -0.087 |
dere | -0.087 |
ettings | -0.084 |
solicit | -0.083 |
outlaw | -0.082 |
Token | P |
Token ID | 350 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
HDL | +0.136 |
glacier | +0.122 |
LDL | +0.111 |
nir | +0.109 |
Greenland | +0.103 |
Neg logit contributions | |
toget | -0.112 |
dere | -0.112 |
ettings | -0.109 |
solicit | -0.107 |
outlaw | -0.106 |
Token | w |
Token ID | 86 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
HDL | +0.090 |
glacier | +0.083 |
LDL | +0.078 |
nir | +0.076 |
uckles | +0.074 |
Neg logit contributions | |
toget | -0.031 |
dere | -0.030 |
ettings | -0.028 |
solicit | -0.028 |
outlaw | -0.027 |
Token | C |
Token ID | 34 |
Feature activation | -8.09e-03 |
Pos logit contributions | |
dere | +0.820 |
toget | +0.802 |
ettings | +0.789 |
solicit | +0.788 |
•• | +0.779 |
Neg logit contributions | |
HDL | -1.234 |
glacier | -1.121 |
LDL | -1.021 |
nir | -1.014 |
Esk | -0.963 |
Token | employees |
Token ID | 4409 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
HDL | +0.006 |
glacier | +0.006 |
LDL | +0.005 |
nir | +0.005 |
Greenland | +0.005 |
Neg logit contributions | |
dere | -0.005 |
toget | -0.005 |
ettings | -0.005 |
solicit | -0.005 |
•• | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
HDL | +0.120 |
glacier | +0.108 |
LDL | +0.097 |
nir | +0.096 |
Greenland | +0.091 |
Neg logit contributions | |
toget | -0.103 |
dere | -0.103 |
ettings | -0.100 |
solicit | -0.099 |
•• | -0.098 |
Token | then |
Token ID | 788 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
dere | +0.028 |
toget | +0.028 |
ettings | +0.027 |
solicit | +0.026 |
•• | +0.026 |
Neg logit contributions | |
HDL | -0.038 |
glacier | -0.034 |
LDL | -0.031 |
nir | -0.030 |
Greenland | -0.029 |
Token | take |
Token ID | 1011 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
dere | +0.078 |
toget | +0.078 |
ettings | +0.075 |
solicit | +0.074 |
•• | +0.074 |
Neg logit contributions | |
HDL | -0.106 |
glacier | -0.096 |
LDL | -0.087 |
nir | -0.085 |
Greenland | -0.081 |
Token | F |
Token ID | 37 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
dere | +0.580 |
toget | +0.579 |
ettings | +0.561 |
solicit | +0.559 |
outlaw | +0.552 |
Neg logit contributions | |
HDL | -0.627 |
glacier | -0.560 |
LDL | -0.503 |
nir | -0.495 |
Greenland | -0.467 |
Token | Co |
Token ID | 1766 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
dere | +0.242 |
toget | +0.242 |
ettings | +0.235 |
solicit | +0.234 |
outlaw | +0.231 |
Neg logit contributions | |
HDL | -0.243 |
glacier | -0.216 |
LDL | -0.193 |
nir | -0.190 |
Greenland | -0.179 |
Token | - |
Token ID | 12 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
dere | +0.602 |
toget | +0.596 |
ettings | +0.578 |
solicit | +0.577 |
•• | +0.568 |
Neg logit contributions | |
HDL | -0.878 |
glacier | -0.796 |
LDL | -0.724 |
nir | -0.715 |
Greenland | -0.681 |
Token | President |
Token ID | 10364 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
dere | +0.620 |
toget | +0.618 |
ettings | +0.602 |
solicit | +0.600 |
•• | +0.595 |
Neg logit contributions | |
HDL | -0.491 |
glacier | -0.428 |
LDL | -0.376 |
nir | -0.367 |
Greenland | -0.343 |
Token | Annie |
Token ID | 25860 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
dere | +0.566 |
toget | +0.565 |
ettings | +0.547 |
solicit | +0.544 |
outlaw | +0.537 |
Neg logit contributions | |
HDL | -0.632 |
glacier | -0.565 |
LDL | -0.508 |
nir | -0.501 |
Greenland | -0.473 |
Token | Laurie |
Token ID | 40811 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
dere | +0.359 |
toget | +0.356 |
ettings | +0.349 |
solicit | +0.348 |
•• | +0.343 |
Neg logit contributions | |
HDL | -0.321 |
glacier | -0.282 |
LDL | -0.248 |
nir | -0.248 |
� | -0.232 |
Token | G |
Token ID | 402 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
dere | +1.185 |
Wy | +1.178 |
toget | +1.176 |
solicit | +1.143 |
outlaw | +1.133 |
Neg logit contributions | |
HDL | -1.206 |
glacier | -1.093 |
nir | -0.981 |
LDL | -0.951 |
� | -0.921 |
Token | aylor |
Token ID | 7167 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
toget | +0.609 |
dere | +0.609 |
ettings | +0.587 |
solicit | +0.583 |
•• | +0.580 |
Neg logit contributions | |
HDL | -0.633 |
glacier | -0.564 |
LDL | -0.506 |
nir | -0.495 |
uckles | -0.472 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
HDL | +0.182 |
glacier | +0.163 |
LDL | +0.146 |
nir | +0.144 |
Greenland | +0.137 |
Neg logit contributions | |
toget | -0.155 |
dere | -0.155 |
ettings | -0.150 |
solicit | -0.148 |
•• | -0.147 |
Token | " |
Token ID | 366 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
dere | +0.067 |
toget | +0.067 |
ettings | +0.064 |
solicit | +0.064 |
outlaw | +0.063 |
Neg logit contributions | |
HDL | -0.111 |
glacier | -0.101 |
LDL | -0.093 |
nir | -0.092 |
Greenland | -0.088 |
Token | V |
Token ID | 53 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
dere | +0.023 |
toget | +0.023 |
ettings | +0.022 |
solicit | +0.022 |
•• | +0.022 |
Neg logit contributions | |
HDL | -0.031 |
glacier | -0.028 |
LDL | -0.025 |
nir | -0.025 |
Greenland | -0.024 |
Token | ler |
Token ID | 1754 |
Feature activation | -9.73e-02 |
Pos logit contributions | |
HDL | +0.146 |
glacier | +0.130 |
LDL | +0.116 |
nir | +0.115 |
Esk | +0.109 |
Neg logit contributions | |
dere | -0.139 |
toget | -0.137 |
ettings | -0.134 |
solicit | -0.134 |
•• | -0.132 |
Token | said |
Token ID | 531 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
HDL | +0.073 |
glacier | +0.065 |
LDL | +0.058 |
nir | +0.057 |
Greenland | +0.054 |
Neg logit contributions | |
toget | -0.070 |
dere | -0.070 |
ettings | -0.068 |
•• | -0.067 |
solicit | -0.067 |
Token | they |
Token ID | 484 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
toget | +0.030 |
dere | +0.030 |
ettings | +0.030 |
solicit | +0.029 |
•• | +0.029 |
Neg logit contributions | |
HDL | -0.036 |
glacier | -0.033 |
LDL | -0.029 |
nir | -0.029 |
Greenland | -0.028 |
Token | took |
Token ID | 1718 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
toget | +0.224 |
dere | +0.223 |
ettings | +0.217 |
solicit | +0.215 |
•• | +0.214 |
Neg logit contributions | |
HDL | -0.204 |
glacier | -0.181 |
LDL | -0.160 |
nir | -0.157 |
Greenland | -0.148 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
toget | +0.016 |
dere | +0.016 |
ettings | +0.015 |
solicit | +0.015 |
•• | +0.015 |
Neg logit contributions | |
HDL | -0.019 |
glacier | -0.017 |
LDL | -0.015 |
nir | -0.015 |
Greenland | -0.014 |
Token | pred |
Token ID | 2747 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
toget | +0.139 |
dere | +0.137 |
ettings | +0.135 |
solicit | +0.132 |
•• | +0.131 |
Neg logit contributions | |
HDL | -0.164 |
glacier | -0.147 |
LDL | -0.132 |
nir | -0.129 |
Greenland | -0.124 |
Token | ications |
Token ID | 3736 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
dere | +1.372 |
toget | +1.356 |
solicit | +1.320 |
ettings | +1.317 |
outlaw | +1.304 |
Neg logit contributions | |
HDL | -1.438 |
glacier | -1.279 |
LDL | -1.143 |
nir | -1.122 |
uckles | -1.063 |
Token | they |
Token ID | 484 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
dere | +0.135 |
toget | +0.135 |
ettings | +0.130 |
solicit | +0.129 |
•• | +0.128 |
Neg logit contributions | |
HDL | -0.179 |
glacier | -0.162 |
LDL | -0.147 |
nir | -0.144 |
Greenland | -0.138 |
Token | made |
Token ID | 925 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
dere | +0.213 |
toget | +0.213 |
ettings | +0.207 |
solicit | +0.205 |
•• | +0.204 |
Neg logit contributions | |
HDL | -0.199 |
glacier | -0.176 |
LDL | -0.156 |
nir | -0.153 |
Greenland | -0.144 |
Token | globally |
Token ID | 18309 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
dere | +0.066 |
toget | +0.066 |
ettings | +0.064 |
solicit | +0.063 |
•• | +0.062 |
Neg logit contributions | |
HDL | -0.086 |
glacier | -0.077 |
LDL | -0.070 |
nir | -0.069 |
Greenland | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
dere | +0.505 |
toget | +0.505 |
ettings | +0.487 |
solicit | +0.484 |
outlaw | +0.478 |
Neg logit contributions | |
HDL | -0.647 |
glacier | -0.582 |
LDL | -0.527 |
nir | -0.520 |
Greenland | -0.494 |
Token | . |
Token ID | 13 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
toget | +0.273 |
dere | +0.273 |
ettings | +0.264 |
solicit | +0.262 |
outlaw | +0.259 |
Neg logit contributions | |
HDL | -0.321 |
glacier | -0.288 |
LDL | -0.259 |
nir | -0.255 |
Greenland | -0.242 |
Token | You |
Token ID | 1639 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
HDL | +0.310 |
glacier | +0.274 |
LDL | +0.250 |
nir | +0.244 |
Esk | +0.234 |
Neg logit contributions | |
toget | -0.269 |
dere | -0.267 |
ettings | -0.259 |
solicit | -0.256 |
outlaw | -0.253 |
Token | 've |
Token ID | 1053 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
toget | +0.007 |
dere | +0.007 |
ettings | +0.006 |
•• | +0.006 |
solicit | +0.006 |
Neg logit contributions | |
HDL | -0.008 |
glacier | -0.007 |
LDL | -0.006 |
nir | -0.006 |
Greenland | -0.006 |
Token | got |
Token ID | 1392 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
dere | +0.154 |
toget | +0.153 |
ettings | +0.149 |
solicit | +0.148 |
•• | +0.147 |
Neg logit contributions | |
HDL | -0.134 |
glacier | -0.118 |
LDL | -0.104 |
nir | -0.103 |
Greenland | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
HDL | +0.206 |
glacier | +0.185 |
LDL | +0.167 |
nir | +0.163 |
Greenland | +0.155 |
Neg logit contributions | |
toget | -0.180 |
dere | -0.180 |
ettings | -0.175 |
solicit | -0.173 |
•• | -0.171 |
Token | hand |
Token ID | 1021 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
dere | +0.027 |
toget | +0.027 |
ettings | +0.027 |
•• | +0.026 |
solicit | +0.026 |
Neg logit contributions | |
HDL | -0.034 |
glacier | -0.030 |
LDL | -0.027 |
nir | -0.027 |
Greenland | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
dere | +0.624 |
toget | +0.621 |
ettings | +0.600 |
solicit | +0.598 |
outlaw | +0.590 |
Neg logit contributions | |
HDL | -0.756 |
glacier | -0.678 |
LDL | -0.613 |
nir | -0.605 |
Greenland | -0.572 |
Token | to |
Token ID | 284 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
dere | +0.078 |
toget | +0.078 |
ettings | +0.075 |
solicit | +0.075 |
outlaw | +0.074 |
Neg logit contributions | |
HDL | -0.091 |
glacier | -0.082 |
LDL | -0.074 |
nir | -0.072 |
Greenland | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
HDL | +0.026 |
glacier | +0.023 |
LDL | +0.021 |
nir | +0.021 |
Esk | +0.020 |
Neg logit contributions | |
toget | -0.023 |
dere | -0.023 |
ettings | -0.022 |
solicit | -0.022 |
•• | -0.022 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
toget | +0.095 |
dere | +0.094 |
ettings | +0.092 |
solicit | +0.090 |
•• | +0.089 |
Neg logit contributions | |
HDL | -0.146 |
glacier | -0.133 |
LDL | -0.121 |
nir | -0.119 |
Esk | -0.115 |
Token | for |
Token ID | 329 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
toget | +0.093 |
dere | +0.093 |
ettings | +0.090 |
solicit | +0.089 |
•• | +0.088 |
Neg logit contributions | |
HDL | -0.117 |
glacier | -0.105 |
LDL | -0.095 |
nir | -0.094 |
Esk | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
dere | +0.170 |
toget | +0.170 |
ettings | +0.164 |
solicit | +0.164 |
outlaw | +0.161 |
Neg logit contributions | |
HDL | -0.210 |
glacier | -0.188 |
LDL | -0.171 |
nir | -0.168 |
uckles | -0.160 |
Token | Apple |
Token ID | 4196 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
dere | +0.147 |
toget | +0.147 |
ettings | +0.142 |
solicit | +0.141 |
outlaw | +0.139 |
Neg logit contributions | |
HDL | -0.172 |
glacier | -0.155 |
LDL | -0.139 |
nir | -0.137 |
Greenland | -0.130 |
Token | is |
Token ID | 318 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
HDL | +0.432 |
glacier | +0.390 |
LDL | +0.352 |
nir | +0.347 |
Esk | +0.332 |
Neg logit contributions | |
dere | -0.337 |
toget | -0.337 |
ettings | -0.326 |
solicit | -0.322 |
•• | -0.318 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
toget | +0.017 |
dere | +0.017 |
ettings | +0.016 |
solicit | +0.016 |
•• | +0.016 |
Neg logit contributions | |
HDL | -0.020 |
glacier | -0.018 |
LDL | -0.016 |
nir | -0.015 |
Greenland | -0.015 |
Token | only |
Token ID | 691 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
toget | +0.089 |
dere | +0.088 |
ettings | +0.085 |
solicit | +0.084 |
•• | +0.083 |
Neg logit contributions | |
HDL | -0.122 |
glacier | -0.110 |
LDL | -0.100 |
nir | -0.098 |
Greenland | -0.094 |
Token | brand |
Token ID | 4508 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
toget | +0.042 |
dere | +0.042 |
ettings | +0.041 |
solicit | +0.040 |
•• | +0.040 |
Neg logit contributions | |
HDL | -0.054 |
glacier | -0.049 |
LDL | -0.044 |
nir | -0.043 |
Esk | -0.042 |
Token | ahead |
Token ID | 4058 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
dere | +0.141 |
toget | +0.141 |
ettings | +0.136 |
solicit | +0.135 |
outlaw | +0.133 |
Neg logit contributions | |
HDL | -0.175 |
glacier | -0.158 |
LDL | -0.143 |
nir | -0.141 |
Greenland | -0.134 |
Token | of |
Token ID | 286 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
HDL | +0.168 |
glacier | +0.152 |
LDL | +0.138 |
nir | +0.136 |
Greenland | +0.130 |
Neg logit contributions | |
dere | -0.116 |
toget | -0.116 |
ettings | -0.111 |
solicit | -0.110 |
outlaw | -0.109 |
Token | it |
Token ID | 340 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
HDL | +0.132 |
glacier | +0.117 |
LDL | +0.104 |
nir | +0.103 |
uckles | +0.096 |
Neg logit contributions | |
dere | -0.137 |
toget | -0.137 |
ettings | -0.133 |
solicit | -0.132 |
outlaw | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
dere | +0.048 |
toget | +0.048 |
ettings | +0.047 |
solicit | +0.046 |
outlaw | +0.046 |
Neg logit contributions | |
HDL | -0.060 |
glacier | -0.054 |
LDL | -0.049 |
nir | -0.048 |
Greenland | -0.045 |
Token | worth |
Token ID | 2861 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
dere | +0.122 |
toget | +0.122 |
ettings | +0.118 |
solicit | +0.118 |
outlaw | +0.116 |
Neg logit contributions | |
HDL | -0.141 |
glacier | -0.126 |
LDL | -0.114 |
nir | -0.112 |
uckles | -0.106 |
Token | transition |
Token ID | 6801 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
HDL | +0.030 |
glacier | +0.027 |
LDL | +0.024 |
nir | +0.024 |
Esk | +0.023 |
Neg logit contributions | |
toget | -0.026 |
dere | -0.025 |
ettings | -0.025 |
WARN | -0.024 |
solicit | -0.024 |
Token | (" |
Token ID | 5855 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
HDL | +0.368 |
glacier | +0.329 |
LDL | +0.296 |
nir | +0.292 |
Greenland | +0.277 |
Neg logit contributions | |
dere | -0.321 |
toget | -0.320 |
ettings | -0.311 |
solicit | -0.308 |
WARN | -0.305 |
Token | trans |
Token ID | 7645 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
HDL | +0.227 |
glacier | +0.204 |
LDL | +0.184 |
nir | +0.182 |
Greenland | +0.172 |
Neg logit contributions | |
dere | -0.193 |
toget | -0.192 |
ettings | -0.186 |
solicit | -0.185 |
outlaw | -0.183 |
Token | sexual |
Token ID | 18338 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
HDL | +0.126 |
glacier | +0.111 |
LDL | +0.098 |
nir | +0.097 |
Esk | +0.090 |
Neg logit contributions | |
dere | -0.147 |
toget | -0.147 |
ettings | -0.143 |
solicit | -0.142 |
•• | -0.141 |
Token | " |
Token ID | 1 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
dere | +0.194 |
toget | +0.194 |
ettings | +0.187 |
solicit | +0.186 |
outlaw | +0.184 |
Neg logit contributions | |
HDL | -0.236 |
glacier | -0.212 |
LDL | -0.191 |
nir | -0.188 |
Greenland | -0.179 |
Token | people |
Token ID | 661 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
HDL | +0.392 |
glacier | +0.351 |
LDL | +0.316 |
nir | +0.311 |
Greenland | +0.295 |
Neg logit contributions | |
dere | -0.340 |
toget | -0.340 |
ettings | -0.329 |
solicit | -0.327 |
outlaw | -0.322 |
Token | ) |
Token ID | 8 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
toget | +0.225 |
dere | +0.224 |
ettings | +0.217 |
solicit | +0.216 |
•• | +0.213 |
Neg logit contributions | |
HDL | -0.249 |
glacier | -0.223 |
LDL | -0.200 |
nir | -0.197 |
Greenland | -0.187 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
dere | +0.070 |
toget | +0.070 |
ettings | +0.068 |
solicit | +0.067 |
•• | +0.066 |
Neg logit contributions | |
HDL | -0.076 |
glacier | -0.068 |
LDL | -0.061 |
nir | -0.060 |
Greenland | -0.057 |
Token | other |
Token ID | 584 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
HDL | +0.136 |
glacier | +0.121 |
LDL | +0.108 |
nir | +0.104 |
Esk | +0.100 |
Neg logit contributions | |
toget | -0.144 |
dere | -0.144 |
ettings | -0.140 |
solicit | -0.138 |
WARN | -0.138 |
Token | gender |
Token ID | 5279 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
toget | +0.097 |
dere | +0.097 |
ettings | +0.094 |
solicit | +0.093 |
WARN | +0.092 |
Neg logit contributions | |
HDL | -0.109 |
glacier | -0.098 |
LDL | -0.088 |
nir | -0.086 |
Esk | -0.082 |
Token | non |
Token ID | 1729 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
HDL | +0.024 |
glacier | +0.022 |
LDL | +0.020 |
nir | +0.020 |
Esk | +0.019 |
Neg logit contributions | |
toget | -0.018 |
dere | -0.018 |
ettings | -0.017 |
WARN | -0.017 |
solicit | -0.017 |
Token | like |
Token ID | 588 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
toget | +0.343 |
dere | +0.343 |
ettings | +0.331 |
solicit | +0.329 |
outlaw | +0.325 |
Neg logit contributions | |
HDL | -0.408 |
glacier | -0.366 |
LDL | -0.331 |
nir | -0.326 |
Greenland | -0.309 |
Token | there |
Token ID | 612 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
toget | +0.027 |
dere | +0.027 |
ettings | +0.027 |
solicit | +0.026 |
•• | +0.026 |
Neg logit contributions | |
HDL | -0.031 |
glacier | -0.028 |
LDL | -0.025 |
nir | -0.024 |
Greenland | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
HDL | +0.187 |
glacier | +0.167 |
LDL | +0.151 |
nir | +0.149 |
Greenland | +0.141 |
Neg logit contributions | |
dere | -0.155 |
toget | -0.154 |
ettings | -0.149 |
solicit | -0.148 |
outlaw | -0.146 |
Token | a |
Token ID | 257 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
HDL | +0.128 |
glacier | +0.115 |
LDL | +0.104 |
nir | +0.102 |
Greenland | +0.097 |
Neg logit contributions | |
toget | -0.109 |
dere | -0.109 |
ettings | -0.106 |
solicit | -0.105 |
•• | -0.103 |
Token | purpose |
Token ID | 4007 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
HDL | +0.043 |
glacier | +0.038 |
LDL | +0.034 |
nir | +0.034 |
Greenland | +0.032 |
Neg logit contributions | |
toget | -0.036 |
dere | -0.035 |
ettings | -0.034 |
solicit | -0.034 |
•• | -0.034 |
Token | ful |
Token ID | 913 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
dere | +0.287 |
toget | +0.287 |
ettings | +0.276 |
solicit | +0.274 |
outlaw | +0.269 |
Neg logit contributions | |
HDL | -0.454 |
glacier | -0.412 |
LDL | -0.377 |
nir | -0.372 |
Greenland | -0.356 |
Token | tactic |
Token ID | 18543 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
toget | +0.135 |
dere | +0.133 |
ettings | +0.130 |
solicit | +0.128 |
•• | +0.127 |
Neg logit contributions | |
HDL | -0.168 |
glacier | -0.151 |
LDL | -0.137 |
nir | -0.134 |
Greenland | -0.128 |
Token | to |
Token ID | 284 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
dere | +0.531 |
toget | +0.531 |
ettings | +0.511 |
solicit | +0.509 |
outlaw | +0.503 |
Neg logit contributions | |
HDL | -0.652 |
glacier | -0.586 |
LDL | -0.530 |
nir | -0.522 |
Greenland | -0.495 |
Token | deter |
Token ID | 2206 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
toget | +0.049 |
dere | +0.048 |
ettings | +0.047 |
•• | +0.046 |
solicit | +0.046 |
Neg logit contributions | |
HDL | -0.068 |
glacier | -0.062 |
LDL | -0.056 |
nir | -0.055 |
Greenland | -0.053 |
Token | people |
Token ID | 661 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
HDL | +0.252 |
glacier | +0.223 |
LDL | +0.199 |
nir | +0.195 |
Greenland | +0.184 |
Neg logit contributions | |
dere | -0.266 |
toget | -0.266 |
ettings | -0.259 |
solicit | -0.257 |
outlaw | -0.254 |
Token | from |
Token ID | 422 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
HDL | +0.098 |
glacier | +0.088 |
LDL | +0.079 |
nir | +0.077 |
Greenland | +0.073 |
Neg logit contributions | |
dere | -0.092 |
toget | -0.092 |
ettings | -0.090 |
solicit | -0.088 |
•• | -0.088 |
Token | for |
Token ID | 329 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
dere | +0.224 |
toget | +0.224 |
ettings | +0.216 |
solicit | +0.214 |
•• | +0.211 |
Neg logit contributions | |
HDL | -0.324 |
glacier | -0.293 |
LDL | -0.267 |
nir | -0.263 |
Greenland | -0.251 |
Token | anything |
Token ID | 1997 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
toget | +0.056 |
dere | +0.056 |
ettings | +0.054 |
solicit | +0.054 |
•• | +0.053 |
Neg logit contributions | |
HDL | -0.071 |
glacier | -0.064 |
LDL | -0.058 |
nir | -0.057 |
Greenland | -0.054 |
Token | having |
Token ID | 1719 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
dere | +0.202 |
toget | +0.202 |
ettings | +0.196 |
solicit | +0.194 |
•• | +0.191 |
Neg logit contributions | |
HDL | -0.276 |
glacier | -0.248 |
LDL | -0.226 |
nir | -0.222 |
Greenland | -0.212 |
Token | to |
Token ID | 284 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
HDL | +0.221 |
glacier | +0.199 |
LDL | +0.179 |
nir | +0.178 |
Esk | +0.168 |
Neg logit contributions | |
dere | -0.184 |
toget | -0.184 |
ettings | -0.177 |
solicit | -0.177 |
outlaw | -0.175 |
Token | do |
Token ID | 466 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
HDL | +0.165 |
glacier | +0.147 |
LDL | +0.133 |
nir | +0.131 |
Greenland | +0.123 |
Neg logit contributions | |
dere | -0.147 |
toget | -0.147 |
ettings | -0.142 |
solicit | -0.142 |
outlaw | -0.140 |
Token | with |
Token ID | 351 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
HDL | +0.258 |
glacier | +0.231 |
LDL | +0.209 |
nir | +0.206 |
Greenland | +0.195 |
Neg logit contributions | |
toget | -0.218 |
dere | -0.218 |
ettings | -0.211 |
solicit | -0.209 |
outlaw | -0.206 |
Token | leaving |
Token ID | 4305 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
dere | +0.054 |
toget | +0.054 |
ettings | +0.052 |
solicit | +0.052 |
outlaw | +0.051 |
Neg logit contributions | |
HDL | -0.065 |
glacier | -0.058 |
LDL | -0.053 |
nir | -0.052 |
Greenland | -0.049 |
Token | chain |
Token ID | 6333 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
HDL | +0.229 |
glacier | +0.205 |
LDL | +0.185 |
nir | +0.181 |
Greenland | +0.173 |
Neg logit contributions | |
toget | -0.195 |
dere | -0.195 |
ettings | -0.189 |
solicit | -0.188 |
•• | -0.185 |
Token | migration |
Token ID | 13472 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
HDL | +0.145 |
glacier | +0.129 |
LDL | +0.116 |
nir | +0.114 |
uckles | +0.107 |
Neg logit contributions | |
dere | -0.139 |
toget | -0.139 |
ettings | -0.134 |
solicit | -0.134 |
outlaw | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
dere | +0.004 |
toget | +0.004 |
ettings | +0.004 |
solicit | +0.004 |
•• | +0.004 |
Neg logit contributions | |
HDL | -0.005 |
glacier | -0.005 |
LDL | -0.004 |
nir | -0.004 |
Greenland | -0.004 |
Token | Chain |
Token ID | 21853 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
HDL | +0.287 |
glacier | +0.256 |
LDL | +0.233 |
nir | +0.228 |
Greenland | +0.217 |
Neg logit contributions | |
toget | -0.239 |
dere | -0.237 |
ettings | -0.230 |
solicit | -0.228 |
outlaw | -0.225 |
Token | a |
Token ID | 257 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
HDL | +0.059 |
glacier | +0.052 |
LDL | +0.047 |
nir | +0.047 |
uckles | +0.044 |
Neg logit contributions | |
dere | -0.052 |
toget | -0.052 |
ettings | -0.050 |
solicit | -0.050 |
outlaw | -0.049 |
Token | cyber |
Token ID | 10075 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
dere | +0.053 |
toget | +0.053 |
ettings | +0.051 |
solicit | +0.051 |
outlaw | +0.050 |
Neg logit contributions | |
HDL | -0.074 |
glacier | -0.067 |
LDL | -0.061 |
nir | -0.060 |
uckles | -0.057 |
Token | attack |
Token ID | 1368 |
Feature activation | +9.88e-02 |
Pos logit contributions | |
toget | +0.031 |
dere | +0.031 |
ettings | +0.030 |
solicit | +0.029 |
•• | +0.029 |
Neg logit contributions | |
HDL | -0.043 |
glacier | -0.039 |
LDL | -0.036 |
nir | -0.035 |
Greenland | -0.034 |
Token | on |
Token ID | 319 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
dere | +0.062 |
toget | +0.062 |
solicit | +0.060 |
ettings | +0.060 |
outlaw | +0.059 |
Neg logit contributions | |
HDL | -0.083 |
glacier | -0.074 |
LDL | -0.068 |
nir | -0.067 |
uckles | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
HDL | +0.085 |
glacier | +0.076 |
LDL | +0.068 |
nir | +0.067 |
Greenland | +0.063 |
Neg logit contributions | |
dere | -0.076 |
toget | -0.076 |
ettings | -0.073 |
solicit | -0.073 |
outlaw | -0.072 |
Token | firm |
Token ID | 4081 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
HDL | +0.052 |
glacier | +0.047 |
LDL | +0.042 |
nir | +0.041 |
Greenland | +0.039 |
Neg logit contributions | |
toget | -0.046 |
dere | -0.046 |
ettings | -0.044 |
solicit | -0.044 |
•• | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
HDL | +0.299 |
glacier | +0.269 |
LDL | +0.244 |
nir | +0.240 |
Esk | +0.228 |
Neg logit contributions | |
dere | -0.239 |
toget | -0.239 |
ettings | -0.231 |
solicit | -0.229 |
•• | -0.226 |
Token | Google |
Token ID | 3012 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
HDL | +0.338 |
glacier | +0.302 |
LDL | +0.273 |
nir | +0.268 |
Greenland | +0.255 |
Neg logit contributions | |
toget | -0.291 |
dere | -0.291 |
ettings | -0.281 |
solicit | -0.279 |
outlaw | -0.275 |
Token | threatened |
Token ID | 8556 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
HDL | +0.566 |
glacier | +0.508 |
LDL | +0.455 |
nir | +0.451 |
Greenland | +0.429 |
Neg logit contributions | |
dere | -0.488 |
toget | -0.487 |
ettings | -0.473 |
solicit | -0.465 |
•• | -0.462 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
dere | +0.226 |
toget | +0.226 |
ettings | +0.218 |
solicit | +0.217 |
outlaw | +0.214 |
Neg logit contributions | |
HDL | -0.272 |
glacier | -0.244 |
LDL | -0.220 |
nir | -0.217 |
Greenland | -0.206 |
Token | withdraw |
Token ID | 8399 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
HDL | +0.214 |
glacier | +0.195 |
LDL | +0.175 |
nir | +0.173 |
Esk | +0.166 |
Neg logit contributions | |
toget | -0.154 |
dere | -0.152 |
ettings | -0.150 |
•• | -0.146 |
solicit | -0.143 |
Token | for |
Token ID | 329 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
HDL | +0.499 |
glacier | +0.448 |
LDL | +0.404 |
nir | +0.398 |
Greenland | +0.378 |
Neg logit contributions | |
dere | -0.414 |
toget | -0.412 |
ettings | -0.400 |
solicit | -0.397 |
•• | -0.395 |
Token | the |
Token ID | 262 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
HDL | +0.254 |
glacier | +0.227 |
LDL | +0.204 |
nir | +0.200 |
Esk | +0.190 |
Neg logit contributions | |
dere | -0.230 |
toget | -0.229 |
ettings | -0.223 |
solicit | -0.221 |
•• | -0.219 |
Token | TC |
Token ID | 17283 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
HDL | +0.362 |
glacier | +0.326 |
LDL | +0.296 |
nir | +0.289 |
Esk | +0.277 |
Neg logit contributions | |
dere | -0.277 |
toget | -0.276 |
ettings | -0.269 |
solicit | -0.265 |
•• | -0.263 |
Token | button |
Token ID | 4936 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
dere | +0.406 |
toget | +0.406 |
ettings | +0.392 |
solicit | +0.389 |
•• | +0.385 |
Neg logit contributions | |
HDL | -0.503 |
glacier | -0.451 |
LDL | -0.408 |
nir | -0.403 |
Greenland | -0.382 |
Token | and |
Token ID | 290 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
HDL | +0.984 |
glacier | +0.885 |
LDL | +0.800 |
nir | +0.789 |
uckles | +0.748 |
Neg logit contributions | |
dere | -0.796 |
toget | -0.793 |
ettings | -0.771 |
solicit | -0.762 |
•• | -0.758 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
HDL | +0.163 |
glacier | +0.145 |
LDL | +0.131 |
nir | +0.129 |
Esk | +0.122 |
Neg logit contributions | |
dere | -0.143 |
toget | -0.142 |
ettings | -0.138 |
solicit | -0.137 |
•• | -0.136 |
Token | other |
Token ID | 584 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
HDL | +0.200 |
glacier | +0.179 |
LDL | +0.162 |
nir | +0.159 |
Esk | +0.151 |
Neg logit contributions | |
dere | -0.162 |
toget | -0.162 |
ettings | -0.157 |
solicit | -0.155 |
•• | -0.154 |
Token | cigarette |
Token ID | 17779 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
dere | +0.233 |
toget | +0.232 |
ettings | +0.225 |
solicit | +0.223 |
•• | +0.220 |
Neg logit contributions | |
HDL | -0.313 |
glacier | -0.282 |
LDL | -0.256 |
nir | -0.252 |
Esk | -0.240 |
Token | lighter |
Token ID | 14871 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
dere | +0.549 |
toget | +0.549 |
ettings | +0.535 |
solicit | +0.533 |
outlaw | +0.528 |
Neg logit contributions | |
HDL | -0.352 |
glacier | -0.301 |
LDL | -0.258 |
nir | -0.253 |
Greenland | -0.233 |
Token | And |
Token ID | 1870 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
HDL | +0.345 |
glacier | +0.309 |
LDL | +0.280 |
nir | +0.275 |
uckles | +0.261 |
Neg logit contributions | |
dere | -0.282 |
toget | -0.281 |
ettings | -0.273 |
solicit | -0.271 |
•• | -0.268 |
Token | here |
Token ID | 994 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
HDL | +0.447 |
glacier | +0.403 |
LDL | +0.364 |
nir | +0.361 |
Esk | +0.341 |
Neg logit contributions | |
dere | -0.352 |
toget | -0.350 |
ettings | -0.341 |
solicit | -0.337 |
•• | -0.334 |
Token | his |
Token ID | 465 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
dere | +0.089 |
toget | +0.089 |
ettings | +0.086 |
solicit | +0.086 |
outlaw | +0.085 |
Neg logit contributions | |
HDL | -0.101 |
glacier | -0.090 |
LDL | -0.081 |
nir | -0.080 |
Greenland | -0.076 |
Token | opponents |
Token ID | 7691 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
toget | +0.116 |
dere | +0.116 |
ettings | +0.112 |
solicit | +0.111 |
•• | +0.110 |
Neg logit contributions | |
HDL | -0.136 |
glacier | -0.122 |
LDL | -0.110 |
nir | -0.108 |
Greenland | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
HDL | +0.066 |
glacier | +0.060 |
LDL | +0.053 |
nir | +0.053 |
Greenland | +0.050 |
Neg logit contributions | |
dere | -0.058 |
toget | -0.058 |
ettings | -0.056 |
solicit | -0.056 |
WARN | -0.055 |
Token | Social |
Token ID | 5483 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
toget | +0.090 |
dere | +0.089 |
ettings | +0.086 |
solicit | +0.085 |
outlaw | +0.084 |
Neg logit contributions | |
HDL | -0.104 |
glacier | -0.092 |
LDL | -0.084 |
nir | -0.082 |
Esk | -0.079 |
Token | movements |
Token ID | 8650 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
toget | +0.072 |
dere | +0.072 |
ettings | +0.069 |
solicit | +0.069 |
•• | +0.068 |
Neg logit contributions | |
HDL | -0.088 |
glacier | -0.079 |
LDL | -0.072 |
nir | -0.071 |
Greenland | -0.067 |
Token | are |
Token ID | 389 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
HDL | +0.040 |
glacier | +0.036 |
LDL | +0.032 |
nir | +0.032 |
Greenland | +0.030 |
Neg logit contributions | |
toget | -0.033 |
dere | -0.033 |
ettings | -0.032 |
solicit | -0.032 |
•• | -0.032 |
Token | back |
Token ID | 736 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
HDL | +0.080 |
glacier | +0.072 |
LDL | +0.065 |
nir | +0.064 |
Greenland | +0.060 |
Neg logit contributions | |
toget | -0.068 |
dere | -0.068 |
ettings | -0.066 |
solicit | -0.065 |
•• | -0.064 |
Token | in |
Token ID | 287 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
HDL | +0.028 |
glacier | +0.025 |
LDL | +0.022 |
nir | +0.022 |
Greenland | +0.021 |
Neg logit contributions | |
dere | -0.022 |
toget | -0.022 |
ettings | -0.021 |
solicit | -0.021 |
outlaw | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
HDL | +0.144 |
glacier | +0.130 |
LDL | +0.116 |
nir | +0.113 |
Greenland | +0.109 |
Neg logit contributions | |
toget | -0.131 |
dere | -0.130 |
ettings | -0.127 |
solicit | -0.125 |
WARN | -0.124 |
Token | streets |
Token ID | 6483 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
HDL | +0.031 |
glacier | +0.028 |
LDL | +0.025 |
nir | +0.025 |
Greenland | +0.024 |
Neg logit contributions | |
toget | -0.025 |
dere | -0.025 |
ettings | -0.025 |
solicit | -0.024 |
WARN | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
dere | +0.140 |
toget | +0.139 |
ettings | +0.135 |
solicit | +0.134 |
WARN | +0.132 |
Neg logit contributions | |
HDL | -0.175 |
glacier | -0.157 |
LDL | -0.142 |
nir | -0.140 |
Greenland | -0.133 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
dere | +0.259 |
toget | +0.258 |
ettings | +0.250 |
solicit | +0.250 |
outlaw | +0.246 |
Neg logit contributions | |
HDL | -0.263 |
glacier | -0.234 |
LDL | -0.210 |
nir | -0.207 |
uckles | -0.195 |
Token | loop |
Token ID | 9052 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
HDL | +0.096 |
glacier | +0.087 |
LDL | +0.078 |
nir | +0.077 |
uckles | +0.073 |
Neg logit contributions | |
dere | -0.078 |
toget | -0.078 |
ettings | -0.075 |
solicit | -0.075 |
outlaw | -0.074 |
Token | from |
Token ID | 422 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
HDL | +0.292 |
glacier | +0.263 |
LDL | +0.238 |
nir | +0.235 |
Esk | +0.223 |
Neg logit contributions | |
toget | -0.224 |
dere | -0.223 |
ettings | -0.217 |
solicit | -0.214 |
•• | -0.213 |
Token | some |
Token ID | 617 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
toget | +0.020 |
dere | +0.020 |
ettings | +0.019 |
solicit | +0.019 |
•• | +0.019 |
Neg logit contributions | |
HDL | -0.023 |
glacier | -0.020 |
LDL | -0.018 |
nir | -0.018 |
Greenland | -0.017 |
Token | RG |
Token ID | 34359 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
HDL | +0.704 |
glacier | +0.632 |
LDL | +0.574 |
nir | +0.560 |
Esk | +0.539 |
Neg logit contributions | |
toget | -0.531 |
dere | -0.523 |
ettings | -0.513 |
solicit | -0.506 |
•• | -0.505 |
Token | 58 |
Token ID | 3365 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
dere | +0.761 |
toget | +0.758 |
ettings | +0.731 |
solicit | +0.729 |
outlaw | +0.719 |
Neg logit contributions | |
HDL | -0.958 |
glacier | -0.863 |
LDL | -0.781 |
nir | -0.771 |
Greenland | -0.732 |
Token | coax |
Token ID | 37700 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
HDL | +0.466 |
glacier | +0.417 |
LDL | +0.377 |
nir | +0.372 |
Esk | +0.352 |
Neg logit contributions | |
toget | -0.390 |
dere | -0.390 |
ettings | -0.378 |
solicit | -0.375 |
•• | -0.371 |
Token | by |
Token ID | 416 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
dere | +0.270 |
toget | +0.269 |
ettings | +0.259 |
solicit | +0.259 |
outlaw | +0.255 |
Neg logit contributions | |
HDL | -0.340 |
glacier | -0.305 |
LDL | -0.277 |
nir | -0.272 |
Greenland | -0.259 |
Token | stripping |
Token ID | 37727 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
toget | +0.009 |
dere | +0.009 |
ettings | +0.009 |
solicit | +0.009 |
•• | +0.009 |
Neg logit contributions | |
HDL | -0.011 |
glacier | -0.010 |
LDL | -0.009 |
nir | -0.009 |
Greenland | -0.008 |
Token | back |
Token ID | 736 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
dere | +0.170 |
toget | +0.169 |
ettings | +0.163 |
solicit | +0.163 |
outlaw | +0.161 |
Neg logit contributions | |
HDL | -0.202 |
glacier | -0.181 |
LDL | -0.163 |
nir | -0.161 |
Greenland | -0.153 |
Token | the |
Token ID | 262 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
HDL | +0.141 |
glacier | +0.126 |
LDL | +0.113 |
nir | +0.111 |
Greenland | +0.105 |
Neg logit contributions | |
dere | -0.127 |
toget | -0.127 |
ettings | -0.123 |
solicit | -0.122 |
outlaw | -0.121 |
Token | onym |
Token ID | 5177 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
HDL | +0.021 |
glacier | +0.019 |
LDL | +0.017 |
nir | +0.017 |
Greenland | +0.016 |
Neg logit contributions | |
dere | -0.013 |
toget | -0.013 |
ettings | -0.013 |
solicit | -0.013 |
outlaw | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
dere | +0.223 |
toget | +0.223 |
ettings | +0.215 |
solicit | +0.213 |
outlaw | +0.210 |
Neg logit contributions | |
HDL | -0.331 |
glacier | -0.300 |
LDL | -0.273 |
nir | -0.270 |
Greenland | -0.257 |
Token | my |
Token ID | 616 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
toget | +0.074 |
dere | +0.073 |
ettings | +0.072 |
solicit | +0.071 |
•• | +0.070 |
Neg logit contributions | |
HDL | -0.095 |
glacier | -0.086 |
LDL | -0.077 |
nir | -0.076 |
Greenland | -0.073 |
Token | country |
Token ID | 1499 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
toget | +0.381 |
dere | +0.380 |
ettings | +0.368 |
solicit | +0.366 |
outlaw | +0.361 |
Neg logit contributions | |
HDL | -0.444 |
glacier | -0.398 |
LDL | -0.358 |
nir | -0.353 |
Greenland | -0.335 |
Token | � |
Token ID | 447 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
HDL | +0.097 |
glacier | +0.087 |
LDL | +0.079 |
nir | +0.078 |
Greenland | +0.074 |
Neg logit contributions | |
toget | -0.082 |
dere | -0.082 |
ettings | -0.079 |
solicit | -0.079 |
•• | -0.077 |
Token | � |
Token ID | 247 |
Feature activation | +7.89e-03 |
Pos logit contributions | |
dere | +0.036 |
toget | +0.036 |
ettings | +0.035 |
solicit | +0.035 |
•• | +0.034 |
Neg logit contributions | |
HDL | -0.029 |
glacier | -0.025 |
LDL | -0.022 |
nir | -0.022 |
Esk | -0.020 |
Token | s |
Token ID | 82 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
dere | +0.006 |
toget | +0.006 |
ettings | +0.005 |
solicit | +0.005 |
outlaw | +0.005 |
Neg logit contributions | |
HDL | -0.006 |
glacier | -0.005 |
LDL | -0.005 |
nir | -0.005 |
Greenland | -0.004 |
Token | dark |
Token ID | 3223 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
HDL | +0.175 |
glacier | +0.159 |
LDL | +0.144 |
nir | +0.142 |
Esk | +0.136 |
Neg logit contributions | |
toget | -0.130 |
dere | -0.129 |
ettings | -0.127 |
solicit | -0.125 |
•• | -0.124 |
Token | past |
Token ID | 1613 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
toget | +0.075 |
dere | +0.074 |
ettings | +0.072 |
solicit | +0.071 |
WARN | +0.070 |
Neg logit contributions | |
HDL | -0.098 |
glacier | -0.089 |
LDL | -0.081 |
nir | -0.080 |
Greenland | -0.076 |
Token | ? |
Token ID | 30 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
dere | +0.090 |
toget | +0.090 |
ettings | +0.087 |
solicit | +0.086 |
outlaw | +0.085 |
Neg logit contributions | |
HDL | -0.090 |
glacier | -0.080 |
LDL | -0.071 |
nir | -0.070 |
Greenland | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
toget | +0.167 |
dere | +0.165 |
ettings | +0.161 |
solicit | +0.159 |
outlaw | +0.157 |
Neg logit contributions | |
HDL | -0.190 |
glacier | -0.169 |
LDL | -0.153 |
nir | -0.150 |
Greenland | -0.144 |
Token | call |
Token ID | 869 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
HDL | +0.152 |
glacier | +0.138 |
LDL | +0.124 |
nir | +0.122 |
Esk | +0.117 |
Neg logit contributions | |
toget | -0.120 |
dere | -0.119 |
ettings | -0.115 |
solicit | -0.114 |
•• | -0.113 |
Token | sign |
Token ID | 1051 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
dere | +0.325 |
toget | +0.324 |
ettings | +0.313 |
solicit | +0.312 |
outlaw | +0.307 |
Neg logit contributions | |
HDL | -0.403 |
glacier | -0.362 |
LDL | -0.328 |
nir | -0.324 |
Greenland | -0.307 |
Token | , |
Token ID | 11 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
HDL | +0.657 |
glacier | +0.591 |
LDL | +0.534 |
nir | +0.526 |
Greenland | +0.499 |
Neg logit contributions | |
toget | -0.535 |
dere | -0.534 |
ettings | -0.516 |
solicit | -0.512 |
•• | -0.506 |
Token | no |
Token ID | 645 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
toget | +0.029 |
dere | +0.029 |
ettings | +0.028 |
solicit | +0.027 |
•• | +0.027 |
Neg logit contributions | |
HDL | -0.057 |
glacier | -0.052 |
LDL | -0.048 |
nir | -0.047 |
Greenland | -0.046 |
Token | add |
Token ID | 751 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
HDL | +0.167 |
glacier | +0.150 |
LDL | +0.137 |
nir | +0.133 |
Esk | +0.128 |
Neg logit contributions | |
toget | -0.128 |
dere | -0.127 |
ettings | -0.124 |
solicit | -0.121 |
•• | -0.121 |
Token | res |
Token ID | 411 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
dere | +0.236 |
toget | +0.235 |
ettings | +0.226 |
solicit | +0.224 |
outlaw | +0.220 |
Neg logit contributions | |
HDL | -0.411 |
glacier | -0.374 |
LDL | -0.344 |
nir | -0.339 |
Greenland | -0.325 |
Token | see |
Token ID | 3826 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
HDL | +0.979 |
glacier | +0.860 |
LDL | +0.753 |
nir | +0.747 |
Greenland | +0.696 |
Neg logit contributions | |
toget | -1.187 |
dere | -1.183 |
ettings | -1.147 |
solicit | -1.143 |
•• | -1.140 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
toget | +0.081 |
dere | +0.081 |
ettings | +0.079 |
solicit | +0.078 |
•• | +0.077 |
Neg logit contributions | |
HDL | -0.101 |
glacier | -0.091 |
LDL | -0.082 |
nir | -0.081 |
Greenland | -0.077 |
Token | just |
Token ID | 655 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
toget | +0.112 |
dere | +0.111 |
ettings | +0.107 |
solicit | +0.106 |
•• | +0.104 |
Neg logit contributions | |
HDL | -0.197 |
glacier | -0.180 |
LDL | -0.165 |
nir | -0.163 |
Greenland | -0.156 |
Token | panic |
Token ID | 13619 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
HDL | +0.210 |
glacier | +0.188 |
LDL | +0.170 |
nir | +0.167 |
Greenland | +0.159 |
Neg logit contributions | |
toget | -0.176 |
dere | -0.175 |
ettings | -0.170 |
solicit | -0.168 |
•• | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
HDL | +0.115 |
glacier | +0.104 |
LDL | +0.094 |
nir | +0.092 |
Greenland | +0.087 |
Neg logit contributions | |
toget | -0.096 |
dere | -0.096 |
ettings | -0.093 |
solicit | -0.092 |
•• | -0.091 |
Token | not |
Token ID | 407 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
HDL | +0.910 |
glacier | +0.817 |
LDL | +0.736 |
nir | +0.724 |
Esk | +0.688 |
Neg logit contributions | |
dere | -0.774 |
toget | -0.773 |
ettings | -0.751 |
solicit | -0.743 |
•• | -0.734 |
Token | to |
Token ID | 284 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
HDL | +0.091 |
glacier | +0.081 |
LDL | +0.073 |
nir | +0.072 |
uckles | +0.069 |
Neg logit contributions | |
toget | -0.078 |
dere | -0.078 |
ettings | -0.075 |
solicit | -0.075 |
outlaw | -0.074 |
Token | have |
Token ID | 423 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
HDL | +0.147 |
glacier | +0.133 |
LDL | +0.120 |
nir | +0.118 |
Greenland | +0.112 |
Neg logit contributions | |
toget | -0.115 |
dere | -0.114 |
ettings | -0.112 |
•• | -0.110 |
solicit | -0.108 |
Token | pre |
Token ID | 662 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
HDL | +0.165 |
glacier | +0.149 |
LDL | +0.135 |
nir | +0.132 |
Greenland | +0.126 |
Neg logit contributions | |
toget | -0.134 |
dere | -0.134 |
ettings | -0.130 |
solicit | -0.129 |
•• | -0.127 |
Token | mar |
Token ID | 3876 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
HDL | +0.100 |
glacier | +0.088 |
LDL | +0.078 |
nir | +0.077 |
Greenland | +0.072 |
Neg logit contributions | |
toget | -0.113 |
dere | -0.113 |
ettings | -0.109 |
solicit | -0.109 |
outlaw | -0.108 |
Token | ital |
Token ID | 1287 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
HDL | +0.361 |
glacier | +0.307 |
LDL | +0.262 |
nir | +0.256 |
Greenland | +0.234 |
Neg logit contributions | |
dere | -0.595 |
toget | -0.595 |
ettings | -0.580 |
solicit | -0.578 |
outlaw | -0.572 |
Token | sex |
Token ID | 1714 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
HDL | +0.976 |
glacier | +0.869 |
LDL | +0.781 |
nir | +0.755 |
Esk | +0.724 |
Neg logit contributions | |
toget | -0.932 |
dere | -0.917 |
ettings | -0.899 |
•• | -0.883 |
WARN | -0.881 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
HDL | +0.105 |
glacier | +0.094 |
LDL | +0.085 |
nir | +0.083 |
uckles | +0.079 |
Neg logit contributions | |
dere | -0.089 |
toget | -0.089 |
ettings | -0.086 |
solicit | -0.086 |
•• | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
HDL | +0.122 |
glacier | +0.108 |
LDL | +0.099 |
nir | +0.097 |
Greenland | +0.092 |
Neg logit contributions | |
toget | -0.106 |
dere | -0.105 |
ettings | -0.102 |
solicit | -0.101 |
outlaw | -0.100 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
HDL | +0.106 |
glacier | +0.095 |
LDL | +0.086 |
nir | +0.084 |
Greenland | +0.080 |
Neg logit contributions | |
toget | -0.093 |
dere | -0.093 |
ettings | -0.090 |
solicit | -0.089 |
outlaw | -0.088 |
Token | She |
Token ID | 3347 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
HDL | +0.083 |
glacier | +0.075 |
LDL | +0.068 |
nir | +0.067 |
Greenland | +0.063 |
Neg logit contributions | |
dere | -0.069 |
toget | -0.069 |
ettings | -0.067 |
solicit | -0.066 |
outlaw | -0.065 |
Token | Gos |
Token ID | 30007 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
HDL | +0.114 |
glacier | +0.103 |
LDL | +0.094 |
nir | +0.092 |
Greenland | +0.089 |
Neg logit contributions | |
toget | -0.087 |
dere | -0.086 |
ettings | -0.083 |
solicit | -0.083 |
•• | -0.081 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
HDL | +0.568 |
glacier | +0.498 |
LDL | +0.447 |
nir | +0.436 |
Greenland | +0.413 |
Neg logit contributions | |
dere | -0.590 |
toget | -0.582 |
ettings | -0.572 |
solicit | -0.569 |
outlaw | -0.560 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
HDL | +0.901 |
glacier | +0.811 |
LDL | +0.736 |
nir | +0.726 |
Greenland | +0.692 |
Neg logit contributions | |
toget | -0.684 |
dere | -0.682 |
ettings | -0.659 |
solicit | -0.652 |
WARN | -0.644 |
Token | Alex |
Token ID | 4422 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
toget | +0.074 |
dere | +0.074 |
ettings | +0.072 |
solicit | +0.071 |
outlaw | +0.070 |
Neg logit contributions | |
HDL | -0.085 |
glacier | -0.076 |
LDL | -0.069 |
nir | -0.067 |
Greenland | -0.064 |
Token | Petty |
Token ID | 41505 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
HDL | +0.108 |
glacier | +0.097 |
LDL | +0.087 |
nir | +0.086 |
Esk | +0.083 |
Neg logit contributions | |
toget | -0.095 |
dere | -0.092 |
ettings | -0.090 |
solicit | -0.089 |
outlaw | -0.089 |
Token | fer |
Token ID | 2232 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
HDL | +0.142 |
glacier | +0.128 |
LDL | +0.116 |
nir | +0.115 |
Greenland | +0.109 |
Neg logit contributions | |
toget | -0.107 |
dere | -0.106 |
ettings | -0.103 |
solicit | -0.102 |
outlaw | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
HDL | +1.098 |
glacier | +0.990 |
LDL | +0.896 |
nir | +0.892 |
Greenland | +0.845 |
Neg logit contributions | |
toget | -0.851 |
dere | -0.845 |
ettings | -0.815 |
solicit | -0.806 |
WARN | -0.800 |
Token | Stephen |
Token ID | 7970 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
toget | +0.108 |
dere | +0.108 |
ettings | +0.104 |
solicit | +0.104 |
outlaw | +0.102 |
Neg logit contributions | |
HDL | -0.123 |
glacier | -0.111 |
LDL | -0.100 |
nir | -0.098 |
Greenland | -0.093 |
Token | Am |
Token ID | 1703 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
HDL | +0.162 |
glacier | +0.145 |
LDL | +0.132 |
nir | +0.130 |
Esk | +0.125 |
Neg logit contributions | |
toget | -0.133 |
dere | -0.131 |
ettings | -0.128 |
solicit | -0.126 |
outlaw | -0.125 |
Token | ell |
Token ID | 695 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
HDL | +0.550 |
glacier | +0.489 |
LDL | +0.439 |
nir | +0.435 |
uckles | +0.411 |
Neg logit contributions | |
toget | -0.534 |
dere | -0.526 |
ettings | -0.509 |
solicit | -0.507 |
WARN | -0.506 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
HDL | +0.878 |
glacier | +0.792 |
LDL | +0.718 |
nir | +0.707 |
uckles | +0.675 |
Neg logit contributions | |
toget | -0.670 |
dere | -0.667 |
ettings | -0.644 |
solicit | -0.639 |
WARN | -0.631 |
Token | , |
Token ID | 11 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
HDL | +0.423 |
glacier | +0.379 |
LDL | +0.342 |
nir | +0.339 |
Greenland | +0.321 |
Neg logit contributions | |
dere | -0.332 |
toget | -0.331 |
solicit | -0.316 |
ettings | -0.315 |
outlaw | -0.312 |
Token | tim |
Token ID | 4628 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
toget | +0.025 |
dere | +0.024 |
ettings | +0.024 |
solicit | +0.023 |
•• | +0.023 |
Neg logit contributions | |
HDL | -0.031 |
glacier | -0.028 |
LDL | -0.026 |
nir | -0.025 |
Greenland | -0.024 |
Token | est |
Token ID | 395 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
toget | +0.068 |
dere | +0.067 |
ettings | +0.065 |
solicit | +0.064 |
•• | +0.064 |
Neg logit contributions | |
HDL | -0.078 |
glacier | -0.069 |
LDL | -0.063 |
nir | -0.062 |
uckles | -0.059 |
Token | retch |
Token ID | 22592 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
HDL | +0.221 |
glacier | +0.201 |
LDL | +0.183 |
nir | +0.182 |
uckles | +0.174 |
Neg logit contributions | |
dere | -0.142 |
toget | -0.142 |
ettings | -0.135 |
solicit | -0.135 |
outlaw | -0.133 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
HDL | +0.720 |
glacier | +0.643 |
LDL | +0.583 |
nir | +0.578 |
uckles | +0.545 |
Neg logit contributions | |
toget | -0.567 |
dere | -0.566 |
ettings | -0.542 |
solicit | -0.537 |
WARN | -0.533 |
Token | ripple |
Token ID | 42462 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
toget | +0.029 |
dere | +0.029 |
ettings | +0.028 |
solicit | +0.027 |
•• | +0.027 |
Neg logit contributions | |
HDL | -0.036 |
glacier | -0.033 |
LDL | -0.030 |
nir | -0.029 |
Greenland | -0.028 |
Token | edit |
Token ID | 4370 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
HDL | +1.324 |
glacier | +1.181 |
LDL | +1.068 |
nir | +1.057 |
Greenland | +0.994 |
Neg logit contributions | |
toget | -1.059 |
dere | -1.047 |
ettings | -1.013 |
solicit | -0.993 |
outlaw | -0.991 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
toget | +0.122 |
dere | +0.122 |
ettings | +0.117 |
solicit | +0.117 |
outlaw | +0.115 |
Neg logit contributions | |
HDL | -0.163 |
glacier | -0.147 |
LDL | -0.134 |
nir | -0.132 |
uckles | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
toget | +0.069 |
dere | +0.069 |
ettings | +0.066 |
solicit | +0.066 |
•• | +0.065 |
Neg logit contributions | |
HDL | -0.088 |
glacier | -0.079 |
LDL | -0.071 |
nir | -0.070 |
Greenland | -0.067 |
Token | more |
Token ID | 517 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
HDL | +0.196 |
glacier | +0.176 |
LDL | +0.159 |
nir | +0.156 |
Greenland | +0.149 |
Neg logit contributions | |
toget | -0.155 |
dere | -0.154 |
ettings | -0.149 |
solicit | -0.148 |
•• | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
dere | +0.011 |
toget | +0.011 |
ettings | +0.010 |
solicit | +0.010 |
outlaw | +0.010 |
Neg logit contributions | |
HDL | -0.012 |
glacier | -0.011 |
LDL | -0.010 |
nir | -0.009 |
Greenland | -0.009 |
Token | problem |
Token ID | 1917 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
dere | +0.368 |
toget | +0.368 |
ettings | +0.353 |
solicit | +0.350 |
outlaw | +0.344 |
Neg logit contributions | |
HDL | -0.632 |
glacier | -0.575 |
LDL | -0.528 |
nir | -0.522 |
Greenland | -0.499 |
Token | and |
Token ID | 290 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
HDL | +0.127 |
glacier | +0.114 |
LDL | +0.103 |
nir | +0.102 |
Greenland | +0.097 |
Neg logit contributions | |
toget | -0.099 |
dere | -0.099 |
ettings | -0.096 |
solicit | -0.095 |
outlaw | -0.094 |
Token | received |
Token ID | 2722 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
HDL | +0.193 |
glacier | +0.173 |
LDL | +0.156 |
nir | +0.152 |
Greenland | +0.145 |
Neg logit contributions | |
toget | -0.172 |
dere | -0.171 |
ettings | -0.166 |
solicit | -0.164 |
•• | -0.163 |
Token | treatment |
Token ID | 3513 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
HDL | +0.601 |
glacier | +0.538 |
LDL | +0.486 |
nir | +0.473 |
Greenland | +0.453 |
Neg logit contributions | |
toget | -0.510 |
dere | -0.509 |
ettings | -0.498 |
solicit | -0.488 |
outlaw | -0.484 |
Token | in |
Token ID | 287 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
HDL | +0.608 |
glacier | +0.548 |
LDL | +0.496 |
nir | +0.485 |
Greenland | +0.466 |
Neg logit contributions | |
dere | -0.479 |
toget | -0.477 |
ettings | -0.465 |
solicit | -0.457 |
WARN | -0.454 |
Token | England |
Token ID | 4492 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
HDL | +0.194 |
glacier | +0.172 |
LDL | +0.153 |
nir | +0.149 |
Esk | +0.142 |
Neg logit contributions | |
toget | -0.205 |
dere | -0.204 |
ettings | -0.199 |
solicit | -0.197 |
•• | -0.195 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
HDL | +1.068 |
glacier | +0.962 |
LDL | +0.868 |
nir | +0.845 |
Greenland | +0.816 |
Neg logit contributions | |
toget | -0.858 |
dere | -0.854 |
ettings | -0.832 |
solicit | -0.819 |
WARN | -0.808 |
Token | he |
Token ID | 339 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
HDL | +0.089 |
glacier | +0.079 |
LDL | +0.071 |
nir | +0.070 |
Greenland | +0.066 |
Neg logit contributions | |
toget | -0.082 |
dere | -0.081 |
ettings | -0.079 |
solicit | -0.078 |
•• | -0.078 |
Token | said |
Token ID | 531 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
HDL | +0.526 |
glacier | +0.471 |
LDL | +0.416 |
nir | +0.409 |
uckles | +0.389 |
Neg logit contributions | |
dere | -0.533 |
toget | -0.533 |
ettings | -0.521 |
solicit | -0.513 |
•• | -0.508 |
Token | of |
Token ID | 286 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
HDL | +0.176 |
glacier | +0.156 |
LDL | +0.140 |
nir | +0.138 |
uckles | +0.130 |
Neg logit contributions | |
dere | -0.172 |
toget | -0.172 |
ettings | -0.166 |
solicit | -0.166 |
outlaw | -0.164 |
Token | NHS |
Token ID | 18183 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
HDL | +0.093 |
glacier | +0.082 |
LDL | +0.073 |
nir | +0.073 |
uckles | +0.068 |
Neg logit contributions | |
dere | -0.097 |
toget | -0.097 |
solicit | -0.094 |
ettings | -0.094 |
outlaw | -0.093 |