Token |
|
Token ID | 198 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
ping | +0.089 |
cks | +0.089 |
opes | +0.088 |
necks | +0.087 |
aron | +0.087 |
Neg logit contributions | |
t | -0.105 |
happened | -0.101 |
help | -0.098 |
please | -0.097 |
day | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
t | +0.019 |
happened | +0.019 |
help | +0.018 |
day | +0.018 |
reward | +0.017 |
Neg logit contributions | |
cks | -0.021 |
aron | -0.020 |
uted | -0.020 |
necks | -0.020 |
opes | -0.020 |
Token | But |
Token ID | 1537 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
happened | +0.019 |
t | +0.019 |
help | +0.018 |
day | +0.018 |
awaited | +0.017 |
Neg logit contributions | |
cks | -0.021 |
necks | -0.021 |
aron | -0.021 |
uted | -0.021 |
valleys | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
necks | +0.301 |
cks | +0.293 |
valleys | +0.290 |
ears | +0.281 |
neck | +0.280 |
Neg logit contributions | |
t | -0.298 |
awaited | -0.268 |
happened | -0.265 |
ha | -0.261 |
va | -0.255 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
necks | +0.045 |
cks | +0.044 |
ping | +0.043 |
valleys | +0.043 |
opes | +0.043 |
Neg logit contributions | |
t | -0.048 |
happened | -0.045 |
awaited | -0.043 |
please | -0.043 |
help | -0.042 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.56e+01 |
Pos logit contributions | |
rily | +0.078 |
valleys | +0.074 |
aron | +0.071 |
uted | +0.068 |
necks | +0.066 |
Neg logit contributions | |
t | -0.338 |
happened | -0.323 |
day | -0.317 |
help | -0.313 |
week | -0.310 |
Token | hes |
Token ID | 956 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
necks | +0.861 |
aters | +0.857 |
valleys | +0.818 |
opes | +0.817 |
aron | +0.816 |
Neg logit contributions | |
t | -1.841 |
happened | -1.779 |
day | -1.697 |
help | -1.687 |
please | -1.662 |
Token | did |
Token ID | 750 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
rily | +0.381 |
aron | +0.379 |
ping | +0.379 |
cks | +0.378 |
uted | +0.378 |
Neg logit contributions | |
t | -0.215 |
happened | -0.204 |
help | -0.203 |
awaited | -0.202 |
week | -0.196 |
Token | not |
Token ID | 407 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
t | +0.202 |
happened | +0.187 |
help | +0.181 |
please | +0.174 |
day | +0.172 |
Neg logit contributions | |
aron | -0.487 |
opes | -0.486 |
necks | -0.485 |
ping | -0.484 |
valleys | -0.484 |
Token | like |
Token ID | 588 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
aron | +0.080 |
cks | +0.079 |
ping | +0.078 |
necks | +0.076 |
uted | +0.074 |
Neg logit contributions | |
t | -0.060 |
happened | -0.058 |
awaited | -0.054 |
week | -0.053 |
day | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
cks | +0.155 |
necks | +0.154 |
ping | +0.153 |
valleys | +0.151 |
opes | +0.151 |
Neg logit contributions | |
t | -0.122 |
happened | -0.110 |
reward | -0.108 |
awaited | -0.106 |
please | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
cks | +0.459 |
ping | +0.445 |
necks | +0.444 |
uted | +0.443 |
aron | +0.441 |
Neg logit contributions | |
t | -0.419 |
week | -0.377 |
happened | -0.377 |
please | -0.376 |
day | -0.374 |
Token | One |
Token ID | 1881 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
cks | +0.099 |
ping | +0.097 |
necks | +0.096 |
uted | +0.096 |
opes | +0.094 |
Neg logit contributions | |
t | -0.094 |
happened | -0.091 |
please | -0.089 |
help | -0.087 |
day | -0.085 |
Token | of |
Token ID | 286 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
valleys | +0.118 |
cks | +0.117 |
ping | +0.116 |
necks | +0.115 |
opes | +0.112 |
Neg logit contributions | |
t | -0.075 |
happened | -0.072 |
please | -0.071 |
awaited | -0.069 |
reward | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
t | +0.244 |
help | +0.242 |
happened | +0.240 |
day | +0.234 |
please | +0.226 |
Neg logit contributions | |
aron | -0.461 |
uted | -0.450 |
opes | -0.449 |
necks | -0.449 |
ping | -0.448 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
necks | +0.041 |
cks | +0.040 |
valleys | +0.039 |
ping | +0.039 |
aron | +0.039 |
Neg logit contributions | |
t | -0.047 |
happened | -0.045 |
please | -0.043 |
help | -0.042 |
awaited | -0.042 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.56e+01 |
Pos logit contributions | |
rily | +0.081 |
aron | +0.074 |
uted | +0.072 |
valleys | +0.069 |
bes | +0.067 |
Neg logit contributions | |
t | -0.332 |
happened | -0.317 |
day | -0.315 |
help | -0.310 |
week | -0.307 |
Token | hes |
Token ID | 956 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
necks | +0.832 |
aters | +0.808 |
aron | +0.802 |
opes | +0.799 |
rily | +0.788 |
Neg logit contributions | |
t | -1.839 |
happened | -1.787 |
day | -1.720 |
help | -1.714 |
please | -1.686 |
Token | looked |
Token ID | 3114 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
ping | +0.367 |
cks | +0.366 |
rily | +0.363 |
uted | +0.362 |
necks | +0.361 |
Neg logit contributions | |
t | -0.223 |
help | -0.208 |
please | -0.205 |
reward | -0.204 |
happened | -0.204 |
Token | different |
Token ID | 1180 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
aters | +0.256 |
aron | +0.255 |
opes | +0.253 |
cks | +0.249 |
bes | +0.248 |
Neg logit contributions | |
happened | -0.167 |
t | -0.162 |
help | -0.159 |
day | -0.156 |
please | -0.154 |
Token | from |
Token ID | 422 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
bes | +0.087 |
cks | +0.085 |
uted | +0.085 |
rily | +0.085 |
aron | +0.084 |
Neg logit contributions | |
day | -0.130 |
happened | -0.130 |
help | -0.127 |
t | -0.124 |
week | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
aron | +0.004 |
uted | +0.004 |
aters | +0.004 |
opes | +0.004 |
cks | +0.004 |
Neg logit contributions | |
help | -0.003 |
happened | -0.003 |
day | -0.003 |
t | -0.003 |
please | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
t | +0.291 |
help | +0.275 |
day | +0.272 |
happened | +0.272 |
please | +0.262 |
Neg logit contributions | |
opes | -0.392 |
cks | -0.385 |
uted | -0.383 |
aters | -0.380 |
valleys | -0.378 |
Token | It |
Token ID | 632 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
opes | +0.096 |
ping | +0.095 |
necks | +0.095 |
cks | +0.095 |
aters | +0.092 |
Neg logit contributions | |
thank | -0.096 |
please | -0.093 |
t | -0.092 |
help | -0.091 |
happened | -0.090 |
Token | sees |
Token ID | 7224 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ping | +0.291 |
opes | +0.290 |
aron | +0.290 |
uted | +0.289 |
cks | +0.289 |
Neg logit contributions | |
t | -0.209 |
happened | -0.206 |
help | -0.202 |
day | -0.197 |
would | -0.194 |
Token | other |
Token ID | 584 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
aron | +0.081 |
necks | +0.080 |
aters | +0.080 |
opes | +0.080 |
cks | +0.080 |
Neg logit contributions | |
happened | -0.057 |
t | -0.057 |
help | -0.054 |
day | -0.053 |
please | -0.052 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
t | +0.368 |
happened | +0.363 |
help | +0.360 |
day | +0.359 |
week | +0.346 |
Neg logit contributions | |
aron | -0.289 |
cks | -0.288 |
rily | -0.288 |
opes | -0.286 |
uted | -0.284 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.55e+01 |
Pos logit contributions | |
rily | +0.093 |
aron | +0.087 |
valleys | +0.085 |
uted | +0.079 |
necks | +0.077 |
Neg logit contributions | |
t | -0.321 |
happened | -0.302 |
day | -0.297 |
help | -0.295 |
week | -0.290 |
Token | hes |
Token ID | 956 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
necks | +0.896 |
aters | +0.883 |
aron | +0.847 |
opes | +0.843 |
rily | +0.832 |
Neg logit contributions | |
t | -1.791 |
happened | -1.744 |
day | -1.674 |
help | -1.669 |
please | -1.635 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
aron | +0.351 |
opes | +0.350 |
necks | +0.350 |
cks | +0.348 |
uted | +0.346 |
Neg logit contributions | |
t | -0.260 |
happened | -0.247 |
help | -0.244 |
day | -0.240 |
please | -0.236 |
Token | It |
Token ID | 632 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
ping | +0.098 |
opes | +0.098 |
necks | +0.098 |
cks | +0.096 |
uted | +0.093 |
Neg logit contributions | |
please | -0.095 |
thank | -0.094 |
t | -0.094 |
help | -0.091 |
happened | -0.091 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
aters | +0.295 |
aron | +0.292 |
ping | +0.292 |
uted | +0.290 |
opes | +0.290 |
Neg logit contributions | |
happened | -0.210 |
t | -0.207 |
help | -0.206 |
would | -0.202 |
day | -0.199 |
Token | new |
Token ID | 649 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
aron | +0.006 |
necks | +0.006 |
opes | +0.006 |
cks | +0.006 |
aters | +0.006 |
Neg logit contributions | |
t | -0.005 |
happened | -0.005 |
help | -0.005 |
day | -0.005 |
please | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
cks | +0.590 |
ping | +0.582 |
opes | +0.582 |
aron | +0.582 |
necks | +0.580 |
Neg logit contributions | |
t | -0.276 |
happened | -0.264 |
help | -0.250 |
day | -0.242 |
please | -0.239 |
Token | to |
Token ID | 284 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
t | +0.001 |
ha | +0.000 |
awaited | +0.000 |
happened | +0.000 |
reward | +0.000 |
Neg logit contributions | |
necks | -0.001 |
ping | -0.001 |
valleys | -0.001 |
cks | -0.001 |
piles | -0.001 |
Token | touch |
Token ID | 3638 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
t | +0.396 |
happened | +0.380 |
awaited | +0.364 |
ha | +0.349 |
week | +0.348 |
Neg logit contributions | |
cks | -0.548 |
necks | -0.546 |
aron | -0.523 |
uted | -0.520 |
opes | -0.518 |
Token | the |
Token ID | 262 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
aron | +0.177 |
opes | +0.176 |
uted | +0.175 |
rily | +0.173 |
ping | +0.173 |
Neg logit contributions | |
help | -0.098 |
happened | -0.097 |
day | -0.096 |
t | -0.096 |
please | -0.092 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
aron | +0.038 |
cks | +0.038 |
uted | +0.038 |
rily | +0.038 |
opes | +0.037 |
Neg logit contributions | |
t | -0.045 |
happened | -0.044 |
help | -0.043 |
day | -0.043 |
week | -0.041 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.55e+01 |
Pos logit contributions | |
rily | +0.094 |
valleys | +0.088 |
aron | +0.085 |
efully | +0.079 |
uted | +0.078 |
Neg logit contributions | |
t | -0.315 |
day | -0.296 |
happened | -0.293 |
help | -0.289 |
week | -0.287 |
Token | hes |
Token ID | 956 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
necks | +0.783 |
aron | +0.764 |
opes | +0.761 |
cks | +0.754 |
valleys | +0.750 |
Neg logit contributions | |
t | -1.867 |
happened | -1.809 |
day | -1.757 |
help | -1.754 |
please | -1.728 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
cks | +0.304 |
aron | +0.304 |
necks | +0.303 |
ping | +0.302 |
uted | +0.299 |
Neg logit contributions | |
t | -0.299 |
happened | -0.290 |
help | -0.274 |
day | -0.271 |
awaited | -0.271 |
Token | They |
Token ID | 1119 |
Feature activation | +8.39e+00 |
Pos logit contributions | |
cks | +0.084 |
ping | +0.083 |
opes | +0.082 |
aron | +0.082 |
uted | +0.081 |
Neg logit contributions | |
t | -0.108 |
happened | -0.104 |
help | -0.101 |
day | -0.101 |
please | -0.100 |
Token | reached |
Token ID | 4251 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
necks | +0.564 |
cks | +0.560 |
aron | +0.559 |
opes | +0.556 |
uted | +0.553 |
Neg logit contributions | |
t | -0.303 |
happened | -0.283 |
day | -0.269 |
help | -0.268 |
please | -0.261 |
Token | out |
Token ID | 503 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
t | +0.030 |
help | +0.030 |
happened | +0.030 |
day | +0.029 |
please | +0.028 |
Neg logit contributions | |
aron | -0.040 |
opes | -0.040 |
uted | -0.040 |
necks | -0.039 |
ping | -0.039 |
Token | ostr |
Token ID | 42387 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
necks | +0.038 |
cks | +0.038 |
opes | +0.038 |
valleys | +0.038 |
aron | +0.037 |
Neg logit contributions | |
t | -0.048 |
happened | -0.046 |
help | -0.044 |
please | -0.044 |
day | -0.044 |
Token | ich |
Token ID | 488 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
cks | +0.011 |
necks | +0.011 |
opes | +0.011 |
aron | +0.011 |
ping | +0.011 |
Neg logit contributions | |
t | -0.020 |
happened | -0.020 |
help | -0.019 |
day | -0.019 |
please | -0.019 |
Token | pen |
Token ID | 3112 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
cks | +0.377 |
opes | +0.375 |
aron | +0.374 |
uted | +0.371 |
necks | +0.370 |
Neg logit contributions | |
t | -0.396 |
help | -0.376 |
day | -0.374 |
happened | -0.374 |
please | -0.367 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
t | +0.134 |
happened | +0.127 |
day | +0.127 |
help | +0.125 |
please | +0.124 |
Neg logit contributions | |
cks | -0.133 |
opes | -0.132 |
valleys | -0.131 |
necks | -0.130 |
uted | -0.129 |
Token | Ost |
Token ID | 38919 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
ping | +0.081 |
opes | +0.079 |
cks | +0.077 |
uted | +0.076 |
necks | +0.076 |
Neg logit contributions | |
please | -0.102 |
t | -0.101 |
thank | -0.099 |
help | -0.099 |
happened | -0.099 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.54e+01 |
Pos logit contributions | |
rily | +0.131 |
edly | +0.118 |
aters | +0.115 |
valleys | +0.111 |
aron | +0.111 |
Neg logit contributions | |
day | -0.285 |
t | -0.280 |
help | -0.267 |
week | -0.265 |
done | -0.263 |
Token | hes |
Token ID | 956 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
aters | +1.029 |
necks | +1.001 |
rily | +0.992 |
ishment | +0.946 |
aron | +0.934 |
Neg logit contributions | |
t | -1.717 |
happened | -1.649 |
day | -1.573 |
help | -1.529 |
week | -1.511 |
Token | are |
Token ID | 389 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
cks | +0.373 |
necks | +0.371 |
aron | +0.370 |
opes | +0.369 |
ping | +0.368 |
Neg logit contributions | |
t | -0.223 |
happened | -0.212 |
help | -0.200 |
day | -0.199 |
please | -0.195 |
Token | big |
Token ID | 1263 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
uted | +0.015 |
opes | +0.015 |
aron | +0.015 |
rily | +0.015 |
aters | +0.015 |
Neg logit contributions | |
t | -0.012 |
happened | -0.012 |
help | -0.012 |
day | -0.012 |
please | -0.012 |
Token | birds |
Token ID | 10087 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
help | +0.176 |
happened | +0.174 |
day | +0.169 |
problem | +0.168 |
thank | +0.165 |
Neg logit contributions | |
rily | -0.180 |
uted | -0.177 |
cks | -0.174 |
bes | -0.174 |
inning | -0.170 |
Token | with |
Token ID | 351 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
opes | +0.251 |
valleys | +0.247 |
rily | +0.244 |
efully | +0.243 |
aters | +0.242 |
Neg logit contributions | |
t | -0.153 |
day | -0.148 |
help | -0.147 |
please | -0.139 |
happened | -0.135 |
Token | ostr |
Token ID | 42387 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
cks | +0.037 |
aron | +0.036 |
opes | +0.036 |
ping | +0.036 |
uted | +0.036 |
Neg logit contributions | |
t | -0.040 |
happened | -0.039 |
help | -0.038 |
day | -0.038 |
please | -0.037 |
Token | ich |
Token ID | 488 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
cks | +0.009 |
aron | +0.009 |
necks | +0.009 |
opes | +0.009 |
ping | +0.009 |
Neg logit contributions | |
t | -0.016 |
happened | -0.015 |
help | -0.015 |
day | -0.015 |
please | -0.014 |
Token | pen |
Token ID | 3112 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
cks | +0.416 |
aron | +0.413 |
opes | +0.413 |
necks | +0.410 |
uted | +0.410 |
Neg logit contributions | |
t | -0.348 |
happened | -0.330 |
help | -0.325 |
day | -0.324 |
please | -0.317 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
t | +0.138 |
happened | +0.131 |
day | +0.130 |
help | +0.127 |
please | +0.126 |
Neg logit contributions | |
cks | -0.139 |
opes | -0.136 |
valleys | -0.135 |
necks | -0.135 |
aron | -0.134 |
Token | Ost |
Token ID | 38919 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ping | +0.086 |
opes | +0.084 |
necks | +0.083 |
cks | +0.082 |
uted | +0.080 |
Neg logit contributions | |
please | -0.090 |
t | -0.088 |
thank | -0.087 |
happened | -0.087 |
help | -0.085 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.54e+01 |
Pos logit contributions | |
rily | +0.135 |
edly | +0.125 |
aters | +0.118 |
strings | +0.118 |
ksh | +0.116 |
Neg logit contributions | |
day | -0.269 |
t | -0.262 |
done | -0.251 |
week | -0.250 |
help | -0.246 |
Token | hes |
Token ID | 956 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
aters | +1.047 |
necks | +1.018 |
rily | +0.989 |
ishment | +0.961 |
aron | +0.939 |
Neg logit contributions | |
t | -1.720 |
happened | -1.649 |
day | -1.561 |
help | -1.505 |
week | -1.499 |
Token | are |
Token ID | 389 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
cks | +0.365 |
necks | +0.360 |
ping | +0.360 |
opes | +0.358 |
aron | +0.358 |
Neg logit contributions | |
t | -0.224 |
happened | -0.212 |
help | -0.202 |
day | -0.198 |
please | -0.197 |
Token | big |
Token ID | 1263 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
aron | +0.012 |
opes | +0.012 |
uted | +0.012 |
valleys | +0.012 |
aters | +0.012 |
Neg logit contributions | |
t | -0.010 |
happened | -0.010 |
help | -0.009 |
day | -0.009 |
please | -0.009 |
Token | birds |
Token ID | 10087 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
happened | +0.170 |
help | +0.168 |
day | +0.163 |
problem | +0.161 |
t | +0.159 |
Neg logit contributions | |
rily | -0.188 |
uted | -0.187 |
cks | -0.187 |
bes | -0.184 |
ags | -0.181 |
Token | with |
Token ID | 351 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
opes | +0.247 |
valleys | +0.245 |
necks | +0.242 |
ags | +0.241 |
rily | +0.241 |
Neg logit contributions | |
t | -0.152 |
day | -0.145 |
help | -0.144 |
happened | -0.138 |
please | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
cks | +0.640 |
opes | +0.639 |
necks | +0.634 |
valleys | +0.630 |
aron | +0.628 |
Neg logit contributions | |
t | -0.460 |
happened | -0.433 |
day | -0.412 |
help | -0.410 |
would | -0.394 |
Token | They |
Token ID | 1119 |
Feature activation | +8.27e+00 |
Pos logit contributions | |
ping | +0.102 |
cks | +0.101 |
opes | +0.096 |
necks | +0.094 |
uted | +0.094 |
Neg logit contributions | |
please | -0.081 |
t | -0.081 |
happened | -0.078 |
thank | -0.076 |
week | -0.075 |
Token | were |
Token ID | 547 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
necks | +0.535 |
cks | +0.531 |
opes | +0.527 |
valleys | +0.526 |
aron | +0.526 |
Neg logit contributions | |
t | -0.321 |
happened | -0.300 |
day | -0.284 |
help | -0.282 |
please | -0.276 |
Token | called |
Token ID | 1444 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
aron | +0.030 |
opes | +0.030 |
necks | +0.030 |
aters | +0.030 |
rily | +0.030 |
Neg logit contributions | |
t | -0.025 |
happened | -0.025 |
day | -0.025 |
help | -0.024 |
please | -0.024 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
cks | +0.139 |
necks | +0.138 |
aron | +0.138 |
opes | +0.138 |
ping | +0.137 |
Neg logit contributions | |
t | -0.113 |
happened | -0.108 |
help | -0.103 |
day | -0.103 |
please | -0.101 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.54e+01 |
Pos logit contributions | |
rily | +0.083 |
aron | +0.082 |
valleys | +0.075 |
bes | +0.075 |
uted | +0.074 |
Neg logit contributions | |
t | -0.304 |
happened | -0.293 |
day | -0.285 |
help | -0.284 |
would | -0.280 |
Token | hes |
Token ID | 956 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
aters | +0.975 |
necks | +0.953 |
aron | +0.914 |
rily | +0.905 |
opes | +0.888 |
Neg logit contributions | |
t | -1.737 |
happened | -1.679 |
day | -1.598 |
help | -1.572 |
week | -1.554 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
cks | +0.324 |
necks | +0.322 |
aron | +0.322 |
opes | +0.320 |
ping | +0.319 |
Neg logit contributions | |
t | -0.267 |
happened | -0.255 |
help | -0.245 |
day | -0.243 |
please | -0.239 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.78e+00 |
Pos logit contributions | |
ping | +0.091 |
cks | +0.090 |
opes | +0.089 |
necks | +0.087 |
uted | +0.087 |
Neg logit contributions | |
t | -0.078 |
please | -0.075 |
happened | -0.073 |
help | -0.072 |
day | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | +8.56e+00 |
Pos logit contributions | |
t | +0.242 |
happened | +0.242 |
would | +0.231 |
day | +0.223 |
help | +0.218 |
Neg logit contributions | |
cks | -0.358 |
ags | -0.352 |
rily | -0.351 |
ping | -0.346 |
aters | -0.345 |
Token | Ben |
Token ID | 3932 |
Feature activation | -7.58e+00 |
Pos logit contributions | |
necks | +0.532 |
opes | +0.523 |
cks | +0.522 |
valleys | +0.516 |
ping | +0.515 |
Neg logit contributions | |
t | -0.377 |
happened | -0.329 |
day | -0.314 |
week | -0.313 |
please | -0.309 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
t | +0.350 |
happened | +0.337 |
help | +0.333 |
day | +0.325 |
please | +0.317 |
Neg logit contributions | |
aron | -0.609 |
cks | -0.604 |
opes | -0.604 |
necks | -0.603 |
uted | -0.602 |
Token | and |
Token ID | 290 |
Feature activation | +8.54e+00 |
Pos logit contributions | |
t | +0.551 |
happened | +0.534 |
help | +0.508 |
day | +0.507 |
please | +0.503 |
Neg logit contributions | |
aron | -0.414 |
necks | -0.411 |
cks | -0.409 |
ping | -0.409 |
uted | -0.405 |
Token | to |
Token ID | 284 |
Feature activation | -9.32e+00 |
Pos logit contributions | |
necks | +0.492 |
neck | +0.489 |
backs | +0.478 |
wrists | +0.472 |
ears | +0.468 |
Neg logit contributions | |
t | -0.367 |
ha | -0.350 |
happened | -0.291 |
awaited | -0.291 |
gh | -0.282 |
Token | the |
Token ID | 262 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
t | +0.464 |
happened | +0.429 |
ha | +0.403 |
awaited | +0.400 |
day | +0.397 |
Neg logit contributions | |
cks | -0.521 |
necks | -0.517 |
ping | -0.513 |
opes | -0.507 |
uted | -0.504 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
necks | +0.030 |
cks | +0.030 |
valleys | +0.029 |
ping | +0.029 |
opes | +0.029 |
Neg logit contributions | |
t | -0.034 |
happened | -0.032 |
please | -0.030 |
help | -0.030 |
awaited | -0.030 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
rily | +0.084 |
valleys | +0.079 |
aron | +0.078 |
uted | +0.071 |
bes | +0.070 |
Neg logit contributions | |
t | -0.299 |
happened | -0.283 |
day | -0.283 |
help | -0.279 |
week | -0.275 |
Token | hes |
Token ID | 956 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
necks | +0.884 |
aters | +0.879 |
aron | +0.845 |
opes | +0.842 |
valleys | +0.838 |
Neg logit contributions | |
t | -1.778 |
happened | -1.729 |
day | -1.664 |
help | -1.656 |
week | -1.618 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
cks | +0.300 |
aron | +0.298 |
necks | +0.297 |
ping | +0.297 |
uted | +0.294 |
Neg logit contributions | |
t | -0.284 |
happened | -0.275 |
help | -0.259 |
day | -0.257 |
awaited | -0.257 |
Token | They |
Token ID | 1119 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
ping | +0.067 |
cks | +0.067 |
opes | +0.065 |
uted | +0.064 |
rily | +0.063 |
Neg logit contributions | |
t | -0.104 |
happened | -0.102 |
day | -0.100 |
help | -0.100 |
please | -0.099 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
necks | +0.545 |
aron | +0.543 |
uted | +0.539 |
cks | +0.538 |
opes | +0.536 |
Neg logit contributions | |
t | -0.301 |
happened | -0.278 |
day | -0.266 |
week | -0.259 |
help | -0.259 |
Token | their |
Token ID | 511 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
t | +0.030 |
happened | +0.029 |
help | +0.028 |
day | +0.027 |
please | +0.027 |
Neg logit contributions | |
cks | -0.039 |
necks | -0.039 |
aron | -0.039 |
opes | -0.039 |
ping | -0.039 |
Token | did |
Token ID | 750 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
t | +0.345 |
happened | +0.327 |
help | +0.310 |
day | +0.308 |
please | +0.301 |
Neg logit contributions | |
cks | -0.608 |
necks | -0.606 |
aron | -0.604 |
opes | -0.602 |
ping | -0.600 |
Token | not |
Token ID | 407 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
help | +0.166 |
t | +0.160 |
happened | +0.153 |
please | +0.147 |
thank | +0.144 |
Neg logit contributions | |
aters | -0.579 |
aron | -0.579 |
ping | -0.570 |
rily | -0.563 |
opes | -0.558 |
Token | know |
Token ID | 760 |
Feature activation | -6.10e+00 |
Pos logit contributions | |
aron | +0.064 |
cks | +0.061 |
ping | +0.061 |
necks | +0.060 |
uted | +0.060 |
Neg logit contributions | |
t | -0.043 |
happened | -0.042 |
awaited | -0.039 |
day | -0.037 |
week | -0.037 |
Token | what |
Token ID | 644 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
t | +0.261 |
happened | +0.252 |
help | +0.241 |
day | +0.238 |
please | +0.234 |
Neg logit contributions | |
aron | -0.365 |
necks | -0.364 |
cks | -0.364 |
opes | -0.362 |
ping | -0.361 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
cks | +0.259 |
valleys | +0.253 |
necks | +0.250 |
aron | +0.248 |
opes | +0.245 |
Neg logit contributions | |
t | -0.190 |
reward | -0.163 |
happened | -0.160 |
ll | -0.156 |
please | -0.155 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
aron | +0.064 |
necks | +0.063 |
cks | +0.063 |
valleys | +0.061 |
opes | +0.061 |
Neg logit contributions | |
t | -0.316 |
happened | -0.308 |
help | -0.301 |
day | -0.300 |
please | -0.297 |
Token | hes |
Token ID | 956 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
cks | +0.869 |
aron | +0.849 |
opes | +0.847 |
necks | +0.846 |
ping | +0.843 |
Neg logit contributions | |
t | -1.730 |
happened | -1.681 |
help | -1.643 |
day | -1.631 |
please | -1.618 |
Token | were |
Token ID | 547 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
cks | +0.352 |
ping | +0.346 |
aron | +0.343 |
opes | +0.343 |
uted | +0.342 |
Neg logit contributions | |
t | -0.231 |
happened | -0.217 |
help | -0.205 |
awaited | -0.199 |
day | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
cks | +0.026 |
opes | +0.026 |
necks | +0.026 |
ping | +0.026 |
aron | +0.026 |
Neg logit contributions | |
t | -0.021 |
happened | -0.020 |
help | -0.019 |
please | -0.019 |
day | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
ping | +0.081 |
cks | +0.080 |
opes | +0.077 |
inning | +0.076 |
bes | +0.076 |
Neg logit contributions | |
t | -0.088 |
please | -0.084 |
happened | -0.084 |
week | -0.083 |
day | -0.083 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
necks | +0.524 |
opes | +0.516 |
cks | +0.515 |
aron | +0.511 |
uted | +0.511 |
Neg logit contributions | |
t | -0.323 |
happened | -0.302 |
day | -0.289 |
help | -0.285 |
week | -0.281 |
Token | They |
Token ID | 1119 |
Feature activation | +8.13e+00 |
Pos logit contributions | |
ping | +0.081 |
rily | +0.078 |
opes | +0.078 |
bes | +0.077 |
necks | +0.075 |
Neg logit contributions | |
t | -0.081 |
day | -0.080 |
thank | -0.080 |
help | -0.079 |
happened | -0.078 |
Token | do |
Token ID | 466 |
Feature activation | -8.45e+00 |
Pos logit contributions | |
necks | +0.539 |
aron | +0.533 |
cks | +0.531 |
opes | +0.528 |
uted | +0.526 |
Neg logit contributions | |
t | -0.293 |
happened | -0.279 |
day | -0.255 |
week | -0.253 |
awaited | -0.250 |
Token | not |
Token ID | 407 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
t | +0.270 |
happened | +0.251 |
help | +0.240 |
day | +0.237 |
please | +0.227 |
Neg logit contributions | |
aron | -0.607 |
necks | -0.607 |
cks | -0.606 |
opes | -0.603 |
ping | -0.602 |
Token | pack |
Token ID | 2353 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
aron | +0.063 |
cks | +0.063 |
necks | +0.062 |
ping | +0.062 |
uted | +0.059 |
Neg logit contributions | |
t | -0.040 |
happened | -0.039 |
awaited | -0.037 |
ha | -0.034 |
reward | -0.034 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
cks | +0.245 |
aron | +0.244 |
necks | +0.244 |
opes | +0.244 |
ping | +0.242 |
Neg logit contributions | |
t | -0.213 |
happened | -0.205 |
help | -0.198 |
day | -0.196 |
please | -0.193 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
rily | +0.101 |
aron | +0.099 |
valleys | +0.096 |
uted | +0.094 |
cks | +0.090 |
Neg logit contributions | |
t | -0.282 |
happened | -0.270 |
help | -0.265 |
day | -0.262 |
please | -0.258 |
Token | hes |
Token ID | 956 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
necks | +0.820 |
aron | +0.802 |
opes | +0.789 |
aters | +0.788 |
rily | +0.779 |
Neg logit contributions | |
t | -1.810 |
happened | -1.761 |
help | -1.709 |
day | -1.705 |
please | -1.673 |
Token | anymore |
Token ID | 7471 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
cks | +0.325 |
aron | +0.323 |
necks | +0.323 |
opes | +0.323 |
uted | +0.321 |
Neg logit contributions | |
t | -0.261 |
happened | -0.249 |
help | -0.242 |
day | -0.240 |
please | -0.235 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
t | +0.263 |
happened | +0.250 |
help | +0.242 |
day | +0.239 |
please | +0.238 |
Neg logit contributions | |
cks | -0.279 |
necks | -0.279 |
aron | -0.277 |
opes | -0.276 |
ping | -0.274 |
Token | They |
Token ID | 1119 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
ping | +0.074 |
rily | +0.073 |
opes | +0.072 |
cks | +0.071 |
necks | +0.071 |
Neg logit contributions | |
t | -0.094 |
happened | -0.091 |
day | -0.089 |
help | -0.088 |
week | -0.087 |
Token | pack |
Token ID | 2353 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
necks | +0.562 |
cks | +0.558 |
aron | +0.554 |
opes | +0.551 |
uted | +0.547 |
Neg logit contributions | |
t | -0.277 |
happened | -0.263 |
day | -0.239 |
week | -0.236 |
awaited | -0.233 |
Token | you |
Token ID | 345 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
necks | +0.146 |
valleys | +0.139 |
cks | +0.137 |
opes | +0.136 |
wrists | +0.133 |
Neg logit contributions | |
happened | -0.056 |
awaited | -0.047 |
week | -0.045 |
t | -0.045 |
reward | -0.044 |
Token | count |
Token ID | 954 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
happened | +0.182 |
t | +0.179 |
awaited | +0.166 |
week | +0.160 |
day | +0.160 |
Neg logit contributions | |
necks | -0.294 |
cks | -0.293 |
aron | -0.291 |
opes | -0.287 |
ping | -0.286 |
Token | how |
Token ID | 703 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
t | +0.006 |
please | +0.005 |
help | +0.005 |
day | +0.005 |
happened | +0.005 |
Neg logit contributions | |
aron | -0.009 |
ping | -0.009 |
uted | -0.009 |
rily | -0.009 |
necks | -0.009 |
Token | many |
Token ID | 867 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
valleys | +0.754 |
necks | +0.738 |
cks | +0.734 |
opes | +0.725 |
uted | +0.715 |
Neg logit contributions | |
happened | -0.453 |
t | -0.448 |
reward | -0.418 |
awaited | -0.409 |
help | -0.398 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
cks | +0.083 |
necks | +0.082 |
opes | +0.080 |
valleys | +0.080 |
ping | +0.079 |
Neg logit contributions | |
t | -0.102 |
happened | -0.097 |
help | -0.092 |
please | -0.091 |
day | -0.091 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
rily | +0.068 |
aron | +0.067 |
uted | +0.063 |
valleys | +0.063 |
necks | +0.062 |
Neg logit contributions | |
t | -0.311 |
happened | -0.301 |
day | -0.295 |
help | -0.294 |
please | -0.289 |
Token | hes |
Token ID | 956 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
cks | +0.943 |
opes | +0.909 |
aron | +0.908 |
uted | +0.906 |
necks | +0.905 |
Neg logit contributions | |
t | -1.658 |
happened | -1.613 |
help | -1.574 |
day | -1.558 |
please | -1.550 |
Token | there |
Token ID | 612 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
cks | +0.363 |
necks | +0.351 |
ping | +0.350 |
opes | +0.348 |
aron | +0.346 |
Neg logit contributions | |
t | -0.217 |
happened | -0.213 |
awaited | -0.195 |
help | -0.191 |
reward | -0.189 |
Token | are |
Token ID | 389 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
t | +0.070 |
happened | +0.067 |
help | +0.062 |
day | +0.061 |
awaited | +0.059 |
Neg logit contributions | |
cks | -0.138 |
necks | -0.137 |
opes | -0.137 |
aron | -0.136 |
ping | -0.136 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
cks | +0.009 |
necks | +0.009 |
opes | +0.009 |
aron | +0.009 |
ping | +0.009 |
Neg logit contributions | |
t | -0.007 |
happened | -0.007 |
help | -0.007 |
day | -0.007 |
please | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
t | +0.057 |
happened | +0.054 |
awaited | +0.051 |
reward | +0.051 |
help | +0.050 |
Neg logit contributions | |
necks | -0.076 |
cks | -0.076 |
aron | -0.075 |
valleys | -0.074 |
uted | -0.073 |
Token | that |
Token ID | 326 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
cks | +0.181 |
necks | +0.179 |
aron | +0.179 |
uted | +0.178 |
opes | +0.177 |
Neg logit contributions | |
t | -0.124 |
happened | -0.117 |
help | -0.113 |
day | -0.111 |
please | -0.109 |
Token | said |
Token ID | 531 |
Feature activation | -9.03e+00 |
Pos logit contributions | |
t | +0.146 |
week | +0.128 |
please | +0.126 |
help | +0.123 |
reward | +0.123 |
Neg logit contributions | |
cks | -0.324 |
necks | -0.319 |
opes | -0.314 |
uted | -0.314 |
valleys | -0.311 |
Token | " |
Token ID | 366 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
t | +0.486 |
day | +0.461 |
week | +0.460 |
happened | +0.452 |
help | +0.440 |
Neg logit contributions | |
cks | -0.419 |
opes | -0.414 |
valleys | -0.412 |
uted | -0.412 |
aron | -0.411 |
Token | O |
Token ID | 46 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
cks | +0.072 |
necks | +0.072 |
aron | +0.072 |
opes | +0.071 |
ping | +0.071 |
Neg logit contributions | |
t | -0.080 |
happened | -0.077 |
help | -0.074 |
day | -0.074 |
please | -0.073 |
Token | st |
Token ID | 301 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
t | +0.026 |
happened | +0.026 |
help | +0.025 |
please | +0.024 |
day | +0.024 |
Neg logit contributions | |
cks | -0.033 |
necks | -0.032 |
opes | -0.032 |
aron | -0.032 |
ping | -0.032 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
necks | +0.301 |
aron | +0.300 |
cks | +0.298 |
uted | +0.298 |
valleys | +0.297 |
Neg logit contributions | |
t | -0.284 |
happened | -0.267 |
help | -0.262 |
day | -0.257 |
please | -0.257 |
Token | hes |
Token ID | 956 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
necks | +0.896 |
cks | +0.890 |
aron | +0.887 |
opes | +0.881 |
ping | +0.872 |
Neg logit contributions | |
t | -1.707 |
happened | -1.654 |
help | -1.608 |
day | -1.601 |
please | -1.583 |
Token | ". |
Token ID | 1911 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
cks | +0.340 |
ping | +0.332 |
opes | +0.332 |
uted | +0.331 |
aron | +0.330 |
Neg logit contributions | |
t | -0.231 |
happened | -0.227 |
help | -0.211 |
awaited | -0.210 |
day | -0.207 |
Token | Sara |
Token ID | 24799 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
ping | +0.269 |
cks | +0.269 |
opes | +0.267 |
inning | +0.260 |
valleys | +0.259 |
Neg logit contributions | |
t | -0.101 |
happened | -0.097 |
please | -0.096 |
thank | -0.089 |
day | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +8.52e+00 |
Pos logit contributions | |
t | +0.143 |
happened | +0.138 |
would | +0.130 |
help | +0.128 |
day | +0.127 |
Neg logit contributions | |
cks | -0.197 |
rily | -0.194 |
ping | -0.192 |
valleys | -0.191 |
ags | -0.191 |
Token | Tom |
Token ID | 4186 |
Feature activation | -9.25e+00 |
Pos logit contributions | |
necks | +0.574 |
opes | +0.571 |
uted | +0.570 |
cks | +0.569 |
aron | +0.567 |
Neg logit contributions | |
t | -0.319 |
happened | -0.274 |
help | -0.266 |
day | -0.260 |
awaited | -0.258 |
Token | cried |
Token ID | 16896 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
t | +0.219 |
happened | +0.207 |
help | +0.204 |
please | +0.196 |
day | +0.190 |
Neg logit contributions | |
opes | -0.381 |
cks | -0.380 |
valleys | -0.379 |
aters | -0.378 |
necks | -0.377 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
cks | +0.171 |
necks | +0.169 |
opes | +0.167 |
valleys | +0.166 |
bes | +0.166 |
Neg logit contributions | |
help | -0.097 |
t | -0.091 |
please | -0.087 |
happened | -0.084 |
day | -0.082 |
Token | " |
Token ID | 366 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
cks | +0.096 |
aters | +0.096 |
ping | +0.095 |
rily | +0.094 |
opes | +0.092 |
Neg logit contributions | |
t | -0.075 |
happened | -0.071 |
help | -0.067 |
please | -0.066 |
they | -0.065 |
Token | The |
Token ID | 464 |
Feature activation | +7.27e+00 |
Pos logit contributions | |
aters | +0.088 |
aron | +0.087 |
opes | +0.086 |
rily | +0.085 |
necks | +0.083 |
Neg logit contributions | |
t | -0.079 |
happened | -0.069 |
help | -0.066 |
day | -0.066 |
we | -0.062 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
necks | +0.411 |
opes | +0.408 |
ping | +0.404 |
cks | +0.399 |
valleys | +0.394 |
Neg logit contributions | |
t | -0.330 |
happened | -0.296 |
awaited | -0.294 |
please | -0.285 |
week | -0.277 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
rily | +0.064 |
valleys | +0.064 |
aron | +0.063 |
uted | +0.059 |
necks | +0.059 |
Neg logit contributions | |
t | -0.313 |
happened | -0.303 |
help | -0.297 |
day | -0.295 |
please | -0.292 |
Token | hes |
Token ID | 956 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
aters | +0.970 |
necks | +0.962 |
rily | +0.913 |
valleys | +0.907 |
opes | +0.900 |
Neg logit contributions | |
t | -1.747 |
happened | -1.686 |
day | -1.601 |
help | -1.583 |
please | -1.552 |
Token | are |
Token ID | 389 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
cks | +0.342 |
ping | +0.334 |
aron | +0.327 |
uted | +0.327 |
necks | +0.325 |
Neg logit contributions | |
t | -0.221 |
happened | -0.218 |
awaited | -0.212 |
help | -0.203 |
reward | -0.203 |
Token | mean |
Token ID | 1612 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
cks | +0.006 |
necks | +0.006 |
ping | +0.006 |
opes | +0.006 |
aron | +0.006 |
Neg logit contributions | |
t | -0.005 |
happened | -0.004 |
day | -0.004 |
help | -0.004 |
awaited | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
t | +0.467 |
happened | +0.448 |
help | +0.432 |
day | +0.429 |
please | +0.422 |
Neg logit contributions | |
cks | -0.498 |
necks | -0.496 |
aron | -0.495 |
opes | -0.493 |
ping | -0.491 |
Token | They |
Token ID | 1119 |
Feature activation | +8.07e+00 |
Pos logit contributions | |
valleys | +0.220 |
necks | +0.218 |
opes | +0.211 |
ping | +0.208 |
cks | +0.207 |
Neg logit contributions | |
t | -0.220 |
please | -0.207 |
happened | -0.203 |
help | -0.197 |
we | -0.192 |
Token |
|
Token ID | 198 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
cks | +0.080 |
necks | +0.080 |
ping | +0.079 |
opes | +0.079 |
aron | +0.079 |
Neg logit contributions | |
t | -0.076 |
happened | -0.073 |
help | -0.070 |
day | -0.070 |
please | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
t | +0.035 |
happened | +0.035 |
help | +0.033 |
day | +0.033 |
reward | +0.033 |
Neg logit contributions | |
cks | -0.039 |
aron | -0.039 |
uted | -0.038 |
necks | -0.038 |
opes | -0.038 |
Token | " |
Token ID | 1 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
t | +0.031 |
happened | +0.031 |
help | +0.029 |
day | +0.029 |
please | +0.028 |
Neg logit contributions | |
cks | -0.044 |
necks | -0.044 |
aron | -0.044 |
uted | -0.044 |
opes | -0.044 |
Token | O |
Token ID | 46 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
t | +0.126 |
happened | +0.118 |
help | +0.114 |
please | +0.114 |
day | +0.113 |
Neg logit contributions | |
cks | -0.128 |
opes | -0.128 |
ping | -0.128 |
rily | -0.126 |
aron | -0.125 |
Token | st |
Token ID | 301 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
help | +0.018 |
happened | +0.018 |
t | +0.018 |
please | +0.017 |
reward | +0.017 |
Neg logit contributions | |
cks | -0.042 |
aron | -0.041 |
necks | -0.041 |
opes | -0.041 |
ping | -0.040 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.53e+01 |
Pos logit contributions | |
aron | +0.322 |
necks | +0.320 |
uted | +0.319 |
valleys | +0.319 |
ping | +0.318 |
Neg logit contributions | |
t | -0.258 |
happened | -0.243 |
help | -0.236 |
day | -0.232 |
please | -0.231 |
Token | hes |
Token ID | 956 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
aters | +0.961 |
necks | +0.941 |
rily | +0.910 |
valleys | +0.887 |
aron | +0.876 |
Neg logit contributions | |
t | -1.737 |
happened | -1.695 |
help | -1.597 |
day | -1.592 |
please | -1.571 |
Token | do |
Token ID | 466 |
Feature activation | -8.47e+00 |
Pos logit contributions | |
cks | +0.326 |
ping | +0.313 |
uted | +0.308 |
aron | +0.306 |
opes | +0.304 |
Neg logit contributions | |
t | -0.246 |
happened | -0.238 |
awaited | -0.234 |
week | -0.227 |
help | -0.220 |
Token | not |
Token ID | 407 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
t | +0.294 |
happened | +0.284 |
day | +0.263 |
help | +0.261 |
week | +0.257 |
Neg logit contributions | |
cks | -0.580 |
necks | -0.572 |
opes | -0.572 |
aron | -0.565 |
uted | -0.564 |
Token | like |
Token ID | 588 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
ping | +0.065 |
cks | +0.064 |
aron | +0.064 |
necks | +0.063 |
uted | +0.063 |
Neg logit contributions | |
t | -0.039 |
happened | -0.036 |
awaited | -0.035 |
reward | -0.032 |
day | -0.032 |
Token | people |
Token ID | 661 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
cks | +0.145 |
opes | +0.145 |
necks | +0.144 |
ping | +0.143 |
uted | +0.142 |
Neg logit contributions | |
t | -0.093 |
happened | -0.080 |
awaited | -0.080 |
reward | -0.079 |
ha | -0.077 |
Token | but |
Token ID | 475 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
happened | +0.240 |
t | +0.239 |
week | +0.212 |
day | +0.211 |
awaited | +0.205 |
Neg logit contributions | |
necks | -0.476 |
rily | -0.464 |
cks | -0.463 |
aron | -0.463 |
uted | -0.457 |
Token | be |
Token ID | 307 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
necks | +0.370 |
neck | +0.359 |
cks | +0.328 |
opes | +0.327 |
ears | +0.321 |
Neg logit contributions | |
t | -0.275 |
ha | -0.254 |
awaited | -0.239 |
happened | -0.238 |
week | -0.217 |
Token | careful |
Token ID | 8161 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
opes | +0.104 |
aters | +0.102 |
rily | +0.102 |
valleys | +0.101 |
uted | +0.100 |
Neg logit contributions | |
help | -0.042 |
please | -0.041 |
day | -0.039 |
t | -0.037 |
week | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
t | +0.120 |
help | +0.109 |
day | +0.108 |
please | +0.106 |
happened | +0.106 |
Neg logit contributions | |
valleys | -0.164 |
cks | -0.160 |
necks | -0.160 |
opes | -0.160 |
uted | -0.159 |
Token | Ost |
Token ID | 38919 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ping | +0.083 |
uted | +0.083 |
opes | +0.082 |
valleys | +0.082 |
cks | +0.082 |
Neg logit contributions | |
t | -0.073 |
please | -0.073 |
help | -0.071 |
thank | -0.068 |
day | -0.066 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
rily | +0.117 |
valleys | +0.104 |
aron | +0.104 |
edly | +0.103 |
aters | +0.102 |
Neg logit contributions | |
day | -0.275 |
t | -0.271 |
help | -0.269 |
week | -0.257 |
done | -0.252 |
Token | hes |
Token ID | 956 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
aters | +0.942 |
necks | +0.930 |
rily | +0.910 |
aron | +0.882 |
opes | +0.878 |
Neg logit contributions | |
t | -1.732 |
happened | -1.676 |
day | -1.617 |
help | -1.601 |
please | -1.566 |
Token | can |
Token ID | 460 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
cks | +0.358 |
necks | +0.353 |
ping | +0.351 |
aron | +0.351 |
opes | +0.349 |
Neg logit contributions | |
t | -0.217 |
happened | -0.211 |
help | -0.194 |
day | -0.192 |
awaited | -0.192 |
Token | be |
Token ID | 307 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
t | +0.321 |
happened | +0.309 |
day | +0.287 |
help | +0.286 |
please | +0.278 |
Neg logit contributions | |
cks | -0.569 |
necks | -0.566 |
aron | -0.563 |
opes | -0.562 |
ping | -0.559 |
Token | gr |
Token ID | 1036 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
opes | +0.076 |
aron | +0.076 |
cks | +0.076 |
necks | +0.075 |
uted | +0.075 |
Neg logit contributions | |
t | -0.068 |
happened | -0.065 |
help | -0.063 |
day | -0.062 |
please | -0.061 |
Token | umpy |
Token ID | 32152 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
rily | +0.146 |
valleys | +0.141 |
necks | +0.138 |
opes | +0.133 |
bes | +0.133 |
Neg logit contributions | |
t | -0.185 |
day | -0.164 |
week | -0.161 |
happened | -0.160 |
help | -0.156 |
Token | Yes |
Token ID | 5297 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
t | +0.137 |
day | +0.131 |
happened | +0.130 |
help | +0.128 |
week | +0.126 |
Neg logit contributions | |
opes | -0.120 |
rily | -0.118 |
aron | -0.117 |
ping | -0.117 |
cks | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
rily | +0.055 |
cks | +0.052 |
opes | +0.052 |
necks | +0.052 |
ping | +0.051 |
Neg logit contributions | |
happened | -0.032 |
t | -0.032 |
awaited | -0.032 |
week | -0.029 |
day | -0.028 |
Token | they |
Token ID | 484 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
t | +0.279 |
happened | +0.260 |
day | +0.241 |
awaited | +0.240 |
week | +0.239 |
Neg logit contributions | |
necks | -0.454 |
cks | -0.454 |
opes | -0.447 |
rily | -0.446 |
ping | -0.445 |
Token | are |
Token ID | 389 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
t | +0.153 |
happened | +0.139 |
day | +0.132 |
please | +0.131 |
week | +0.130 |
Neg logit contributions | |
cks | -0.258 |
necks | -0.255 |
opes | -0.254 |
valleys | -0.251 |
ping | -0.251 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
cks | +0.006 |
necks | +0.006 |
aron | +0.006 |
opes | +0.006 |
ping | +0.006 |
Neg logit contributions | |
t | -0.004 |
happened | -0.004 |
help | -0.003 |
day | -0.003 |
please | -0.003 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
aron | +0.072 |
valleys | +0.069 |
necks | +0.069 |
rily | +0.069 |
cks | +0.069 |
Neg logit contributions | |
t | -0.300 |
happened | -0.291 |
help | -0.285 |
day | -0.284 |
please | -0.280 |
Token | hes |
Token ID | 956 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
necks | +0.828 |
aters | +0.808 |
aron | +0.806 |
opes | +0.796 |
rily | +0.789 |
Neg logit contributions | |
t | -1.786 |
happened | -1.744 |
help | -1.684 |
day | -1.683 |
please | -1.651 |
Token | ," |
Token ID | 553 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
cks | +0.345 |
necks | +0.341 |
aron | +0.340 |
ping | +0.339 |
opes | +0.338 |
Neg logit contributions | |
t | -0.233 |
happened | -0.223 |
help | -0.208 |
day | -0.207 |
awaited | -0.204 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.41e+00 |
Pos logit contributions | |
t | +0.290 |
happened | +0.246 |
awaited | +0.244 |
ha | +0.235 |
week | +0.232 |
Neg logit contributions | |
necks | -0.356 |
cks | -0.350 |
efully | -0.339 |
valleys | -0.335 |
aron | -0.330 |
Token | said |
Token ID | 531 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
t | +0.261 |
happened | +0.241 |
help | +0.231 |
day | +0.226 |
reward | +0.223 |
Neg logit contributions | |
aron | -0.727 |
uted | -0.713 |
ping | -0.700 |
cks | -0.699 |
necks | -0.698 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
t | +0.442 |
happened | +0.420 |
day | +0.406 |
awaited | +0.402 |
week | +0.399 |
Neg logit contributions | |
aron | -0.491 |
ping | -0.486 |
rily | -0.485 |
cks | -0.481 |
necks | -0.480 |
Token | ie |
Token ID | 494 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
t | +0.029 |
happened | +0.027 |
help | +0.026 |
day | +0.026 |
please | +0.026 |
Neg logit contributions | |
cks | -0.040 |
necks | -0.040 |
aron | -0.040 |
opes | -0.040 |
uted | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
day | +0.142 |
t | +0.136 |
would | +0.135 |
help | +0.134 |
please | +0.126 |
Neg logit contributions | |
valleys | -0.261 |
cks | -0.258 |
ags | -0.251 |
uted | -0.251 |
opes | -0.250 |
Token | Unlike |
Token ID | 12101 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
cks | +0.102 |
uted | +0.102 |
opes | +0.100 |
necks | +0.100 |
aron | +0.100 |
Neg logit contributions | |
t | -0.060 |
day | -0.057 |
please | -0.055 |
help | -0.054 |
week | -0.052 |
Token | other |
Token ID | 584 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
cks | +0.475 |
ping | +0.473 |
necks | +0.465 |
opes | +0.463 |
valleys | +0.462 |
Neg logit contributions | |
t | -0.348 |
happened | -0.340 |
help | -0.313 |
please | -0.311 |
reward | -0.310 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
t | +0.393 |
happened | +0.377 |
help | +0.361 |
day | +0.359 |
please | +0.357 |
Neg logit contributions | |
necks | -0.310 |
cks | -0.308 |
ping | -0.304 |
opes | -0.304 |
aron | -0.302 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
rily | +0.065 |
aron | +0.063 |
valleys | +0.060 |
uted | +0.058 |
necks | +0.056 |
Neg logit contributions | |
t | -0.308 |
happened | -0.299 |
day | -0.293 |
help | -0.290 |
week | -0.287 |
Token | hes |
Token ID | 956 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
necks | +0.917 |
aters | +0.900 |
aron | +0.879 |
opes | +0.865 |
rily | +0.865 |
Neg logit contributions | |
t | -1.742 |
happened | -1.688 |
day | -1.630 |
help | -1.603 |
week | -1.587 |
Token | , |
Token ID | 11 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
cks | +0.347 |
ping | +0.346 |
opes | +0.343 |
necks | +0.342 |
aron | +0.339 |
Neg logit contributions | |
t | -0.219 |
happened | -0.208 |
help | -0.198 |
please | -0.197 |
reward | -0.195 |
Token | his |
Token ID | 465 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
t | +0.250 |
happened | +0.235 |
day | +0.229 |
help | +0.227 |
please | +0.223 |
Neg logit contributions | |
aron | -0.491 |
cks | -0.490 |
necks | -0.485 |
uted | -0.484 |
aters | -0.483 |
Token | feathers |
Token ID | 27400 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
necks | +0.158 |
opes | +0.154 |
cks | +0.154 |
ping | +0.153 |
aron | +0.152 |
Neg logit contributions | |
t | -0.136 |
happened | -0.128 |
help | -0.120 |
please | -0.120 |
awaited | -0.119 |
Token | gl |
Token ID | 1278 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
ping | +0.850 |
cks | +0.850 |
necks | +0.849 |
opes | +0.845 |
aron | +0.841 |
Neg logit contributions | |
t | -0.495 |
happened | -0.466 |
help | -0.449 |
please | -0.445 |
day | -0.436 |
Token | Look |
Token ID | 8567 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
rily | +0.078 |
cks | +0.077 |
bes | +0.077 |
ags | +0.076 |
opes | +0.075 |
Neg logit contributions | |
t | -0.071 |
day | -0.067 |
would | -0.065 |
week | -0.064 |
ha | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
cks | +0.186 |
uted | +0.180 |
opes | +0.179 |
rily | +0.179 |
necks | +0.175 |
Neg logit contributions | |
t | -0.121 |
week | -0.102 |
happened | -0.102 |
awaited | -0.098 |
day | -0.096 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
t | +0.346 |
happened | +0.298 |
awaited | +0.280 |
week | +0.277 |
day | +0.268 |
Neg logit contributions | |
necks | -0.408 |
valleys | -0.404 |
cks | -0.399 |
neck | -0.397 |
opes | -0.397 |
Token | , |
Token ID | 11 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
t | +0.341 |
help | +0.307 |
happened | +0.305 |
reward | +0.292 |
please | +0.275 |
Neg logit contributions | |
aters | -0.647 |
aron | -0.645 |
ping | -0.637 |
uted | -0.633 |
cks | -0.628 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
t | +0.367 |
happened | +0.315 |
week | +0.298 |
awaited | +0.294 |
day | +0.293 |
Neg logit contributions | |
valleys | -0.387 |
necks | -0.386 |
cks | -0.378 |
neck | -0.377 |
opes | -0.369 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
rily | +0.059 |
aron | +0.059 |
valleys | +0.057 |
uted | +0.055 |
necks | +0.055 |
Neg logit contributions | |
t | -0.308 |
happened | -0.299 |
help | -0.292 |
day | -0.292 |
please | -0.288 |
Token | hes |
Token ID | 956 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
aters | +0.935 |
necks | +0.921 |
rily | +0.891 |
aron | +0.884 |
opes | +0.866 |
Neg logit contributions | |
t | -1.708 |
happened | -1.676 |
day | -1.604 |
help | -1.596 |
please | -1.563 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
cks | +0.358 |
ping | +0.351 |
necks | +0.350 |
opes | +0.349 |
uted | +0.348 |
Neg logit contributions | |
t | -0.219 |
happened | -0.209 |
help | -0.194 |
day | -0.192 |
awaited | -0.191 |
Token |
|
Token ID | 198 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
cks | +0.075 |
aron | +0.074 |
ping | +0.074 |
opes | +0.074 |
necks | +0.073 |
Neg logit contributions | |
t | -0.071 |
happened | -0.068 |
help | -0.067 |
day | -0.066 |
please | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
t | +0.039 |
happened | +0.039 |
reward | +0.037 |
help | +0.037 |
awaited | +0.036 |
Neg logit contributions | |
cks | -0.037 |
uted | -0.037 |
aron | -0.037 |
necks | -0.036 |
opes | -0.036 |
Token | " |
Token ID | 1 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
t | +0.045 |
happened | +0.044 |
help | +0.042 |
day | +0.042 |
please | +0.041 |
Neg logit contributions | |
cks | -0.034 |
necks | -0.034 |
aron | -0.034 |
opes | -0.033 |
uted | -0.033 |
Token | should |
Token ID | 815 |
Feature activation | -8.26e+00 |
Pos logit contributions | |
cks | +0.396 |
opes | +0.396 |
necks | +0.395 |
aron | +0.394 |
uted | +0.394 |
Neg logit contributions | |
t | -0.211 |
happened | -0.197 |
day | -0.195 |
week | -0.193 |
awaited | -0.184 |
Token | not |
Token ID | 407 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
t | +0.295 |
happened | +0.286 |
awaited | +0.263 |
week | +0.251 |
day | +0.250 |
Neg logit contributions | |
necks | -0.553 |
aron | -0.552 |
cks | -0.549 |
opes | -0.545 |
ping | -0.536 |
Token | tease |
Token ID | 34691 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
cks | +0.057 |
necks | +0.057 |
aron | +0.057 |
ping | +0.056 |
opes | +0.056 |
Neg logit contributions | |
t | -0.035 |
happened | -0.034 |
awaited | -0.032 |
day | -0.031 |
week | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
t | +0.153 |
happened | +0.149 |
help | +0.146 |
day | +0.141 |
please | +0.140 |
Neg logit contributions | |
aron | -0.261 |
rily | -0.260 |
valleys | -0.258 |
necks | -0.258 |
opes | -0.257 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
cks | +0.023 |
necks | +0.023 |
aron | +0.023 |
opes | +0.023 |
uted | +0.023 |
Neg logit contributions | |
t | -0.025 |
happened | -0.024 |
help | -0.023 |
day | -0.023 |
please | -0.023 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
rily | +0.064 |
valleys | +0.063 |
aron | +0.062 |
uted | +0.058 |
necks | +0.057 |
Neg logit contributions | |
t | -0.306 |
happened | -0.294 |
help | -0.289 |
day | -0.289 |
please | -0.283 |
Token | hes |
Token ID | 956 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
necks | +0.767 |
cks | +0.765 |
aron | +0.761 |
opes | +0.756 |
ping | +0.747 |
Neg logit contributions | |
t | -1.822 |
happened | -1.770 |
help | -1.724 |
day | -1.718 |
please | -1.698 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
cks | +0.286 |
ping | +0.284 |
aron | +0.284 |
necks | +0.281 |
uted | +0.280 |
Neg logit contributions | |
t | -0.276 |
happened | -0.274 |
awaited | -0.257 |
help | -0.250 |
reward | -0.248 |
Token | They |
Token ID | 1119 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
ping | +0.075 |
rily | +0.075 |
valleys | +0.073 |
necks | +0.073 |
opes | +0.073 |
Neg logit contributions | |
please | -0.076 |
t | -0.076 |
help | -0.074 |
we | -0.071 |
thank | -0.070 |
Token | are |
Token ID | 389 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
necks | +0.513 |
cks | +0.509 |
opes | +0.505 |
uted | +0.495 |
ping | +0.494 |
Neg logit contributions | |
t | -0.296 |
happened | -0.283 |
week | -0.279 |
day | -0.270 |
please | -0.265 |
Token | not |
Token ID | 407 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
cks | +0.005 |
aron | +0.005 |
necks | +0.005 |
opes | +0.005 |
uted | +0.005 |
Neg logit contributions | |
t | -0.003 |
happened | -0.003 |
help | -0.003 |
day | -0.003 |
please | -0.003 |
Token | shouted |
Token ID | 17293 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
t | +0.382 |
happened | +0.365 |
help | +0.352 |
please | +0.342 |
day | +0.330 |
Neg logit contributions | |
rily | -0.591 |
opes | -0.590 |
valleys | -0.587 |
cks | -0.587 |
aters | -0.581 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.030 |
happened | +0.029 |
day | +0.027 |
help | +0.027 |
week | +0.026 |
Neg logit contributions | |
aron | -0.039 |
cks | -0.039 |
necks | -0.039 |
ping | -0.039 |
uted | -0.039 |
Token | " |
Token ID | 366 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
aron | +0.076 |
cks | +0.076 |
necks | +0.076 |
opes | +0.075 |
uted | +0.075 |
Neg logit contributions | |
t | -0.072 |
happened | -0.069 |
help | -0.067 |
day | -0.067 |
week | -0.065 |
Token | The |
Token ID | 464 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
opes | +0.090 |
aters | +0.086 |
aron | +0.086 |
ping | +0.085 |
rily | +0.085 |
Neg logit contributions | |
t | -0.066 |
we | -0.055 |
they | -0.055 |
please | -0.054 |
day | -0.053 |
Token | ost |
Token ID | 23619 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
necks | +0.370 |
cks | +0.366 |
opes | +0.365 |
ping | +0.363 |
aron | +0.362 |
Neg logit contributions | |
t | -0.378 |
happened | -0.360 |
help | -0.346 |
please | -0.341 |
day | -0.340 |
Token | ric |
Token ID | 1173 |
Feature activation | +2.52e+01 |
Pos logit contributions | |
rily | +0.081 |
valleys | +0.075 |
aron | +0.073 |
uted | +0.068 |
bes | +0.067 |
Neg logit contributions | |
t | -0.292 |
happened | -0.276 |
day | -0.271 |
help | -0.269 |
please | -0.264 |
Token | hes |
Token ID | 956 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
necks | +0.892 |
aters | +0.883 |
rily | +0.843 |
aron | +0.837 |
opes | +0.836 |
Neg logit contributions | |
t | -1.785 |
happened | -1.719 |
day | -1.649 |
help | -1.628 |
please | -1.606 |
Token | are |
Token ID | 389 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
cks | +0.350 |
ping | +0.341 |
uted | +0.337 |
necks | +0.336 |
opes | +0.336 |
Neg logit contributions | |
t | -0.214 |
happened | -0.208 |
help | -0.196 |
awaited | -0.194 |
week | -0.190 |
Token | so |
Token ID | 523 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
aron | +0.003 |
necks | +0.003 |
uted | +0.003 |
opes | +0.003 |
cks | +0.003 |
Neg logit contributions | |
t | -0.002 |
happened | -0.002 |
help | -0.002 |
day | -0.002 |
please | -0.002 |
Token | funny |
Token ID | 8258 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
cks | +0.375 |
necks | +0.370 |
aron | +0.366 |
opes | +0.365 |
uted | +0.365 |
Neg logit contributions | |
t | -0.315 |
happened | -0.305 |
help | -0.291 |
day | -0.286 |
please | -0.285 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
t | +0.068 |
happened | +0.065 |
day | +0.064 |
help | +0.062 |
please | +0.062 |
Neg logit contributions | |
rily | -0.114 |
valleys | -0.113 |
necks | -0.113 |
ags | -0.113 |
cks | -0.112 |
Token | At |
Token ID | 2953 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
t | +0.045 |
day | +0.041 |
week | +0.041 |
happened | +0.040 |
please | +0.040 |
Neg logit contributions | |
cks | -0.044 |
ping | -0.043 |
necks | -0.043 |
opes | -0.042 |
aron | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
valleys | +0.137 |
cks | +0.127 |
ags | +0.123 |
rivers | +0.122 |
ping | +0.121 |
Neg logit contributions | |
t | -0.143 |
happened | -0.129 |
please | -0.121 |
ha | -0.119 |
awaited | -0.117 |
Token | end |
Token ID | 886 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
valleys | +0.029 |
necks | +0.028 |
ping | +0.027 |
opes | +0.027 |
cks | +0.027 |
Neg logit contributions | |
t | -0.016 |
happened | -0.016 |
please | -0.014 |
awaited | -0.013 |
help | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
happened | +0.180 |
t | +0.166 |
reward | +0.160 |
would | +0.160 |
help | +0.156 |
Neg logit contributions | |
valleys | -0.249 |
aters | -0.247 |
piles | -0.241 |
aron | -0.237 |
ady | -0.233 |
Token | the |
Token ID | 262 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
t | +0.352 |
happened | +0.321 |
please | +0.311 |
would | +0.300 |
help | +0.297 |
Neg logit contributions | |
cks | -0.401 |
valleys | -0.392 |
necks | -0.390 |
aron | -0.389 |
ping | -0.387 |
Token | week |
Token ID | 1285 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
valleys | +0.033 |
necks | +0.033 |
strings | +0.032 |
ping | +0.032 |
opes | +0.031 |
Neg logit contributions | |
happened | -0.012 |
t | -0.011 |
please | -0.011 |
ha | -0.008 |
would | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
t | +0.470 |
happened | +0.411 |
help | +0.401 |
please | +0.394 |
ha | +0.370 |
Neg logit contributions | |
aron | -1.075 |
valleys | -1.072 |
aters | -1.061 |
uted | -1.046 |
necks | -1.045 |
Token | Sus |
Token ID | 8932 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
t | +0.252 |
happened | +0.238 |
help | +0.222 |
day | +0.217 |
please | +0.214 |
Neg logit contributions | |
aron | -0.474 |
valleys | -0.473 |
uted | -0.472 |
rily | -0.472 |
necks | -0.472 |
Token | ie |
Token ID | 494 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
t | +0.000 |
happened | +0.000 |
help | +0.000 |
day | +0.000 |
please | +0.000 |
Neg logit contributions | |
cks | -0.001 |
necks | -0.001 |
aron | -0.001 |
opes | -0.001 |
ping | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -9.11e+00 |
Pos logit contributions | |
t | +0.159 |
happened | +0.148 |
help | +0.141 |
day | +0.139 |
please | +0.139 |
Neg logit contributions | |
necks | -0.242 |
aron | -0.242 |
opes | -0.239 |
cks | -0.239 |
uted | -0.239 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
t | +0.386 |
awaited | +0.373 |
happened | +0.363 |
day | +0.351 |
ll | +0.351 |
Neg logit contributions | |
rily | -0.519 |
edly | -0.493 |
uted | -0.486 |
aron | -0.475 |
efully | -0.469 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
opes | +0.034 |
cks | +0.034 |
uted | +0.034 |
aters | +0.033 |
necks | +0.033 |
Neg logit contributions | |
t | -0.040 |
help | -0.037 |
happened | -0.037 |
day | -0.037 |
week | -0.036 |
Token | told |
Token ID | 1297 |
Feature activation | -7.41e+00 |
Pos logit contributions | |
necks | +0.480 |
valleys | +0.462 |
cks | +0.456 |
aron | +0.441 |
neck | +0.440 |
Neg logit contributions | |
t | -0.413 |
ha | -0.362 |
happened | -0.355 |
problem | -0.343 |
week | -0.340 |
Token | their |
Token ID | 511 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
t | +0.402 |
happened | +0.365 |
awaited | +0.348 |
ha | +0.343 |
week | +0.341 |
Neg logit contributions | |
cks | -0.381 |
necks | -0.378 |
uted | -0.376 |
ping | -0.376 |
opes | -0.373 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
piles | +0.204 |
opes | +0.202 |
necks | +0.202 |
ears | +0.200 |
backs | +0.196 |
Neg logit contributions | |
t | -0.160 |
awaited | -0.143 |
ha | -0.133 |
happened | -0.131 |
please | -0.130 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
t | +0.445 |
happened | +0.423 |
help | +0.405 |
day | +0.401 |
please | +0.396 |
Neg logit contributions | |
cks | -0.532 |
aron | -0.531 |
necks | -0.530 |
ping | -0.527 |
opes | -0.526 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
valleys | +0.269 |
cks | +0.266 |
bes | +0.258 |
uted | +0.257 |
spots | +0.257 |
Neg logit contributions | |
reward | -0.118 |
please | -0.117 |
use | -0.104 |
t | -0.104 |
ipop | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.737 |
happened | +0.706 |
help | +0.680 |
day | +0.676 |
please | +0.661 |
Neg logit contributions | |
cks | -0.862 |
necks | -0.860 |
opes | -0.859 |
aron | -0.858 |
uted | -0.850 |
Token |
|
Token ID | 198 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
cks | +0.086 |
ping | +0.086 |
necks | +0.085 |
opes | +0.085 |
aron | +0.084 |
Neg logit contributions | |
t | -0.066 |
happened | -0.063 |
help | -0.060 |
day | -0.060 |
please | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
t | +0.037 |
happened | +0.036 |
help | +0.035 |
day | +0.034 |
please | +0.034 |
Neg logit contributions | |
cks | -0.046 |
aron | -0.045 |
necks | -0.045 |
opes | -0.045 |
uted | -0.045 |
Token | Their |
Token ID | 14574 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
t | +0.035 |
happened | +0.033 |
help | +0.032 |
day | +0.032 |
please | +0.032 |
Neg logit contributions | |
cks | -0.048 |
opes | -0.048 |
necks | -0.048 |
ping | -0.048 |
aron | -0.047 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.47e+00 |
Pos logit contributions | |
necks | +0.423 |
opes | +0.402 |
ears | +0.397 |
piles | +0.393 |
backs | +0.388 |
Neg logit contributions | |
t | -0.255 |
awaited | -0.239 |
ha | -0.235 |
please | -0.217 |
happened | -0.216 |
Token | 's |
Token ID | 338 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
t | +0.279 |
day | +0.251 |
happened | +0.249 |
help | +0.249 |
week | +0.247 |
Neg logit contributions | |
necks | -0.447 |
aron | -0.442 |
ping | -0.439 |
valleys | -0.438 |
opes | -0.437 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
t | +0.019 |
awaited | +0.017 |
happened | +0.017 |
ha | +0.016 |
week | +0.015 |
Neg logit contributions | |
necks | -0.032 |
opes | -0.031 |
neck | -0.031 |
ping | -0.031 |
valleys | -0.030 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
t | +0.338 |
reward | +0.306 |
day | +0.301 |
week | +0.290 |
help | +0.282 |
Neg logit contributions | |
ping | -0.648 |
aron | -0.642 |
uted | -0.632 |
cks | -0.625 |
opes | -0.625 |
Token | what |
Token ID | 644 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
happened | +0.198 |
t | +0.196 |
help | +0.189 |
day | +0.181 |
please | +0.180 |
Neg logit contributions | |
necks | -0.331 |
aron | -0.329 |
cks | -0.326 |
aters | -0.323 |
opes | -0.323 |
Token | had |
Token ID | 550 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
opes | +0.281 |
uted | +0.280 |
strings | +0.279 |
bes | +0.278 |
valleys | +0.275 |
Neg logit contributions | |
reward | -0.118 |
inconvenience | -0.112 |
bye | -0.107 |
t | -0.104 |
please | -0.103 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
t | +0.071 |
please | +0.066 |
day | +0.060 |
week | +0.057 |
reward | +0.057 |
Neg logit contributions | |
ping | -0.367 |
uted | -0.361 |
cks | -0.356 |
opes | -0.350 |
ps | -0.345 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.736 |
happened | +0.716 |
day | +0.705 |
help | +0.684 |
week | +0.664 |
Neg logit contributions | |
cks | -0.888 |
valleys | -0.874 |
opes | -0.873 |
necks | -0.868 |
aters | -0.867 |
Token | She |
Token ID | 1375 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
cks | +0.070 |
necks | +0.070 |
aron | +0.069 |
opes | +0.069 |
ping | +0.069 |
Neg logit contributions | |
t | -0.081 |
happened | -0.078 |
help | -0.075 |
day | -0.075 |
please | -0.074 |
Token | stepped |
Token ID | 10764 |
Feature activation | +5.08e+00 |
Pos logit contributions | |
aron | +0.218 |
uted | +0.215 |
necks | +0.213 |
ping | +0.212 |
cks | +0.212 |
Neg logit contributions | |
t | -0.134 |
day | -0.123 |
week | -0.121 |
happened | -0.121 |
awaited | -0.116 |
Token | in |
Token ID | 287 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
opes | +0.306 |
cks | +0.302 |
necks | +0.301 |
aters | +0.293 |
aron | +0.292 |
Neg logit contributions | |
t | -0.236 |
help | -0.236 |
please | -0.225 |
happened | -0.217 |
day | -0.216 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
opes | +0.081 |
cks | +0.080 |
uted | +0.078 |
necks | +0.077 |
aters | +0.077 |
Neg logit contributions | |
help | -0.079 |
t | -0.076 |
happened | -0.074 |
day | -0.073 |
please | -0.072 |
Token | into |
Token ID | 656 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
cks | +0.086 |
opes | +0.084 |
uted | +0.083 |
aron | +0.083 |
necks | +0.082 |
Neg logit contributions | |
help | -0.044 |
day | -0.043 |
t | -0.042 |
happened | -0.041 |
thank | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
aron | +0.559 |
uted | +0.544 |
cks | +0.537 |
ping | +0.534 |
ksh | +0.532 |
Neg logit contributions | |
help | -0.265 |
day | -0.237 |
happened | -0.219 |
week | -0.215 |
t | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
t | +0.117 |
day | +0.114 |
help | +0.114 |
happened | +0.109 |
please | +0.108 |
Neg logit contributions | |
cks | -0.120 |
necks | -0.115 |
uted | -0.115 |
opes | -0.115 |
aron | -0.115 |
Token | but |
Token ID | 475 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
help | +0.336 |
t | +0.331 |
day | +0.326 |
happened | +0.325 |
would | +0.319 |
Neg logit contributions | |
aters | -0.416 |
cks | -0.409 |
opes | -0.401 |
efully | -0.391 |
uted | -0.390 |
Token | nothing |
Token ID | 2147 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
valleys | +0.371 |
necks | +0.358 |
uted | +0.348 |
ping | +0.347 |
opes | +0.346 |
Neg logit contributions | |
t | -0.231 |
happened | -0.218 |
reward | -0.209 |
help | -0.208 |
week | -0.205 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
ping | +0.223 |
aron | +0.221 |
valleys | +0.214 |
cks | +0.212 |
uted | +0.211 |
Neg logit contributions | |
please | -0.103 |
reward | -0.092 |
t | -0.090 |
thank | -0.087 |
Sorry | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.714 |
happened | +0.676 |
help | +0.654 |
day | +0.649 |
please | +0.632 |
Neg logit contributions | |
cks | -0.892 |
opes | -0.886 |
aron | -0.885 |
necks | -0.884 |
uted | -0.877 |
Token | |
Token ID | 220 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
cks | +0.079 |
necks | +0.076 |
ping | +0.076 |
opes | +0.075 |
uted | +0.074 |
Neg logit contributions | |
t | -0.078 |
happened | -0.072 |
help | -0.071 |
day | -0.071 |
please | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
necks | +0.189 |
cks | +0.187 |
ping | +0.187 |
opes | +0.186 |
aron | +0.186 |
Neg logit contributions | |
t | -0.133 |
happened | -0.124 |
help | -0.119 |
day | -0.118 |
please | -0.116 |
Token |
|
Token ID | 198 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
t | +0.037 |
happened | +0.036 |
help | +0.035 |
day | +0.034 |
please | +0.034 |
Neg logit contributions | |
cks | -0.044 |
aron | -0.044 |
necks | -0.044 |
uted | -0.044 |
opes | -0.043 |
Token | The |
Token ID | 464 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
t | +0.049 |
week | +0.043 |
day | +0.043 |
please | +0.043 |
help | +0.043 |
Neg logit contributions | |
cks | -0.039 |
rily | -0.039 |
ping | -0.038 |
opes | -0.038 |
aters | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
cks | +0.410 |
necks | +0.408 |
valleys | +0.398 |
uted | +0.391 |
bes | +0.391 |
Neg logit contributions | |
t | -0.249 |
happened | -0.234 |
help | -0.226 |
day | -0.224 |
please | -0.221 |
Token |
|
Token ID | 198 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
aron | +0.070 |
cks | +0.070 |
opes | +0.069 |
necks | +0.069 |
uted | +0.069 |
Neg logit contributions | |
t | -0.075 |
happened | -0.072 |
day | -0.071 |
help | -0.070 |
week | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
happened | +0.045 |
t | +0.044 |
reward | +0.044 |
problem | +0.043 |
day | +0.042 |
Neg logit contributions | |
cks | -0.037 |
aron | -0.036 |
uted | -0.036 |
valleys | -0.034 |
opes | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
happened | +0.039 |
t | +0.037 |
awaited | +0.035 |
day | +0.035 |
week | +0.035 |
Neg logit contributions | |
cks | -0.044 |
necks | -0.043 |
aron | -0.042 |
opes | -0.042 |
uted | -0.042 |
Token | What |
Token ID | 2061 |
Feature activation | +9.61e+00 |
Pos logit contributions | |
t | +0.126 |
happened | +0.121 |
help | +0.117 |
day | +0.115 |
please | +0.115 |
Neg logit contributions | |
cks | -0.132 |
opes | -0.132 |
necks | -0.131 |
aron | -0.131 |
ping | -0.131 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
uted | +0.647 |
cks | +0.638 |
opes | +0.618 |
aron | +0.601 |
ping | +0.589 |
Neg logit contributions | |
t | -0.293 |
week | -0.264 |
reward | -0.258 |
ha | -0.246 |
day | -0.245 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
t | +0.630 |
ha | +0.549 |
reward | +0.545 |
awaited | +0.524 |
happened | +0.523 |
Neg logit contributions | |
aron | -0.921 |
ping | -0.920 |
uted | -0.907 |
rily | -0.897 |
cks | -0.895 |
Token | Sam |
Token ID | 3409 |
Feature activation | -7.80e+00 |
Pos logit contributions | |
t | +0.247 |
happened | +0.224 |
day | +0.209 |
week | +0.207 |
help | +0.204 |
Neg logit contributions | |
cks | -0.500 |
opes | -0.497 |
necks | -0.495 |
aron | -0.494 |
uted | -0.494 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
t | +0.323 |
reward | +0.273 |
help | +0.271 |
please | +0.249 |
thank | +0.249 |
Neg logit contributions | |
aron | -0.512 |
ping | -0.497 |
cks | -0.489 |
uted | -0.486 |
opes | -0.479 |
Token | his |
Token ID | 465 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
t | +0.068 |
ha | +0.063 |
awaited | +0.061 |
week | +0.059 |
reward | +0.059 |
Neg logit contributions | |
cks | -0.075 |
necks | -0.074 |
neck | -0.071 |
uted | -0.070 |
valleys | -0.070 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.47e+00 |
Pos logit contributions | |
necks | +0.218 |
cks | +0.216 |
opes | +0.216 |
aron | +0.215 |
uted | +0.214 |
Neg logit contributions | |
t | -0.068 |
happened | -0.061 |
awaited | -0.056 |
help | -0.054 |
day | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
t | +0.194 |
happened | +0.186 |
help | +0.178 |
day | +0.174 |
please | +0.171 |
Neg logit contributions | |
necks | -0.335 |
aron | -0.333 |
cks | -0.333 |
opes | -0.332 |
ping | -0.331 |
Token | journal |
Token ID | 3989 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
cks | +0.024 |
necks | +0.024 |
aron | +0.024 |
opes | +0.024 |
ping | +0.024 |
Neg logit contributions | |
t | -0.021 |
happened | -0.021 |
help | -0.020 |
day | -0.020 |
please | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
t | +0.046 |
happened | +0.045 |
help | +0.043 |
day | +0.043 |
please | +0.042 |
Neg logit contributions | |
cks | -0.035 |
aron | -0.035 |
necks | -0.035 |
opes | -0.035 |
ping | -0.034 |
Token | understood |
Token ID | 7247 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
necks | +0.516 |
cks | +0.513 |
uted | +0.512 |
aron | +0.510 |
ping | +0.509 |
Neg logit contributions | |
t | -0.357 |
happened | -0.315 |
day | -0.314 |
week | -0.309 |
please | -0.304 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
t | +0.218 |
happened | +0.195 |
day | +0.194 |
week | +0.192 |
ha | +0.189 |
Neg logit contributions | |
aron | -0.222 |
cks | -0.219 |
uted | -0.218 |
necks | -0.214 |
opes | -0.214 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
spots | +0.198 |
circles | +0.195 |
shapes | +0.194 |
bes | +0.192 |
piles | +0.185 |
Neg logit contributions | |
bye | -0.166 |
reward | -0.164 |
inconvenience | -0.161 |
ye | -0.160 |
use | -0.154 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.736 |
happened | +0.703 |
help | +0.676 |
day | +0.671 |
please | +0.656 |
Neg logit contributions | |
cks | -0.867 |
necks | -0.863 |
opes | -0.861 |
aron | -0.860 |
valleys | -0.854 |
Token | She |
Token ID | 1375 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
cks | +0.070 |
ping | +0.069 |
necks | +0.069 |
opes | +0.068 |
aron | +0.067 |
Neg logit contributions | |
t | -0.082 |
happened | -0.080 |
help | -0.077 |
please | -0.076 |
day | -0.076 |
Token | hugged |
Token ID | 41130 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
aron | +0.223 |
uted | +0.220 |
necks | +0.218 |
cks | +0.217 |
ping | +0.215 |
Neg logit contributions | |
t | -0.130 |
day | -0.120 |
week | -0.118 |
happened | -0.117 |
help | -0.112 |
Token | Anna |
Token ID | 11735 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
cks | +0.086 |
necks | +0.085 |
opes | +0.085 |
aron | +0.085 |
ping | +0.085 |
Neg logit contributions | |
t | -0.052 |
happened | -0.049 |
help | -0.047 |
day | -0.046 |
please | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
help | +0.247 |
t | +0.246 |
day | +0.246 |
would | +0.232 |
thank | +0.230 |
Neg logit contributions | |
cks | -0.294 |
opes | -0.287 |
valleys | -0.284 |
aters | -0.264 |
necks | -0.263 |
Token | told |
Token ID | 1297 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
necks | +0.497 |
aron | +0.485 |
valleys | +0.479 |
cks | +0.478 |
uted | +0.474 |
Neg logit contributions | |
t | -0.338 |
happened | -0.317 |
day | -0.299 |
week | -0.294 |
please | -0.293 |
Token | Mom |
Token ID | 11254 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
t | +0.374 |
happened | +0.338 |
awaited | +0.322 |
ha | +0.316 |
week | +0.310 |
Neg logit contributions | |
necks | -0.412 |
opes | -0.408 |
ping | -0.405 |
cks | -0.404 |
uted | -0.404 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
t | +0.330 |
happened | +0.317 |
help | +0.298 |
day | +0.295 |
reward | +0.294 |
Neg logit contributions | |
necks | -0.341 |
ping | -0.339 |
aron | -0.339 |
opes | -0.337 |
uted | -0.336 |
Token | Dad |
Token ID | 17415 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
necks | +0.415 |
uted | +0.392 |
wrists | +0.391 |
aron | +0.381 |
ksh | +0.379 |
Neg logit contributions | |
t | -0.456 |
ha | -0.427 |
awaited | -0.395 |
problem | -0.391 |
reward | -0.381 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
t | +0.231 |
happened | +0.215 |
ha | +0.208 |
reward | +0.202 |
please | +0.201 |
Neg logit contributions | |
necks | -0.252 |
ping | -0.251 |
uted | -0.250 |
aron | -0.247 |
cks | -0.245 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
uted | +0.283 |
spots | +0.268 |
cks | +0.265 |
stripes | +0.264 |
strings | +0.259 |
Neg logit contributions | |
use | -0.118 |
t | -0.112 |
ha | -0.108 |
reward | -0.106 |
please | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.728 |
happened | +0.697 |
help | +0.673 |
day | +0.669 |
please | +0.652 |
Neg logit contributions | |
cks | -0.880 |
opes | -0.876 |
necks | -0.875 |
aron | -0.874 |
valleys | -0.867 |
Token | Mom |
Token ID | 11254 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
cks | +0.081 |
ping | +0.080 |
necks | +0.077 |
opes | +0.077 |
uted | +0.077 |
Neg logit contributions | |
t | -0.073 |
happened | -0.072 |
day | -0.070 |
please | -0.070 |
week | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
t | +0.425 |
happened | +0.412 |
help | +0.401 |
day | +0.399 |
please | +0.394 |
Neg logit contributions | |
cks | -0.248 |
necks | -0.245 |
opes | -0.244 |
aron | -0.243 |
ping | -0.241 |
Token | Dad |
Token ID | 17415 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
necks | +0.513 |
uted | +0.490 |
rily | +0.490 |
aron | +0.488 |
ping | +0.486 |
Neg logit contributions | |
t | -0.372 |
happened | -0.331 |
ha | -0.323 |
awaited | -0.320 |
day | -0.312 |
Token | were |
Token ID | 547 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
t | +0.193 |
happened | +0.173 |
week | +0.172 |
day | +0.171 |
please | +0.166 |
Neg logit contributions | |
uted | -0.291 |
aron | -0.291 |
necks | -0.288 |
ping | -0.283 |
cks | -0.283 |
Token | them |
Token ID | 606 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
help | +0.116 |
please | +0.110 |
day | +0.108 |
t | +0.108 |
happened | +0.108 |
Neg logit contributions | |
cks | -0.187 |
opes | -0.185 |
aters | -0.183 |
aron | -0.183 |
valleys | -0.182 |
Token | and |
Token ID | 290 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
valleys | +0.088 |
cks | +0.088 |
opes | +0.084 |
necks | +0.080 |
rily | +0.080 |
Neg logit contributions | |
help | -0.072 |
day | -0.070 |
t | -0.069 |
thank | -0.067 |
to | -0.065 |
Token | tell |
Token ID | 1560 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
necks | +0.608 |
cks | +0.608 |
aron | +0.603 |
opes | +0.598 |
uted | +0.596 |
Neg logit contributions | |
t | -0.266 |
happened | -0.240 |
day | -0.221 |
week | -0.213 |
please | -0.212 |
Token | them |
Token ID | 606 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
t | +0.240 |
happened | +0.217 |
ha | +0.211 |
awaited | +0.210 |
reward | +0.209 |
Neg logit contributions | |
cks | -0.178 |
ping | -0.177 |
necks | -0.177 |
uted | -0.176 |
opes | -0.175 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
uted | +0.083 |
opes | +0.083 |
necks | +0.083 |
cks | +0.083 |
ping | +0.082 |
Neg logit contributions | |
t | -0.064 |
happened | -0.060 |
day | -0.058 |
reward | -0.058 |
awaited | -0.057 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
cks | +0.253 |
spots | +0.250 |
necks | +0.243 |
valleys | +0.242 |
circles | +0.239 |
Neg logit contributions | |
reward | -0.123 |
t | -0.118 |
please | -0.118 |
ha | -0.117 |
ipop | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.733 |
happened | +0.702 |
help | +0.676 |
day | +0.672 |
please | +0.657 |
Neg logit contributions | |
cks | -0.866 |
necks | -0.865 |
aron | -0.864 |
opes | -0.863 |
valleys | -0.854 |
Token | Mom |
Token ID | 11254 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
ping | +0.067 |
cks | +0.066 |
opes | +0.065 |
rily | +0.065 |
uted | +0.064 |
Neg logit contributions | |
t | -0.086 |
happened | -0.085 |
day | -0.081 |
help | -0.081 |
please | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
t | +0.346 |
happened | +0.344 |
help | +0.338 |
would | +0.337 |
day | +0.329 |
Neg logit contributions | |
rily | -0.321 |
valleys | -0.315 |
opes | -0.307 |
cks | -0.304 |
ping | -0.303 |
Token | dad |
Token ID | 9955 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
necks | +0.544 |
valleys | +0.517 |
opes | +0.511 |
cks | +0.511 |
ping | +0.510 |
Neg logit contributions | |
t | -0.363 |
happened | -0.311 |
ha | -0.299 |
awaited | -0.298 |
reward | -0.297 |
Token | are |
Token ID | 389 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
t | +0.157 |
happened | +0.147 |
day | +0.138 |
help | +0.137 |
please | +0.134 |
Neg logit contributions | |
cks | -0.326 |
necks | -0.324 |
aron | -0.324 |
opes | -0.322 |
uted | -0.321 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
aron | +0.199 |
ping | +0.199 |
necks | +0.197 |
opes | +0.196 |
uted | +0.196 |
Neg logit contributions | |
t | -0.275 |
happened | -0.263 |
help | -0.255 |
day | -0.251 |
reward | -0.251 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ping | +0.478 |
necks | +0.475 |
valleys | +0.472 |
cks | +0.463 |
opes | +0.460 |
Neg logit contributions | |
t | -0.384 |
reward | -0.340 |
ha | -0.337 |
happened | -0.335 |
awaited | -0.322 |
Token | 't |
Token ID | 470 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
t | +0.043 |
happened | +0.042 |
day | +0.038 |
help | +0.037 |
week | +0.036 |
Neg logit contributions | |
cks | -0.162 |
uted | -0.161 |
opes | -0.161 |
aron | -0.160 |
ping | -0.159 |
Token | know |
Token ID | 760 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
t | +0.276 |
happened | +0.251 |
awaited | +0.243 |
day | +0.227 |
reward | +0.226 |
Neg logit contributions | |
ping | -0.460 |
aron | -0.459 |
cks | -0.442 |
necks | -0.436 |
uted | -0.433 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
t | +0.307 |
happened | +0.281 |
day | +0.272 |
week | +0.268 |
please | +0.265 |
Neg logit contributions | |
cks | -0.344 |
necks | -0.339 |
opes | -0.339 |
uted | -0.339 |
valleys | -0.337 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
necks | +0.223 |
valleys | +0.217 |
neck | +0.214 |
bes | +0.214 |
spots | +0.212 |
Neg logit contributions | |
t | -0.157 |
reward | -0.151 |
ll | -0.148 |
ipop | -0.144 |
inconvenience | -0.141 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
t | +0.666 |
happened | +0.647 |
reward | +0.631 |
help | +0.616 |
awaited | +0.612 |
Neg logit contributions | |
necks | -0.871 |
ping | -0.870 |
cks | -0.870 |
uted | -0.865 |
aron | -0.863 |
Token | her |
Token ID | 607 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
t | +0.482 |
happened | +0.432 |
ha | +0.417 |
week | +0.406 |
day | +0.405 |
Neg logit contributions | |
cks | -0.514 |
opes | -0.501 |
ping | -0.501 |
necks | -0.496 |
uted | -0.496 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
necks | +0.007 |
opes | +0.007 |
aron | +0.007 |
cks | +0.007 |
ping | +0.007 |
Neg logit contributions | |
t | -0.006 |
happened | -0.006 |
please | -0.005 |
help | -0.005 |
day | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | +8.02e+00 |
Pos logit contributions | |
cks | +0.080 |
necks | +0.078 |
ping | +0.078 |
opes | +0.078 |
aron | +0.077 |
Neg logit contributions | |
t | -0.073 |
happened | -0.069 |
day | -0.067 |
help | -0.066 |
please | -0.065 |
Token | missed |
Token ID | 6825 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
necks | +0.428 |
efully | +0.426 |
valleys | +0.426 |
uted | +0.417 |
ping | +0.412 |
Neg logit contributions | |
t | -0.394 |
happened | -0.356 |
week | -0.343 |
day | -0.340 |
awaited | -0.332 |
Token | her |
Token ID | 607 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
help | +0.114 |
please | +0.109 |
day | +0.108 |
happened | +0.106 |
t | +0.106 |
Neg logit contributions | |
cks | -0.192 |
valleys | -0.188 |
opes | -0.187 |
aron | -0.186 |
bes | -0.186 |
Token | and |
Token ID | 290 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
valleys | +0.008 |
cks | +0.008 |
opes | +0.008 |
aters | +0.007 |
necks | +0.007 |
Neg logit contributions | |
help | -0.005 |
thank | -0.005 |
day | -0.005 |
, | -0.005 |
please | -0.005 |
Token | tell |
Token ID | 1560 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
necks | +0.601 |
cks | +0.601 |
aron | +0.596 |
opes | +0.592 |
uted | +0.590 |
Neg logit contributions | |
t | -0.274 |
happened | -0.247 |
day | -0.228 |
week | -0.222 |
please | -0.222 |
Token | her |
Token ID | 607 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
t | +0.246 |
ha | +0.216 |
happened | +0.214 |
awaited | +0.213 |
reward | +0.208 |
Neg logit contributions | |
ping | -0.176 |
uted | -0.174 |
cks | -0.173 |
opes | -0.170 |
ags | -0.169 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
cks | +0.007 |
uted | +0.007 |
rily | +0.007 |
opes | +0.007 |
necks | +0.007 |
Neg logit contributions | |
t | -0.005 |
happened | -0.004 |
ha | -0.004 |
awaited | -0.004 |
day | -0.004 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
valleys | +0.241 |
cks | +0.240 |
spots | +0.239 |
bes | +0.239 |
necks | +0.236 |
Neg logit contributions | |
reward | -0.136 |
please | -0.122 |
ipop | -0.115 |
ha | -0.110 |
t | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.739 |
happened | +0.707 |
help | +0.680 |
day | +0.676 |
please | +0.663 |
Neg logit contributions | |
cks | -0.859 |
necks | -0.858 |
aron | -0.857 |
opes | -0.855 |
ping | -0.847 |
Token |
|
Token ID | 198 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
cks | +0.078 |
necks | +0.077 |
opes | +0.077 |
ping | +0.077 |
aron | +0.077 |
Neg logit contributions | |
t | -0.073 |
happened | -0.070 |
help | -0.067 |
day | -0.067 |
please | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
t | +0.036 |
happened | +0.035 |
help | +0.033 |
day | +0.033 |
please | +0.033 |
Neg logit contributions | |
cks | -0.047 |
necks | -0.047 |
aron | -0.047 |
opes | -0.047 |
ping | -0.046 |
Token | " |
Token ID | 1 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
t | +0.044 |
happened | +0.042 |
help | +0.041 |
day | +0.041 |
please | +0.041 |
Neg logit contributions | |
opes | -0.039 |
ping | -0.039 |
cks | -0.039 |
necks | -0.039 |
aron | -0.039 |
Token | Mom |
Token ID | 29252 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
t | +0.126 |
happened | +0.123 |
day | +0.115 |
help | +0.115 |
please | +0.112 |
Neg logit contributions | |
cks | -0.133 |
opes | -0.132 |
rily | -0.130 |
necks | -0.130 |
ping | -0.130 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
cks | +0.132 |
valleys | +0.128 |
necks | +0.128 |
opes | +0.126 |
bes | +0.125 |
Neg logit contributions | |
t | -0.126 |
help | -0.121 |
day | -0.120 |
please | -0.119 |
happened | -0.117 |
Token | came |
Token ID | 1625 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
cks | +0.591 |
ping | +0.585 |
valleys | +0.581 |
aron | +0.576 |
necks | +0.571 |
Neg logit contributions | |
t | -0.288 |
week | -0.252 |
day | -0.252 |
reward | -0.245 |
happened | -0.230 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
t | +0.236 |
help | +0.232 |
happened | +0.217 |
day | +0.213 |
please | +0.206 |
Neg logit contributions | |
opes | -0.624 |
aron | -0.624 |
necks | -0.619 |
cks | -0.619 |
rily | -0.617 |
Token | see |
Token ID | 766 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
t | +0.380 |
happened | +0.333 |
day | +0.319 |
week | +0.307 |
problem | +0.302 |
Neg logit contributions | |
valleys | -0.611 |
cks | -0.609 |
necks | -0.606 |
aron | -0.599 |
ping | -0.597 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
t | +0.122 |
happened | +0.117 |
help | +0.114 |
day | +0.110 |
please | +0.109 |
Neg logit contributions | |
necks | -0.186 |
aron | -0.186 |
cks | -0.185 |
opes | -0.185 |
ping | -0.184 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
cks | +0.159 |
valleys | +0.156 |
bes | +0.144 |
spots | +0.142 |
circles | +0.138 |
Neg logit contributions | |
reward | -0.246 |
inconvenience | -0.227 |
wait | -0.223 |
exam | -0.219 |
please | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.724 |
happened | +0.691 |
help | +0.666 |
day | +0.661 |
please | +0.647 |
Neg logit contributions | |
cks | -0.882 |
opes | -0.879 |
necks | -0.877 |
aron | -0.873 |
uted | -0.869 |
Token | She |
Token ID | 1375 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
cks | +0.067 |
aron | +0.066 |
ping | +0.066 |
uted | +0.066 |
rily | +0.065 |
Neg logit contributions | |
t | -0.084 |
happened | -0.082 |
help | -0.080 |
please | -0.079 |
day | -0.079 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
aron | +0.222 |
necks | +0.221 |
cks | +0.218 |
uted | +0.216 |
valleys | +0.215 |
Neg logit contributions | |
t | -0.132 |
day | -0.119 |
week | -0.117 |
happened | -0.115 |
reward | -0.110 |
Token | Fl |
Token ID | 1610 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
t | +0.175 |
happened | +0.171 |
help | +0.164 |
day | +0.157 |
please | +0.154 |
Neg logit contributions | |
aron | -0.353 |
necks | -0.351 |
opes | -0.347 |
cks | -0.346 |
ping | -0.345 |
Token | uffy |
Token ID | 15352 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
t | +0.001 |
happened | +0.001 |
help | +0.001 |
please | +0.001 |
day | +0.001 |
Neg logit contributions | |
aron | -0.003 |
valleys | -0.003 |
cks | -0.003 |
necks | -0.003 |
ping | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
t | +0.038 |
happened | +0.037 |
help | +0.035 |
day | +0.035 |
please | +0.034 |
Neg logit contributions | |
cks | -0.045 |
aron | -0.045 |
necks | -0.045 |
uted | -0.045 |
opes | -0.045 |
Token | But |
Token ID | 1537 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
t | +0.051 |
help | +0.047 |
happened | +0.046 |
please | +0.046 |
day | +0.046 |
Neg logit contributions | |
cks | -0.035 |
ping | -0.035 |
necks | -0.035 |
opes | -0.035 |
rily | -0.034 |
Token | then |
Token ID | 788 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
necks | +0.248 |
valleys | +0.246 |
ping | +0.239 |
uted | +0.234 |
rily | +0.234 |
Neg logit contributions | |
t | -0.318 |
happened | -0.291 |
awaited | -0.278 |
help | -0.275 |
week | -0.270 |
Token | something |
Token ID | 1223 |
Feature activation | +8.16e+00 |
Pos logit contributions | |
valleys | +0.154 |
necks | +0.147 |
opes | +0.143 |
neck | +0.140 |
rivers | +0.140 |
Neg logit contributions | |
t | -0.094 |
week | -0.074 |
happened | -0.071 |
ll | -0.070 |
day | -0.070 |
Token | magical |
Token ID | 10883 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ping | +0.407 |
valleys | +0.392 |
cks | +0.391 |
uted | +0.390 |
aron | +0.376 |
Neg logit contributions | |
t | -0.396 |
please | -0.362 |
week | -0.357 |
we | -0.344 |
reward | -0.339 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
t | +0.023 |
please | +0.020 |
week | +0.019 |
help | +0.019 |
thank | +0.016 |
Neg logit contributions | |
ping | -0.119 |
uted | -0.117 |
aron | -0.115 |
opes | -0.115 |
edly | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.677 |
happened | +0.661 |
help | +0.624 |
day | +0.615 |
please | +0.608 |
Neg logit contributions | |
aron | -0.930 |
cks | -0.928 |
necks | -0.928 |
opes | -0.924 |
aters | -0.917 |
Token | A |
Token ID | 317 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
cks | +0.086 |
necks | +0.083 |
ping | +0.080 |
opes | +0.079 |
uted | +0.078 |
Neg logit contributions | |
t | -0.072 |
happened | -0.069 |
please | -0.068 |
help | -0.066 |
week | -0.066 |
Token | rainbow |
Token ID | 27223 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
valleys | +0.210 |
aron | +0.196 |
unison | +0.194 |
strings | +0.193 |
neck | +0.192 |
Neg logit contributions | |
t | -0.260 |
happened | -0.231 |
awaited | -0.223 |
ll | -0.219 |
help | -0.214 |
Token | appeared |
Token ID | 4120 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
ping | +0.157 |
cks | +0.155 |
uted | +0.154 |
valleys | +0.154 |
opes | +0.153 |
Neg logit contributions | |
t | -0.103 |
help | -0.096 |
please | -0.095 |
week | -0.092 |
day | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
t | +0.214 |
happened | +0.210 |
help | +0.197 |
day | +0.194 |
please | +0.194 |
Neg logit contributions | |
necks | -0.323 |
cks | -0.319 |
bes | -0.312 |
opes | -0.307 |
aron | -0.305 |
Token | my |
Token ID | 1820 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
t | +0.420 |
happened | +0.402 |
help | +0.382 |
day | +0.378 |
please | +0.373 |
Neg logit contributions | |
cks | -0.555 |
aron | -0.554 |
necks | -0.554 |
ping | -0.554 |
opes | -0.550 |
Token | and |
Token ID | 290 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
t | +0.109 |
happened | +0.103 |
day | +0.101 |
reward | +0.101 |
week | +0.100 |
Neg logit contributions | |
aron | -0.096 |
ping | -0.096 |
uted | -0.094 |
necks | -0.094 |
opes | -0.093 |
Token | daddy |
Token ID | 35822 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
opes | +0.533 |
necks | +0.532 |
ping | +0.528 |
uted | +0.519 |
piles | +0.509 |
Neg logit contributions | |
t | -0.363 |
ha | -0.298 |
reward | -0.296 |
contest | -0.270 |
happened | -0.268 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
t | +0.166 |
reward | +0.157 |
day | +0.149 |
week | +0.148 |
happened | +0.146 |
Neg logit contributions | |
ping | -0.303 |
uted | -0.303 |
aron | -0.298 |
necks | -0.290 |
opes | -0.286 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
t | +0.230 |
happened | +0.212 |
day | +0.205 |
help | +0.203 |
reward | +0.200 |
Neg logit contributions | |
cks | -0.305 |
ping | -0.301 |
opes | -0.301 |
uted | -0.301 |
necks | -0.298 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
bes | +0.231 |
uted | +0.227 |
strings | +0.224 |
spots | +0.223 |
cks | +0.219 |
Neg logit contributions | |
reward | -0.159 |
please | -0.144 |
thank | -0.135 |
ye | -0.134 |
inconvenience | -0.133 |
Token | and |
Token ID | 290 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
t | +0.874 |
happened | +0.822 |
day | +0.815 |
help | +0.805 |
week | +0.782 |
Neg logit contributions | |
cks | -0.780 |
valleys | -0.777 |
aters | -0.762 |
opes | -0.756 |
necks | -0.755 |
Token | they |
Token ID | 484 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
ping | +0.532 |
uted | +0.517 |
aron | +0.502 |
valleys | +0.501 |
cks | +0.496 |
Neg logit contributions | |
t | -0.342 |
reward | -0.302 |
week | -0.280 |
day | -0.277 |
please | -0.274 |
Token | discuss |
Token ID | 2112 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
t | +0.168 |
happened | +0.154 |
day | +0.149 |
week | +0.146 |
help | +0.145 |
Neg logit contributions | |
uted | -0.246 |
ping | -0.245 |
cks | -0.245 |
necks | -0.244 |
opes | -0.243 |
Token | how |
Token ID | 703 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
t | +0.084 |
happened | +0.083 |
help | +0.080 |
day | +0.079 |
please | +0.077 |
Neg logit contributions | |
aron | -0.125 |
cks | -0.125 |
necks | -0.124 |
opes | -0.124 |
ping | -0.124 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
ping | +0.705 |
uted | +0.671 |
cks | +0.667 |
valleys | +0.661 |
necks | +0.645 |
Neg logit contributions | |
reward | -0.469 |
awaited | -0.414 |
please | -0.406 |
ha | -0.406 |
happened | -0.400 |
Token | but |
Token ID | 475 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
t | +0.357 |
help | +0.354 |
please | +0.348 |
happened | +0.344 |
day | +0.343 |
Neg logit contributions | |
cks | -0.389 |
aters | -0.374 |
rily | -0.374 |
opes | -0.373 |
uted | -0.371 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
necks | +0.341 |
uted | +0.340 |
valleys | +0.337 |
rily | +0.332 |
opes | +0.328 |
Neg logit contributions | |
t | -0.260 |
ha | -0.232 |
happened | -0.232 |
help | -0.218 |
awaited | -0.217 |
Token | 't |
Token ID | 470 |
Feature activation | -7.16e+00 |
Pos logit contributions | |
t | +0.044 |
happened | +0.039 |
help | +0.036 |
day | +0.035 |
please | +0.034 |
Neg logit contributions | |
necks | -0.168 |
cks | -0.167 |
aron | -0.167 |
opes | -0.166 |
ping | -0.166 |
Token | know |
Token ID | 760 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
t | +0.282 |
happened | +0.276 |
ha | +0.267 |
awaited | +0.258 |
day | +0.241 |
Neg logit contributions | |
aron | -0.433 |
ping | -0.427 |
cks | -0.410 |
uted | -0.408 |
rily | -0.408 |
Token | what |
Token ID | 644 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
t | +0.305 |
happened | +0.284 |
help | +0.274 |
day | +0.274 |
please | +0.270 |
Neg logit contributions | |
cks | -0.342 |
opes | -0.339 |
necks | -0.338 |
uted | -0.337 |
aron | -0.336 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
valleys | +0.272 |
cks | +0.267 |
opes | +0.266 |
necks | +0.266 |
aron | +0.258 |
Neg logit contributions | |
t | -0.158 |
reward | -0.135 |
please | -0.126 |
ha | -0.125 |
thank | -0.122 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
t | +0.677 |
happened | +0.644 |
help | +0.617 |
reward | +0.607 |
day | +0.606 |
Neg logit contributions | |
cks | -0.897 |
necks | -0.886 |
ping | -0.886 |
aron | -0.883 |
uted | -0.883 |
Token | the |
Token ID | 262 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
t | +0.425 |
happened | +0.394 |
day | +0.369 |
help | +0.362 |
week | +0.361 |
Neg logit contributions | |
cks | -0.565 |
opes | -0.552 |
ping | -0.550 |
uted | -0.550 |
necks | -0.549 |
Token | box |
Token ID | 3091 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
necks | +0.023 |
cks | +0.023 |
aron | +0.023 |
opes | +0.023 |
ping | +0.023 |
Neg logit contributions | |
t | -0.022 |
happened | -0.021 |
help | -0.020 |
day | -0.020 |
please | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.116 |
happened | +0.112 |
help | +0.106 |
ha | +0.105 |
day | +0.104 |
Neg logit contributions | |
ping | -0.129 |
cks | -0.129 |
rily | -0.129 |
uted | -0.127 |
aron | -0.127 |
Token | James |
Token ID | 3700 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
cks | +0.074 |
ping | +0.072 |
necks | +0.072 |
aron | +0.071 |
opes | +0.071 |
Neg logit contributions | |
t | -0.080 |
happened | -0.075 |
day | -0.073 |
help | -0.072 |
please | -0.072 |
Token | depend |
Token ID | 4745 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
aron | +0.291 |
uted | +0.283 |
rily | +0.280 |
ping | +0.279 |
valleys | +0.279 |
Neg logit contributions | |
t | -0.232 |
happened | -0.214 |
help | -0.205 |
please | -0.200 |
awaited | -0.199 |
Token | able |
Token ID | 540 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
aron | +0.060 |
cks | +0.057 |
inning | +0.057 |
ping | +0.054 |
rily | +0.053 |
Neg logit contributions | |
help | -0.089 |
thank | -0.088 |
please | -0.087 |
t | -0.086 |
reward | -0.086 |
Token | day |
Token ID | 1110 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
t | +0.227 |
happened | +0.207 |
help | +0.192 |
awaited | +0.190 |
please | +0.188 |
Neg logit contributions | |
aron | -0.325 |
rily | -0.315 |
ping | -0.311 |
aters | -0.310 |
necks | -0.309 |
Token | of |
Token ID | 286 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
t | +0.681 |
happened | +0.671 |
help | +0.634 |
reward | +0.622 |
awaited | +0.613 |
Neg logit contributions | |
aron | -0.818 |
ping | -0.802 |
necks | -0.798 |
cks | -0.794 |
uted | -0.791 |
Token | the |
Token ID | 262 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
t | +0.302 |
happened | +0.281 |
help | +0.265 |
day | +0.262 |
please | +0.259 |
Neg logit contributions | |
cks | -0.449 |
opes | -0.445 |
necks | -0.445 |
ping | -0.443 |
aron | -0.442 |
Token | week |
Token ID | 1285 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
valleys | +0.026 |
opes | +0.026 |
ping | +0.026 |
necks | +0.025 |
aron | +0.025 |
Neg logit contributions | |
t | -0.019 |
happened | -0.017 |
please | -0.016 |
help | -0.016 |
awaited | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.772 |
happened | +0.740 |
help | +0.712 |
please | +0.695 |
day | +0.689 |
Neg logit contributions | |
aron | -0.812 |
necks | -0.805 |
cks | -0.801 |
ping | -0.799 |
opes | -0.797 |
Token | It |
Token ID | 632 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
cks | +0.089 |
necks | +0.088 |
ping | +0.088 |
opes | +0.087 |
uted | +0.086 |
Neg logit contributions | |
t | -0.063 |
please | -0.059 |
help | -0.058 |
happened | -0.057 |
day | -0.057 |
Token | 's |
Token ID | 338 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
aron | +0.263 |
cks | +0.262 |
opes | +0.261 |
valleys | +0.261 |
ping | +0.260 |
Neg logit contributions | |
t | -0.196 |
happened | -0.184 |
help | -0.178 |
please | -0.176 |
day | -0.174 |
Token | a |
Token ID | 257 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
t | +0.018 |
happened | +0.018 |
day | +0.018 |
help | +0.017 |
please | +0.017 |
Neg logit contributions | |
necks | -0.032 |
cks | -0.032 |
opes | -0.032 |
uted | -0.032 |
ping | -0.031 |
Token | day |
Token ID | 1110 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
aron | +0.261 |
valleys | +0.260 |
unison | +0.259 |
necks | +0.256 |
opes | +0.246 |
Neg logit contributions | |
t | -0.238 |
happened | -0.225 |
awaited | -0.206 |
help | -0.196 |
ha | -0.192 |
Token | the |
Token ID | 262 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
t | +0.380 |
happened | +0.349 |
help | +0.324 |
day | +0.322 |
please | +0.321 |
Neg logit contributions | |
cks | -0.604 |
necks | -0.600 |
opes | -0.597 |
ping | -0.597 |
valleys | -0.596 |
Token | spring |
Token ID | 6076 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
necks | +0.028 |
valleys | +0.027 |
uted | +0.027 |
opes | +0.027 |
ping | +0.027 |
Neg logit contributions | |
t | -0.018 |
happened | -0.017 |
please | -0.016 |
help | -0.015 |
awaited | -0.015 |
Token | class |
Token ID | 1398 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
aron | +0.226 |
valleys | +0.225 |
necks | +0.225 |
ping | +0.224 |
aters | +0.223 |
Neg logit contributions | |
t | -0.133 |
happened | -0.132 |
help | -0.121 |
please | -0.116 |
thank | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
t | +0.132 |
happened | +0.130 |
help | +0.123 |
please | +0.120 |
day | +0.118 |
Neg logit contributions | |
aron | -0.140 |
necks | -0.139 |
valleys | -0.136 |
ping | -0.135 |
uted | -0.135 |
Token | next |
Token ID | 1306 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
necks | +0.027 |
valleys | +0.027 |
ping | +0.026 |
opes | +0.026 |
cks | +0.026 |
Neg logit contributions | |
t | -0.019 |
happened | -0.019 |
please | -0.017 |
help | -0.017 |
awaited | -0.017 |
Token | week |
Token ID | 1285 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
t | +0.131 |
happened | +0.129 |
please | +0.103 |
awaited | +0.100 |
thank | +0.096 |
Neg logit contributions | |
valleys | -0.371 |
necks | -0.368 |
aron | -0.363 |
efully | -0.362 |
unison | -0.362 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.786 |
happened | +0.754 |
help | +0.726 |
please | +0.711 |
day | +0.703 |
Neg logit contributions | |
aron | -0.794 |
necks | -0.792 |
valleys | -0.783 |
ping | -0.782 |
opes | -0.776 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
cks | +0.081 |
aron | +0.081 |
necks | +0.081 |
opes | +0.080 |
uted | +0.080 |
Neg logit contributions | |
t | -0.068 |
happened | -0.065 |
help | -0.063 |
day | -0.062 |
please | -0.061 |
Token | Once |
Token ID | 7454 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
necks | +0.089 |
cks | +0.089 |
opes | +0.089 |
ping | +0.088 |
aron | +0.087 |
Neg logit contributions | |
t | -0.065 |
happened | -0.062 |
day | -0.060 |
help | -0.058 |
week | -0.058 |
Token | upon |
Token ID | 2402 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
reward | +0.217 |
help | +0.203 |
inconvenience | +0.200 |
wait | +0.196 |
ha | +0.194 |
Neg logit contributions | |
rily | -0.095 |
cks | -0.089 |
valleys | -0.085 |
uted | -0.082 |
piles | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
opes | +0.434 |
aters | +0.432 |
necks | +0.431 |
cks | +0.427 |
rily | +0.420 |
Neg logit contributions | |
happened | -0.253 |
t | -0.249 |
day | -0.244 |
help | -0.243 |
please | -0.225 |
Token | his |
Token ID | 465 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
t | +0.035 |
happened | +0.034 |
day | +0.033 |
help | +0.033 |
please | +0.032 |
Neg logit contributions | |
cks | -0.046 |
necks | -0.046 |
aron | -0.046 |
opes | -0.046 |
uted | -0.046 |
Token | favourite |
Token ID | 12507 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
necks | +0.170 |
opes | +0.169 |
cks | +0.169 |
aron | +0.169 |
ping | +0.168 |
Neg logit contributions | |
t | -0.113 |
happened | -0.108 |
help | -0.102 |
day | -0.100 |
please | -0.099 |
Token | day |
Token ID | 1110 |
Feature activation | -1.48e+01 |
Pos logit contributions | |
cks | +0.148 |
necks | +0.145 |
aron | +0.145 |
uted | +0.144 |
valleys | +0.144 |
Neg logit contributions | |
t | -0.096 |
happened | -0.092 |
day | -0.091 |
help | -0.089 |
week | -0.087 |
Token | of |
Token ID | 286 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
t | +0.679 |
happened | +0.652 |
help | +0.624 |
please | +0.611 |
day | +0.608 |
Neg logit contributions | |
cks | -0.828 |
opes | -0.827 |
necks | -0.827 |
ping | -0.826 |
aron | -0.823 |
Token | the |
Token ID | 262 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
happened | +0.292 |
day | +0.292 |
t | +0.287 |
help | +0.286 |
week | +0.278 |
Neg logit contributions | |
aron | -0.449 |
cks | -0.449 |
necks | -0.444 |
uted | -0.442 |
rily | -0.442 |
Token | week |
Token ID | 1285 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
necks | +0.024 |
opes | +0.024 |
aron | +0.024 |
ping | +0.024 |
cks | +0.023 |
Neg logit contributions | |
t | -0.022 |
happened | -0.021 |
help | -0.020 |
please | -0.020 |
day | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.722 |
happened | +0.695 |
day | +0.677 |
help | +0.668 |
week | +0.655 |
Neg logit contributions | |
cks | -0.878 |
necks | -0.867 |
opes | -0.863 |
aron | -0.863 |
uted | -0.860 |
Token | One |
Token ID | 1881 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
cks | +0.081 |
ping | +0.080 |
uted | +0.080 |
necks | +0.080 |
rily | +0.079 |
Neg logit contributions | |
t | -0.070 |
happened | -0.067 |
day | -0.066 |
help | -0.065 |
please | -0.064 |
Token | Sunday |
Token ID | 3502 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
ping | +0.127 |
aron | +0.127 |
inning | +0.125 |
aters | +0.123 |
ady | +0.123 |
Neg logit contributions | |
t | -0.029 |
happened | -0.026 |
help | -0.022 |
reward | -0.022 |
please | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -7.17e+00 |
Pos logit contributions | |
t | +0.171 |
help | +0.165 |
please | +0.165 |
thank | +0.151 |
reward | +0.146 |
Neg logit contributions | |
aron | -0.292 |
valleys | -0.291 |
aters | -0.284 |
fields | -0.275 |
ping | -0.273 |
Token | Jake |
Token ID | 14757 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
t | +0.297 |
happened | +0.282 |
help | +0.263 |
reward | +0.259 |
ha | +0.258 |
Neg logit contributions | |
opes | -0.432 |
necks | -0.431 |
cks | -0.430 |
valleys | -0.429 |
uted | -0.425 |
Token | could |
Token ID | 714 |
Feature activation | -7.97e+00 |
Pos logit contributions | |
necks | +0.231 |
opes | +0.227 |
cks | +0.226 |
ping | +0.226 |
aron | +0.224 |
Neg logit contributions | |
t | -0.131 |
happened | -0.118 |
help | -0.116 |
please | -0.114 |
day | -0.114 |
Token | not |
Token ID | 407 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
t | +0.284 |
happened | +0.275 |
day | +0.257 |
week | +0.253 |
awaited | +0.250 |
Neg logit contributions | |
cks | -0.530 |
necks | -0.526 |
ping | -0.523 |
opes | -0.522 |
aron | -0.521 |
Token | hop |
Token ID | 1725 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
cks | +0.055 |
necks | +0.055 |
aron | +0.055 |
ping | +0.055 |
opes | +0.054 |
Neg logit contributions | |
t | -0.036 |
happened | -0.036 |
day | -0.033 |
week | -0.032 |
help | -0.032 |
Token | for |
Token ID | 329 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
cks | +0.226 |
necks | +0.225 |
aron | +0.224 |
opes | +0.224 |
uted | +0.222 |
Neg logit contributions | |
t | -0.202 |
happened | -0.192 |
help | -0.186 |
day | -0.185 |
please | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
t | +0.240 |
happened | +0.228 |
day | +0.214 |
please | +0.213 |
awaited | +0.213 |
Neg logit contributions | |
necks | -0.240 |
cks | -0.238 |
ping | -0.237 |
opes | -0.236 |
valleys | -0.234 |
Token | week |
Token ID | 1285 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
neck | +0.239 |
valleys | +0.224 |
moss | +0.223 |
necks | +0.222 |
tail | +0.222 |
Neg logit contributions | |
happened | -0.242 |
awaited | -0.237 |
done | -0.214 |
happens | -0.214 |
t | -0.210 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
t | +0.729 |
happened | +0.698 |
help | +0.673 |
day | +0.668 |
please | +0.656 |
Neg logit contributions | |
cks | -0.863 |
necks | -0.858 |
aron | -0.856 |
opes | -0.854 |
uted | -0.849 |
Token | Ho |
Token ID | 9544 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
cks | +0.083 |
uted | +0.080 |
aron | +0.078 |
necks | +0.077 |
valleys | +0.077 |
Neg logit contributions | |
t | -0.071 |
help | -0.068 |
please | -0.067 |
day | -0.065 |
happened | -0.065 |
Token | ppy |
Token ID | 14097 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
t | +0.029 |
happened | +0.027 |
help | +0.026 |
please | +0.025 |
day | +0.025 |
Neg logit contributions | |
cks | -0.035 |
valleys | -0.035 |
uted | -0.035 |
necks | -0.035 |
aron | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
t | +0.089 |
happened | +0.082 |
help | +0.080 |
please | +0.078 |
day | +0.078 |
Neg logit contributions | |
necks | -0.146 |
opes | -0.143 |
ping | -0.143 |
aron | -0.142 |
valleys | -0.142 |
Token | sad |
Token ID | 6507 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
t | +0.036 |
happened | +0.034 |
help | +0.033 |
day | +0.033 |
please | +0.032 |
Neg logit contributions | |
cks | -0.045 |
necks | -0.045 |
aron | -0.045 |
opes | -0.045 |
uted | -0.044 |
Token | felt |
Token ID | 2936 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
cks | +0.246 |
aters | +0.244 |
aron | +0.243 |
opes | +0.242 |
ping | +0.241 |
Neg logit contributions | |
t | -0.115 |
happened | -0.111 |
help | -0.103 |
day | -0.101 |
please | -0.100 |
Token | sad |
Token ID | 6507 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
aters | +0.373 |
opes | +0.369 |
necks | +0.365 |
aron | +0.362 |
cks | +0.353 |
Neg logit contributions | |
help | -0.237 |
happened | -0.227 |
t | -0.223 |
please | -0.219 |
thank | -0.218 |
Token | and |
Token ID | 290 |
Feature activation | +8.40e+00 |
Pos logit contributions | |
cks | +0.039 |
necks | +0.039 |
opes | +0.038 |
aron | +0.038 |
uted | +0.038 |
Neg logit contributions | |
t | -0.039 |
happened | -0.038 |
help | -0.037 |
day | -0.036 |
please | -0.036 |
Token | wondered |
Token ID | 14028 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
ping | +0.474 |
cks | +0.469 |
necks | +0.466 |
valleys | +0.465 |
uted | +0.458 |
Neg logit contributions | |
t | -0.404 |
happened | -0.359 |
reward | -0.349 |
help | -0.348 |
ha | -0.344 |
Token | what |
Token ID | 644 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
cks | +0.370 |
aron | +0.370 |
ping | +0.369 |
uted | +0.369 |
opes | +0.368 |
Neg logit contributions | |
t | -0.310 |
happened | -0.285 |
day | -0.271 |
week | -0.269 |
reward | -0.263 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
valleys | +0.191 |
rivers | +0.172 |
necks | +0.170 |
cks | +0.168 |
fields | +0.168 |
Neg logit contributions | |
t | -0.225 |
ipop | -0.209 |
ll | -0.208 |
olly | -0.203 |
reward | -0.202 |
Token | to |
Token ID | 284 |
Feature activation | -9.46e+00 |
Pos logit contributions | |
t | +0.649 |
happened | +0.621 |
help | +0.592 |
day | +0.586 |
please | +0.576 |
Neg logit contributions | |
cks | -0.935 |
necks | -0.931 |
aron | -0.929 |
ping | -0.924 |
opes | -0.924 |
Token | the |
Token ID | 262 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
t | +0.438 |
happened | +0.393 |
week | +0.371 |
day | +0.370 |
ha | +0.370 |
Neg logit contributions | |
cks | -0.563 |
ping | -0.553 |
opes | -0.543 |
necks | -0.542 |
uted | -0.541 |
Token | bird |
Token ID | 6512 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
cks | +0.029 |
necks | +0.029 |
aron | +0.029 |
opes | +0.029 |
ping | +0.029 |
Neg logit contributions | |
t | -0.017 |
happened | -0.016 |
help | -0.015 |
day | -0.015 |
please | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
t | +0.319 |
happened | +0.303 |
help | +0.287 |
reward | +0.282 |
day | +0.282 |
Neg logit contributions | |
cks | -0.323 |
ping | -0.323 |
necks | -0.317 |
aron | -0.315 |
uted | -0.314 |
Token | The |
Token ID | 383 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
cks | +0.079 |
opes | +0.078 |
necks | +0.077 |
ping | +0.077 |
uted | +0.077 |
Neg logit contributions | |
t | -0.072 |
happened | -0.067 |
help | -0.066 |
day | -0.065 |
please | -0.065 |
Token | disc |
Token ID | 1221 |
Feature activation | +9.10e+00 |
Pos logit contributions | |
cks | +0.024 |
aron | +0.023 |
opes | +0.023 |
uted | +0.023 |
necks | +0.023 |
Neg logit contributions | |
t | -0.022 |
happened | -0.021 |
help | -0.021 |
day | -0.021 |
week | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
aron | +0.506 |
necks | +0.503 |
opes | +0.502 |
cks | +0.498 |
ping | +0.497 |
Neg logit contributions | |
t | -0.433 |
happened | -0.415 |
help | -0.400 |
day | -0.395 |
please | -0.388 |
Token | He |
Token ID | 679 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
opes | +0.082 |
ping | +0.080 |
cks | +0.077 |
uted | +0.077 |
necks | +0.076 |
Neg logit contributions | |
t | -0.074 |
happened | -0.072 |
please | -0.069 |
day | -0.068 |
help | -0.068 |
Token | understands |
Token ID | 14759 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
rily | +0.263 |
aters | +0.260 |
ping | +0.259 |
aron | +0.258 |
edly | +0.253 |
Neg logit contributions | |
happened | -0.109 |
help | -0.105 |
thank | -0.105 |
problem | -0.101 |
would | -0.099 |
Token | what |
Token ID | 644 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
t | +0.060 |
happened | +0.055 |
day | +0.053 |
help | +0.053 |
week | +0.052 |
Neg logit contributions | |
cks | -0.079 |
aron | -0.079 |
necks | -0.078 |
uted | -0.077 |
ping | -0.077 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
cks | +0.187 |
valleys | +0.178 |
spots | +0.177 |
corners | +0.173 |
yourselves | +0.171 |
Neg logit contributions | |
t | -0.179 |
ha | -0.177 |
reward | -0.167 |
please | -0.163 |
ll | -0.161 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.719 |
happened | +0.682 |
help | +0.657 |
day | +0.655 |
please | +0.637 |
Neg logit contributions | |
opes | -0.889 |
necks | -0.887 |
cks | -0.884 |
aron | -0.880 |
valleys | -0.879 |
Token | He |
Token ID | 679 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
opes | +0.080 |
ping | +0.079 |
cks | +0.078 |
necks | +0.078 |
uted | +0.077 |
Neg logit contributions | |
t | -0.073 |
happened | -0.070 |
please | -0.067 |
day | -0.067 |
help | -0.066 |
Token | is |
Token ID | 318 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
ping | +0.251 |
aters | +0.249 |
rily | +0.249 |
aron | +0.243 |
valleys | +0.241 |
Neg logit contributions | |
happened | -0.118 |
thank | -0.114 |
help | -0.112 |
would | -0.108 |
problem | -0.107 |
Token | not |
Token ID | 407 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
opes | +0.024 |
necks | +0.024 |
aters | +0.023 |
valleys | +0.023 |
aron | +0.023 |
Neg logit contributions | |
t | -0.016 |
happened | -0.015 |
help | -0.015 |
day | -0.014 |
please | -0.014 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
cks | +0.050 |
necks | +0.049 |
aron | +0.049 |
opes | +0.049 |
ping | +0.049 |
Neg logit contributions | |
t | -0.043 |
happened | -0.041 |
help | -0.040 |
day | -0.039 |
please | -0.039 |
Token | put |
Token ID | 1234 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
t | +0.222 |
happened | +0.208 |
help | +0.199 |
day | +0.199 |
week | +0.194 |
Neg logit contributions | |
aron | -0.362 |
necks | -0.361 |
cks | -0.359 |
uted | -0.358 |
opes | -0.358 |
Token | it |
Token ID | 340 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
cks | +0.129 |
necks | +0.128 |
aron | +0.127 |
ping | +0.127 |
valleys | +0.127 |
Neg logit contributions | |
t | -0.059 |
happened | -0.054 |
help | -0.050 |
please | -0.049 |
day | -0.049 |
Token | right |
Token ID | 826 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
t | +0.097 |
happened | +0.094 |
help | +0.090 |
day | +0.089 |
please | +0.088 |
Neg logit contributions | |
cks | -0.101 |
necks | -0.101 |
ping | -0.100 |
aron | -0.100 |
opes | -0.100 |
Token | on |
Token ID | 319 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
t | +0.142 |
happened | +0.136 |
help | +0.131 |
day | +0.131 |
please | +0.128 |
Neg logit contributions | |
cks | -0.159 |
necks | -0.158 |
aron | -0.158 |
opes | -0.157 |
ping | -0.157 |
Token | her |
Token ID | 607 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
t | +0.121 |
day | +0.116 |
happened | +0.116 |
help | +0.114 |
week | +0.112 |
Neg logit contributions | |
cks | -0.173 |
necks | -0.168 |
opes | -0.168 |
uted | -0.166 |
ping | -0.166 |
Token | wrist |
Token ID | 15980 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
necks | +0.019 |
cks | +0.019 |
aron | +0.018 |
opes | +0.018 |
ping | +0.018 |
Neg logit contributions | |
t | -0.027 |
happened | -0.026 |
help | -0.025 |
day | -0.025 |
please | -0.025 |
Token | ! |
Token ID | 0 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
cks | +0.890 |
opes | +0.869 |
necks | +0.868 |
uted | +0.862 |
valleys | +0.861 |
Neg logit contributions | |
t | -0.730 |
happened | -0.683 |
day | -0.669 |
help | -0.665 |
please | -0.651 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
cks | +0.186 |
necks | +0.186 |
aron | +0.185 |
opes | +0.185 |
ping | +0.183 |
Neg logit contributions | |
t | -0.263 |
happened | -0.254 |
help | -0.246 |
day | -0.245 |
please | -0.242 |
Token | Daddy |
Token ID | 26926 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
necks | +0.073 |
opes | +0.072 |
aters | +0.072 |
rily | +0.071 |
ping | +0.070 |
Neg logit contributions | |
t | -0.066 |
happened | -0.061 |
please | -0.058 |
awaited | -0.058 |
ha | -0.058 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.77e+00 |
Pos logit contributions | |
t | +0.132 |
happened | +0.120 |
week | +0.117 |
help | +0.116 |
day | +0.116 |
Neg logit contributions | |
aron | -0.222 |
uted | -0.219 |
necks | -0.216 |
ping | -0.214 |
opes | -0.212 |
Token | it |
Token ID | 340 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
t | +0.213 |
happened | +0.198 |
help | +0.191 |
day | +0.190 |
please | +0.188 |
Neg logit contributions | |
cks | -0.281 |
ping | -0.280 |
opes | -0.280 |
uted | -0.279 |
necks | -0.278 |
Token | slapped |
Token ID | 31213 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
uted | +0.476 |
cks | +0.469 |
ping | +0.467 |
necks | +0.465 |
efully | +0.458 |
Neg logit contributions | |
t | -0.341 |
week | -0.305 |
awaited | -0.303 |
day | -0.292 |
reward | -0.289 |
Token | him |
Token ID | 683 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
t | +0.012 |
happened | +0.012 |
help | +0.011 |
day | +0.011 |
please | +0.011 |
Neg logit contributions | |
aron | -0.020 |
cks | -0.020 |
opes | -0.020 |
necks | -0.020 |
aters | -0.020 |
Token | again |
Token ID | 757 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
help | +0.193 |
t | +0.192 |
day | +0.188 |
happened | +0.181 |
please | +0.177 |
Neg logit contributions | |
valleys | -0.295 |
aron | -0.294 |
opes | -0.290 |
necks | -0.289 |
aters | -0.289 |
Token | on |
Token ID | 319 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
t | +0.068 |
happened | +0.065 |
help | +0.063 |
day | +0.063 |
please | +0.061 |
Neg logit contributions | |
cks | -0.081 |
necks | -0.080 |
opes | -0.080 |
aron | -0.080 |
uted | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
t | +0.115 |
happened | +0.112 |
help | +0.111 |
day | +0.110 |
week | +0.105 |
Neg logit contributions | |
cks | -0.202 |
necks | -0.201 |
aron | -0.201 |
uted | -0.200 |
opes | -0.199 |
Token | neck |
Token ID | 7393 |
Feature activation | +1.67e+01 |
Pos logit contributions | |
cks | +0.019 |
aron | +0.019 |
uted | +0.019 |
opes | +0.018 |
aters | +0.018 |
Neg logit contributions | |
t | -0.029 |
help | -0.029 |
day | -0.028 |
happened | -0.028 |
week | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
cks | +0.910 |
necks | +0.906 |
aron | +0.905 |
opes | +0.900 |
ping | +0.899 |
Neg logit contributions | |
t | -0.805 |
happened | -0.775 |
help | -0.747 |
day | -0.739 |
please | -0.729 |
Token | |
Token ID | 220 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
cks | +0.067 |
necks | +0.066 |
aron | +0.066 |
ping | +0.066 |
opes | +0.066 |
Neg logit contributions | |
t | -0.085 |
happened | -0.081 |
help | -0.079 |
day | -0.078 |
please | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
necks | +0.194 |
ping | +0.192 |
cks | +0.191 |
opes | +0.190 |
aron | +0.190 |
Neg logit contributions | |
t | -0.131 |
happened | -0.122 |
help | -0.115 |
day | -0.115 |
please | -0.113 |
Token | This |
Token ID | 1212 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
t | +0.037 |
happened | +0.037 |
help | +0.035 |
day | +0.034 |
please | +0.034 |
Neg logit contributions | |
aron | -0.043 |
cks | -0.043 |
necks | -0.043 |
uted | -0.043 |
opes | -0.042 |
Token | time |
Token ID | 640 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
necks | +0.313 |
strings | +0.300 |
opes | +0.300 |
valleys | +0.299 |
aron | +0.298 |
Neg logit contributions | |
t | -0.179 |
please | -0.172 |
help | -0.158 |
awaited | -0.153 |
thank | -0.147 |
Token | louder |
Token ID | 27089 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
cks | +0.374 |
valleys | +0.368 |
necks | +0.367 |
ping | +0.360 |
aron | +0.358 |
Neg logit contributions | |
t | -0.506 |
happened | -0.484 |
day | -0.467 |
week | -0.460 |
awaited | -0.459 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
uted | +0.145 |
aters | +0.145 |
rily | +0.144 |
efully | +0.142 |
opes | +0.141 |
Neg logit contributions | |
t | -0.088 |
help | -0.086 |
day | -0.084 |
happened | -0.083 |
thank | -0.081 |
Token | It |
Token ID | 632 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
ping | +0.099 |
opes | +0.097 |
necks | +0.096 |
cks | +0.096 |
aters | +0.094 |
Neg logit contributions | |
t | -0.060 |
please | -0.057 |
happened | -0.055 |
thank | -0.054 |
help | -0.054 |
Token | made |
Token ID | 925 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
cks | +0.288 |
necks | +0.286 |
aron | +0.283 |
valleys | +0.281 |
ping | +0.281 |
Neg logit contributions | |
t | -0.186 |
happened | -0.173 |
help | -0.169 |
day | -0.168 |
week | -0.166 |
Token | their |
Token ID | 511 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
happened | +0.211 |
help | +0.208 |
t | +0.200 |
day | +0.199 |
thank | +0.193 |
Neg logit contributions | |
aron | -0.344 |
necks | -0.337 |
aters | -0.332 |
cks | -0.330 |
opes | -0.329 |
Token | ears |
Token ID | 11368 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
aron | +0.127 |
cks | +0.125 |
uted | +0.124 |
opes | +0.123 |
ping | +0.123 |
Neg logit contributions | |
t | -0.241 |
happened | -0.235 |
help | -0.231 |
day | -0.230 |
please | -0.225 |
Token | hurt |
Token ID | 5938 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
opes | +0.963 |
efully | +0.952 |
necks | +0.950 |
ags | +0.949 |
aron | +0.949 |
Neg logit contributions | |
t | -0.670 |
help | -0.631 |
please | -0.593 |
thank | -0.593 |
day | -0.593 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
help | +0.100 |
t | +0.098 |
day | +0.096 |
ever | +0.094 |
happened | +0.092 |
Neg logit contributions | |
bes | -0.161 |
cks | -0.159 |
rily | -0.156 |
opes | -0.155 |
uted | -0.154 |
Token | It |
Token ID | 632 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
ping | +0.101 |
opes | +0.099 |
necks | +0.098 |
cks | +0.097 |
aters | +0.096 |
Neg logit contributions | |
t | -0.057 |
please | -0.054 |
happened | -0.053 |
thank | -0.050 |
help | -0.050 |
Token | made |
Token ID | 925 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
cks | +0.307 |
necks | +0.305 |
aron | +0.304 |
opes | +0.303 |
ping | +0.302 |
Neg logit contributions | |
t | -0.165 |
happened | -0.155 |
help | -0.148 |
day | -0.146 |
please | -0.143 |
Token | their |
Token ID | 511 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
happened | +0.213 |
help | +0.206 |
t | +0.200 |
day | +0.198 |
thank | +0.194 |
Neg logit contributions | |
aron | -0.346 |
necks | -0.341 |
aters | -0.336 |
opes | -0.332 |
cks | -0.331 |
Token | She |
Token ID | 1375 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
cks | +0.094 |
necks | +0.092 |
uted | +0.090 |
ping | +0.090 |
aron | +0.089 |
Neg logit contributions | |
t | -0.086 |
happened | -0.082 |
help | -0.081 |
please | -0.080 |
day | -0.080 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
aron | +0.249 |
necks | +0.247 |
uted | +0.245 |
opes | +0.245 |
cks | +0.242 |
Neg logit contributions | |
t | -0.130 |
week | -0.112 |
happened | -0.112 |
day | -0.110 |
please | -0.110 |
Token | into |
Token ID | 656 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
cks | +0.210 |
necks | +0.209 |
aron | +0.209 |
opes | +0.208 |
ping | +0.207 |
Neg logit contributions | |
t | -0.191 |
happened | -0.183 |
help | -0.176 |
day | -0.175 |
please | -0.172 |
Token | Emily |
Token ID | 17608 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
cks | +0.495 |
uted | +0.480 |
aron | +0.477 |
opes | +0.476 |
ping | +0.475 |
Neg logit contributions | |
help | -0.332 |
happened | -0.321 |
t | -0.313 |
day | -0.312 |
reward | -0.304 |
Token | 's |
Token ID | 338 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
t | +0.285 |
day | +0.279 |
help | +0.275 |
happened | +0.264 |
week | +0.263 |
Neg logit contributions | |
cks | -0.425 |
opes | -0.404 |
ags | -0.403 |
uted | -0.403 |
valleys | -0.397 |
Token | ears |
Token ID | 11368 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
help | +0.011 |
day | +0.011 |
t | +0.011 |
happened | +0.011 |
reward | +0.011 |
Neg logit contributions | |
cks | -0.013 |
uted | -0.012 |
opes | -0.012 |
aron | -0.012 |
ping | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
cks | +0.792 |
necks | +0.755 |
opes | +0.755 |
uted | +0.742 |
valleys | +0.738 |
Neg logit contributions | |
t | -0.872 |
happened | -0.835 |
help | -0.810 |
day | -0.804 |
please | -0.781 |
Token | nose |
Token ID | 9686 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
help | +0.330 |
happened | +0.323 |
day | +0.319 |
would | +0.317 |
please | +0.313 |
Neg logit contributions | |
cks | -0.388 |
uted | -0.368 |
aters | -0.367 |
opes | -0.366 |
rily | -0.363 |
Token | and |
Token ID | 290 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
cks | +0.275 |
necks | +0.271 |
opes | +0.269 |
aron | +0.269 |
uted | +0.269 |
Neg logit contributions | |
t | -0.120 |
happened | -0.113 |
help | -0.106 |
day | -0.104 |
please | -0.101 |
Token | throat |
Token ID | 13589 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
cks | +0.461 |
necks | +0.461 |
aron | +0.459 |
opes | +0.458 |
ping | +0.455 |
Neg logit contributions | |
t | -0.433 |
happened | -0.412 |
help | -0.397 |
day | -0.395 |
please | -0.390 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
cks | +0.148 |
necks | +0.147 |
aron | +0.147 |
opes | +0.147 |
ping | +0.146 |
Neg logit contributions | |
t | -0.114 |
happened | -0.109 |
help | -0.104 |
day | -0.103 |
please | -0.102 |
Token | jewelry |
Token ID | 22634 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
necks | +0.270 |
cks | +0.266 |
aron | +0.264 |
opes | +0.262 |
ping | +0.262 |
Neg logit contributions | |
t | -0.317 |
happened | -0.306 |
help | -0.287 |
please | -0.287 |
day | -0.287 |
Token | on |
Token ID | 319 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
necks | +0.321 |
cks | +0.319 |
aron | +0.318 |
ping | +0.315 |
opes | +0.315 |
Neg logit contributions | |
t | -0.300 |
happened | -0.292 |
help | -0.278 |
day | -0.275 |
please | -0.272 |
Token | her |
Token ID | 607 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
help | +0.080 |
day | +0.079 |
t | +0.075 |
please | +0.072 |
week | +0.072 |
Neg logit contributions | |
cks | -0.199 |
ping | -0.196 |
opes | -0.196 |
uted | -0.194 |
aron | -0.194 |
Token | fingers |
Token ID | 9353 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
uted | +0.030 |
aron | +0.030 |
cks | +0.029 |
valleys | +0.029 |
ping | +0.029 |
Neg logit contributions | |
help | -0.028 |
t | -0.028 |
day | -0.028 |
happened | -0.027 |
reward | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
cks | +0.595 |
opes | +0.589 |
necks | +0.588 |
aron | +0.587 |
uted | +0.584 |
Neg logit contributions | |
t | -0.485 |
happened | -0.459 |
help | -0.442 |
day | -0.441 |
please | -0.432 |
Token | wrists |
Token ID | 38163 |
Feature activation | +1.78e+01 |
Pos logit contributions | |
help | +0.293 |
thank | +0.288 |
please | +0.277 |
she | +0.276 |
would | +0.267 |
Neg logit contributions | |
uted | -0.408 |
opes | -0.400 |
inning | -0.400 |
aters | -0.399 |
efully | -0.396 |
Token | , |
Token ID | 11 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
cks | +1.482 |
opes | +1.464 |
aron | +1.456 |
uted | +1.454 |
ping | +1.443 |
Neg logit contributions | |
t | -0.367 |
happened | -0.321 |
help | -0.315 |
day | -0.305 |
please | -0.299 |
Token | and |
Token ID | 290 |
Feature activation | +8.87e+00 |
Pos logit contributions | |
help | +0.334 |
thank | +0.326 |
she | +0.320 |
would | +0.318 |
please | +0.313 |
Neg logit contributions | |
inning | -0.358 |
uted | -0.354 |
opes | -0.351 |
aron | -0.350 |
cks | -0.348 |
Token | ears |
Token ID | 11368 |
Feature activation | +1.58e+01 |
Pos logit contributions | |
aron | +0.574 |
cks | +0.570 |
ping | +0.570 |
opes | +0.569 |
uted | +0.569 |
Neg logit contributions | |
t | -0.333 |
happened | -0.328 |
help | -0.319 |
day | -0.312 |
please | -0.304 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
cks | +0.956 |
necks | +0.950 |
opes | +0.948 |
aron | +0.944 |
uted | +0.941 |
Neg logit contributions | |
t | -0.678 |
happened | -0.642 |
help | -0.620 |
day | -0.610 |
please | -0.601 |
Token | She |
Token ID | 1375 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
cks | +0.115 |
ping | +0.110 |
uted | +0.107 |
opes | +0.107 |
inning | +0.107 |
Neg logit contributions | |
happened | -0.088 |
t | -0.087 |
thank | -0.087 |
day | -0.086 |
please | -0.086 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
necks | +0.537 |
aron | +0.525 |
opes | +0.519 |
ping | +0.517 |
cks | +0.517 |
Neg logit contributions | |
t | -0.358 |
happened | -0.320 |
ha | -0.303 |
please | -0.300 |
awaited | -0.296 |
Token | grow |
Token ID | 1663 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
necks | +0.064 |
cks | +0.063 |
aron | +0.063 |
aters | +0.063 |
valleys | +0.062 |
Neg logit contributions | |
help | -0.039 |
happened | -0.039 |
t | -0.038 |
please | -0.038 |
day | -0.038 |
Token | every |
Token ID | 790 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
necks | +0.345 |
bes | +0.339 |
cks | +0.329 |
opes | +0.329 |
unison | +0.325 |
Neg logit contributions | |
day | -0.203 |
help | -0.202 |
would | -0.202 |
happened | -0.200 |
t | -0.193 |
Token | day |
Token ID | 1110 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
valleys | +0.033 |
rily | +0.032 |
ping | +0.032 |
necks | +0.032 |
cks | +0.032 |
Neg logit contributions | |
t | -0.010 |
happened | -0.008 |
awaited | -0.007 |
please | -0.007 |
ha | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
t | +0.696 |
happened | +0.665 |
help | +0.645 |
day | +0.642 |
please | +0.627 |
Neg logit contributions | |
cks | -0.826 |
necks | -0.819 |
opes | -0.817 |
aron | -0.817 |
uted | -0.813 |
Token | They |
Token ID | 1119 |
Feature activation | +8.09e+00 |
Pos logit contributions | |
cks | +0.088 |
ping | +0.088 |
necks | +0.087 |
opes | +0.087 |
aron | +0.087 |
Neg logit contributions | |
t | -0.070 |
happened | -0.067 |
day | -0.065 |
help | -0.064 |
please | -0.064 |
Token | were |
Token ID | 547 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
necks | +0.489 |
aron | +0.480 |
opes | +0.478 |
uted | +0.474 |
valleys | +0.473 |
Neg logit contributions | |
t | -0.353 |
happened | -0.323 |
help | -0.302 |
day | -0.302 |
please | -0.302 |
Token | very |
Token ID | 845 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
necks | +0.022 |
opes | +0.021 |
cks | +0.021 |
aron | +0.021 |
uted | +0.021 |
Neg logit contributions | |
day | -0.015 |
help | -0.015 |
happened | -0.015 |
t | -0.015 |
please | -0.014 |
Token | excited |
Token ID | 6568 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
aron | +0.172 |
cks | +0.171 |
rily | +0.166 |
necks | +0.166 |
uted | +0.166 |
Neg logit contributions | |
t | -0.194 |
happened | -0.186 |
awaited | -0.174 |
help | -0.172 |
reward | -0.171 |
Token | to |
Token ID | 284 |
Feature activation | -9.42e+00 |
Pos logit contributions | |
ping | +0.044 |
aron | +0.043 |
necks | +0.043 |
opes | +0.042 |
uted | +0.042 |
Neg logit contributions | |
t | -0.019 |
happened | -0.018 |
ha | -0.018 |
reward | -0.018 |
help | -0.018 |
Token | eat |
Token ID | 4483 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
t | +0.303 |
happened | +0.283 |
day | +0.258 |
help | +0.255 |
week | +0.249 |
Neg logit contributions | |
cks | -0.673 |
necks | -0.671 |
aron | -0.669 |
opes | -0.669 |
ping | -0.664 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
cks | +0.568 |
necks | +0.565 |
aron | +0.564 |
opes | +0.562 |
ping | +0.560 |
Neg logit contributions | |
t | -0.412 |
happened | -0.393 |
help | -0.376 |
day | -0.373 |
please | -0.366 |
Token | They |
Token ID | 1119 |
Feature activation | +8.99e+00 |
Pos logit contributions | |
cks | +0.117 |
ping | +0.117 |
necks | +0.114 |
opes | +0.114 |
aron | +0.113 |
Neg logit contributions | |
t | -0.122 |
happened | -0.115 |
please | -0.115 |
day | -0.114 |
help | -0.112 |
Token | were |
Token ID | 547 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
necks | +0.585 |
cks | +0.584 |
aron | +0.579 |
opes | +0.579 |
valleys | +0.576 |
Neg logit contributions | |
t | -0.340 |
happened | -0.319 |
day | -0.300 |
help | -0.299 |
please | -0.293 |
Token | tw |
Token ID | 665 |
Feature activation | +8.75e+00 |
Pos logit contributions | |
aron | +0.070 |
cks | +0.070 |
necks | +0.070 |
opes | +0.069 |
uted | +0.069 |
Neg logit contributions | |
t | -0.061 |
happened | -0.059 |
help | -0.057 |
day | -0.057 |
please | -0.056 |
Token | irling |
Token ID | 24297 |
Feature activation | +1.74e+01 |
Pos logit contributions | |
aron | +0.337 |
ping | +0.323 |
uted | +0.314 |
valleys | +0.305 |
opes | +0.304 |
Neg logit contributions | |
t | -0.563 |
please | -0.527 |
help | -0.526 |
happened | -0.509 |
day | -0.507 |
Token | and |
Token ID | 290 |
Feature activation | +9.22e+00 |
Pos logit contributions | |
cks | +0.997 |
aron | +0.966 |
opes | +0.966 |
aters | +0.955 |
necks | +0.941 |
Neg logit contributions | |
t | -0.852 |
day | -0.815 |
happened | -0.815 |
help | -0.761 |
would | -0.757 |
Token | jumping |
Token ID | 14284 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
cks | +0.460 |
aron | +0.459 |
necks | +0.457 |
opes | +0.456 |
uted | +0.454 |
Neg logit contributions | |
t | -0.490 |
happened | -0.472 |
help | -0.457 |
day | -0.455 |
please | -0.446 |
Token | , |
Token ID | 11 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
cks | +0.386 |
aters | +0.376 |
necks | +0.368 |
opes | +0.367 |
ady | +0.367 |
Neg logit contributions | |
t | -0.267 |
day | -0.244 |
happened | -0.241 |
would | -0.237 |
help | -0.237 |
Token | when |
Token ID | 618 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
day | +0.291 |
they | +0.285 |
would | +0.285 |
she | +0.284 |
help | +0.281 |
Neg logit contributions | |
aters | -0.366 |
aron | -0.361 |
ags | -0.360 |
opes | -0.356 |
cks | -0.356 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
valleys | +0.123 |
necks | +0.118 |
opes | +0.117 |
cks | +0.116 |
aters | +0.114 |
Neg logit contributions | |
t | -0.056 |
happened | -0.047 |
help | -0.045 |
reward | -0.044 |
please | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
t | +0.017 |
please | +0.015 |
help | +0.014 |
day | +0.014 |
week | +0.014 |
Neg logit contributions | |
valleys | -0.030 |
necks | -0.029 |
opes | -0.029 |
cks | -0.029 |
ping | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -9.43e+00 |
Pos logit contributions | |
necks | +0.184 |
cks | +0.183 |
opes | +0.182 |
ping | +0.181 |
valleys | +0.181 |
Neg logit contributions | |
t | -0.047 |
happened | -0.041 |
help | -0.035 |
day | -0.035 |
please | -0.034 |
Token | roll |
Token ID | 4836 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
help | +0.292 |
t | +0.273 |
please | +0.268 |
day | +0.257 |
thank | +0.250 |
Neg logit contributions | |
uted | -0.706 |
ping | -0.698 |
aron | -0.691 |
rily | -0.689 |
opes | -0.689 |
Token | the |
Token ID | 262 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
aron | +0.400 |
ping | +0.396 |
opes | +0.395 |
uted | +0.392 |
cks | +0.391 |
Neg logit contributions | |
t | -0.189 |
day | -0.173 |
happened | -0.172 |
help | -0.167 |
please | -0.161 |
Token | ball |
Token ID | 2613 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
aron | +0.032 |
cks | +0.031 |
uted | +0.031 |
ping | +0.031 |
rily | +0.030 |
Neg logit contributions | |
t | -0.020 |
day | -0.019 |
help | -0.018 |
happened | -0.018 |
week | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -9.42e+00 |
Pos logit contributions | |
aron | +0.054 |
cks | +0.054 |
necks | +0.054 |
opes | +0.054 |
ping | +0.054 |
Neg logit contributions | |
t | -0.045 |
happened | -0.042 |
day | -0.041 |
help | -0.041 |
please | -0.040 |
Token | each |
Token ID | 1123 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
help | +0.391 |
day | +0.355 |
please | +0.347 |
thank | +0.339 |
would | +0.330 |
Neg logit contributions | |
uted | -0.623 |
aron | -0.620 |
ping | -0.616 |
aters | -0.610 |
opes | -0.610 |
Token | other |
Token ID | 584 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
aron | +0.390 |
cks | +0.387 |
opes | +0.385 |
necks | +0.384 |
ping | +0.382 |
Neg logit contributions | |
t | -0.199 |
day | -0.184 |
happened | -0.184 |
help | -0.180 |
week | -0.174 |
Token | and |
Token ID | 290 |
Feature activation | +8.47e+00 |
Pos logit contributions | |
day | +0.346 |
t | +0.333 |
help | +0.326 |
week | +0.324 |
would | +0.314 |
Neg logit contributions | |
cks | -0.361 |
opes | -0.348 |
uted | -0.348 |
rily | -0.343 |
valleys | -0.342 |
Token | catch |
Token ID | 4929 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
necks | +0.558 |
cks | +0.552 |
aron | +0.545 |
opes | +0.543 |
valleys | +0.543 |
Neg logit contributions | |
t | -0.326 |
happened | -0.307 |
day | -0.275 |
week | -0.272 |
help | -0.272 |
Token | it |
Token ID | 340 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
aron | +0.096 |
opes | +0.093 |
edly | +0.092 |
aters | +0.091 |
ping | +0.091 |
Neg logit contributions | |
day | -0.025 |
help | -0.023 |
happened | -0.023 |
t | -0.020 |
week | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
t | +0.096 |
day | +0.092 |
happened | +0.090 |
help | +0.090 |
please | +0.087 |
Neg logit contributions | |
aron | -0.130 |
opes | -0.128 |
uted | -0.127 |
necks | -0.127 |
ping | -0.127 |
Token | She |
Token ID | 1375 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
cks | +0.254 |
necks | +0.254 |
opes | +0.253 |
aron | +0.253 |
uted | +0.252 |
Neg logit contributions | |
t | -0.165 |
happened | -0.157 |
help | -0.150 |
day | -0.149 |
please | -0.145 |
Token | had |
Token ID | 550 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
aron | +0.223 |
necks | +0.222 |
cks | +0.221 |
opes | +0.221 |
uted | +0.221 |
Neg logit contributions | |
t | -0.135 |
happened | -0.125 |
day | -0.121 |
help | -0.121 |
week | -0.118 |
Token | found |
Token ID | 1043 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
t | +0.175 |
day | +0.162 |
happened | +0.160 |
awaited | +0.157 |
please | +0.157 |
Neg logit contributions | |
necks | -0.276 |
cks | -0.271 |
opes | -0.270 |
ping | -0.269 |
valleys | -0.269 |
Token | Sam |
Token ID | 3409 |
Feature activation | -7.74e+00 |
Pos logit contributions | |
t | +0.281 |
happened | +0.267 |
day | +0.255 |
please | +0.252 |
help | +0.252 |
Neg logit contributions | |
cks | -0.323 |
opes | -0.318 |
necks | -0.318 |
ping | -0.318 |
uted | -0.317 |
Token | with |
Token ID | 351 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
t | +0.383 |
happened | +0.367 |
help | +0.354 |
day | +0.352 |
please | +0.346 |
Neg logit contributions | |
cks | -0.415 |
necks | -0.413 |
aron | -0.412 |
opes | -0.411 |
uted | -0.407 |
Token | all |
Token ID | 477 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
cks | +0.233 |
necks | +0.232 |
opes | +0.231 |
ping | +0.229 |
aron | +0.229 |
Neg logit contributions | |
t | -0.217 |
happened | -0.206 |
day | -0.197 |
help | -0.196 |
please | -0.194 |
Token | the |
Token ID | 262 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
necks | +0.405 |
cks | +0.405 |
opes | +0.403 |
aron | +0.403 |
uted | +0.399 |
Neg logit contributions | |
t | -0.247 |
happened | -0.235 |
help | -0.225 |
day | -0.225 |
week | -0.216 |
Token | plastic |
Token ID | 7309 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
cks | +0.025 |
aron | +0.025 |
uted | +0.025 |
ping | +0.025 |
opes | +0.025 |
Neg logit contributions | |
t | -0.027 |
happened | -0.026 |
help | -0.026 |
day | -0.025 |
week | -0.025 |
Token | pieces |
Token ID | 5207 |
Feature activation | +7.66e+00 |
Pos logit contributions | |
cks | +0.331 |
aron | +0.324 |
uted | +0.322 |
ping | +0.320 |
opes | +0.318 |
Neg logit contributions | |
t | -0.453 |
happened | -0.435 |
help | -0.428 |
day | -0.423 |
please | -0.411 |
Token | , |
Token ID | 11 |
Feature activation | -7.08e+00 |
Pos logit contributions | |
cks | +0.415 |
ping | +0.411 |
necks | +0.411 |
aron | +0.411 |
opes | +0.408 |
Neg logit contributions | |
t | -0.364 |
happened | -0.351 |
help | -0.338 |
please | -0.335 |
day | -0.334 |
Token | and |
Token ID | 290 |
Feature activation | +8.48e+00 |
Pos logit contributions | |
t | +0.367 |
happened | +0.364 |
help | +0.358 |
day | +0.349 |
would | +0.342 |
Neg logit contributions | |
cks | -0.362 |
uted | -0.352 |
aters | -0.350 |
rily | -0.350 |
aron | -0.349 |
Token | Mia |
Token ID | 32189 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
aron | +0.081 |
valleys | +0.079 |
necks | +0.079 |
cks | +0.078 |
rily | +0.077 |
Neg logit contributions | |
t | -0.056 |
happened | -0.054 |
awaited | -0.052 |
help | -0.051 |
day | -0.050 |
Token | said |
Token ID | 531 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
t | +0.134 |
happened | +0.120 |
help | +0.113 |
day | +0.112 |
week | +0.108 |
Neg logit contributions | |
aron | -0.412 |
necks | -0.410 |
uted | -0.406 |
cks | -0.405 |
opes | -0.404 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
t | +0.469 |
happened | +0.449 |
day | +0.436 |
awaited | +0.432 |
week | +0.430 |
Neg logit contributions | |
aron | -0.464 |
ping | -0.459 |
rily | -0.459 |
uted | -0.456 |
cks | -0.453 |
Token |
|
Token ID | 198 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
cks | +0.088 |
ping | +0.087 |
opes | +0.087 |
necks | +0.086 |
rily | +0.085 |
Neg logit contributions | |
t | -0.066 |
happened | -0.062 |
help | -0.060 |
please | -0.060 |
day | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
t | +0.037 |
happened | +0.035 |
help | +0.034 |
day | +0.034 |
please | +0.033 |
Neg logit contributions | |
cks | -0.047 |
necks | -0.047 |
aron | -0.047 |
opes | -0.047 |
ping | -0.047 |
Token | They |
Token ID | 2990 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
t | +0.038 |
please | +0.035 |
help | +0.034 |
happened | +0.033 |
day | +0.033 |
Neg logit contributions | |
ping | -0.048 |
rily | -0.048 |
opes | -0.047 |
aters | -0.047 |
cks | -0.046 |
Token | leaned |
Token ID | 23831 |
Feature activation | +8.03e+00 |
Pos logit contributions | |
cks | +0.745 |
aron | +0.739 |
ping | +0.737 |
opes | +0.730 |
uted | +0.728 |
Neg logit contributions | |
t | -0.432 |
happened | -0.418 |
help | -0.407 |
day | -0.386 |
please | -0.386 |
Token | over |
Token ID | 625 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
opes | +0.510 |
cks | +0.499 |
aron | +0.497 |
necks | +0.495 |
bes | +0.491 |
Neg logit contributions | |
t | -0.352 |
day | -0.328 |
happened | -0.328 |
please | -0.322 |
help | -0.319 |
Token | the |
Token ID | 262 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
opes | +0.098 |
aron | +0.098 |
uted | +0.098 |
cks | +0.098 |
ping | +0.097 |
Neg logit contributions | |
help | -0.065 |
day | -0.061 |
t | -0.061 |
happened | -0.060 |
week | -0.057 |
Token | hole |
Token ID | 7604 |
Feature activation | +9.07e+00 |
Pos logit contributions | |
aron | +0.018 |
cks | +0.018 |
uted | +0.018 |
opes | +0.018 |
aters | +0.018 |
Neg logit contributions | |
t | -0.029 |
happened | -0.028 |
help | -0.028 |
day | -0.028 |
please | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e+00 |
Pos logit contributions | |
cks | +0.463 |
opes | +0.458 |
aters | +0.450 |
necks | +0.448 |
aron | +0.445 |
Neg logit contributions | |
t | -0.502 |
day | -0.468 |
happened | -0.460 |
help | -0.452 |
week | -0.448 |
Token | little |
Token ID | 1310 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ping | +0.384 |
necks | +0.372 |
valleys | +0.371 |
uted | +0.368 |
opes | +0.364 |
Neg logit contributions | |
t | -0.374 |
happened | -0.353 |
please | -0.343 |
would | -0.330 |
awaited | -0.329 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
t | +0.005 |
happened | +0.005 |
please | +0.004 |
help | +0.004 |
awaited | +0.004 |
Neg logit contributions | |
necks | -0.006 |
valleys | -0.006 |
ping | -0.006 |
aron | -0.006 |
rily | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
t | +0.108 |
happened | +0.100 |
help | +0.096 |
day | +0.096 |
week | +0.095 |
Neg logit contributions | |
necks | -0.170 |
aron | -0.168 |
uted | -0.166 |
opes | -0.166 |
cks | -0.166 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
t | +0.024 |
happened | +0.023 |
help | +0.022 |
day | +0.022 |
please | +0.022 |
Neg logit contributions | |
opes | -0.026 |
necks | -0.026 |
cks | -0.025 |
aters | -0.025 |
aron | -0.025 |
Token | but |
Token ID | 475 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
ping | +0.074 |
aron | +0.073 |
necks | +0.072 |
uted | +0.072 |
cks | +0.072 |
Neg logit contributions | |
t | -0.065 |
happened | -0.062 |
help | -0.059 |
reward | -0.058 |
day | -0.058 |
Token | brave |
Token ID | 14802 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
uted | +0.427 |
valleys | +0.427 |
ping | +0.427 |
necks | +0.426 |
cks | +0.424 |
Neg logit contributions | |
t | -0.224 |
happened | -0.201 |
help | -0.192 |
week | -0.187 |
reward | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
t | +0.172 |
happened | +0.155 |
help | +0.153 |
please | +0.151 |
reward | +0.150 |
Neg logit contributions | |
ping | -0.157 |
aron | -0.156 |
necks | -0.151 |
rily | -0.151 |
valleys | -0.149 |
Token | She |
Token ID | 1375 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
cks | +0.107 |
necks | +0.099 |
opes | +0.098 |
bes | +0.098 |
aters | +0.095 |
Neg logit contributions | |
t | -0.086 |
happened | -0.084 |
please | -0.083 |
day | -0.082 |
help | -0.081 |
Token | started |
Token ID | 2067 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
necks | +0.245 |
aron | +0.244 |
cks | +0.243 |
opes | +0.242 |
ping | +0.241 |
Neg logit contributions | |
t | -0.146 |
happened | -0.137 |
help | -0.131 |
day | -0.130 |
please | -0.127 |
Token | to |
Token ID | 284 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
cks | +0.065 |
aron | +0.065 |
necks | +0.065 |
opes | +0.064 |
uted | +0.064 |
Neg logit contributions | |
t | -0.015 |
happened | -0.014 |
help | -0.013 |
day | -0.012 |
please | -0.012 |
Token | shout |
Token ID | 9191 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
help | +0.348 |
happened | +0.341 |
t | +0.339 |
day | +0.325 |
please | +0.322 |
Neg logit contributions | |
cks | -0.590 |
aron | -0.586 |
opes | -0.585 |
rily | -0.583 |
aters | -0.581 |
Token | tried |
Token ID | 3088 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
t | +0.196 |
happened | +0.182 |
please | +0.177 |
week | +0.174 |
help | +0.174 |
Neg logit contributions | |
necks | -0.392 |
opes | -0.385 |
aron | -0.383 |
cks | -0.381 |
valleys | -0.380 |
Token | to |
Token ID | 284 |
Feature activation | -9.22e+00 |
Pos logit contributions | |
t | +0.044 |
happened | +0.040 |
help | +0.039 |
day | +0.038 |
please | +0.035 |
Neg logit contributions | |
cks | -0.147 |
aron | -0.147 |
uted | -0.146 |
opes | -0.145 |
rily | -0.145 |
Token | fly |
Token ID | 6129 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
help | +0.318 |
t | +0.311 |
please | +0.289 |
day | +0.287 |
happened | +0.285 |
Neg logit contributions | |
cks | -0.637 |
uted | -0.635 |
opes | -0.634 |
rily | -0.633 |
valleys | -0.629 |
Token | and |
Token ID | 290 |
Feature activation | +8.66e+00 |
Pos logit contributions | |
opes | +0.250 |
cks | +0.250 |
aron | +0.248 |
uted | +0.248 |
necks | +0.246 |
Neg logit contributions | |
t | -0.199 |
help | -0.188 |
happened | -0.187 |
day | -0.185 |
please | -0.182 |
Token | even |
Token ID | 772 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
necks | +0.493 |
valleys | +0.487 |
cks | +0.468 |
neck | +0.467 |
bes | +0.457 |
Neg logit contributions | |
t | -0.399 |
happened | -0.381 |
awaited | -0.350 |
week | -0.346 |
ha | -0.346 |
Token | turned |
Token ID | 2900 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
valleys | +0.271 |
cks | +0.269 |
necks | +0.267 |
ping | +0.263 |
aron | +0.254 |
Neg logit contributions | |
t | -0.243 |
happened | -0.213 |
awaited | -0.207 |
please | -0.204 |
ha | -0.199 |
Token | it |
Token ID | 340 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
cks | +0.277 |
necks | +0.276 |
aron | +0.275 |
opes | +0.275 |
uted | +0.273 |
Neg logit contributions | |
t | -0.214 |
happened | -0.204 |
help | -0.197 |
day | -0.195 |
please | -0.191 |
Token | into |
Token ID | 656 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
t | +0.099 |
happened | +0.095 |
help | +0.092 |
day | +0.091 |
please | +0.090 |
Neg logit contributions | |
cks | -0.101 |
necks | -0.101 |
aron | -0.101 |
opes | -0.100 |
ping | -0.100 |
Token | a |
Token ID | 257 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
uted | +0.505 |
cks | +0.502 |
aron | +0.494 |
ping | +0.490 |
opes | +0.487 |
Neg logit contributions | |
help | -0.324 |
day | -0.304 |
happened | -0.299 |
week | -0.285 |
please | -0.285 |
Token | pirate |
Token ID | 25868 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
valleys | +0.272 |
necks | +0.266 |
aron | +0.263 |
rily | +0.254 |
ping | +0.253 |
Neg logit contributions | |
t | -0.278 |
happened | -0.267 |
awaited | -0.246 |
help | -0.241 |
please | -0.236 |
Token | ship |
Token ID | 4074 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
t | +0.081 |
happened | +0.078 |
help | +0.074 |
day | +0.073 |
please | +0.072 |
Neg logit contributions | |
necks | -0.088 |
cks | -0.087 |
aron | -0.087 |
opes | -0.086 |
ping | -0.086 |
Token | her |
Token ID | 607 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
t | +0.151 |
happened | +0.144 |
day | +0.132 |
help | +0.131 |
please | +0.131 |
Neg logit contributions | |
ping | -0.179 |
aron | -0.179 |
necks | -0.178 |
cks | -0.176 |
opes | -0.176 |
Token | and |
Token ID | 290 |
Feature activation | +8.60e+00 |
Pos logit contributions | |
cks | +0.020 |
necks | +0.020 |
aron | +0.020 |
opes | +0.020 |
ping | +0.020 |
Neg logit contributions | |
t | -0.013 |
happened | -0.013 |
help | -0.012 |
day | -0.012 |
please | -0.012 |
Token | went |
Token ID | 1816 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
ping | +0.505 |
necks | +0.500 |
uted | +0.499 |
aron | +0.496 |
cks | +0.494 |
Neg logit contributions | |
t | -0.393 |
ha | -0.324 |
happened | -0.317 |
please | -0.310 |
week | -0.309 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
t | +0.100 |
happened | +0.096 |
help | +0.088 |
day | +0.087 |
please | +0.086 |
Neg logit contributions | |
cks | -0.175 |
necks | -0.175 |
aron | -0.174 |
ping | -0.173 |
valleys | -0.172 |
Token | her |
Token ID | 607 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
t | +0.124 |
happened | +0.118 |
help | +0.114 |
day | +0.112 |
please | +0.110 |
Neg logit contributions | |
cks | -0.203 |
necks | -0.202 |
aron | -0.202 |
opes | -0.201 |
uted | -0.200 |
Token | house |
Token ID | 2156 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
necks | +0.015 |
cks | +0.014 |
opes | +0.014 |
valleys | +0.014 |
aters | +0.014 |
Neg logit contributions | |
t | -0.015 |
happened | -0.014 |
please | -0.013 |
ha | -0.013 |
help | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
cks | +0.048 |
necks | +0.047 |
aron | +0.047 |
opes | +0.047 |
ping | +0.047 |
Neg logit contributions | |
t | -0.040 |
happened | -0.039 |
help | -0.037 |
day | -0.037 |
please | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
cks | +0.091 |
necks | +0.089 |
ping | +0.089 |
opes | +0.089 |
uted | +0.087 |
Neg logit contributions | |
t | -0.076 |
day | -0.072 |
happened | -0.072 |
help | -0.071 |
week | -0.070 |
Token | knew |
Token ID | 2993 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
necks | +0.224 |
aron | +0.221 |
valleys | +0.216 |
opes | +0.216 |
uted | +0.215 |
Neg logit contributions | |
t | -0.145 |
happened | -0.131 |
please | -0.125 |
help | -0.124 |
week | -0.123 |
Token | she |
Token ID | 673 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
t | +0.282 |
happened | +0.232 |
week | +0.225 |
ha | +0.223 |
reward | +0.216 |
Neg logit contributions | |
uted | -0.452 |
rily | -0.449 |
valleys | -0.444 |
ping | -0.441 |
aron | -0.441 |
Token | 'd |
Token ID | 1549 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
t | +0.161 |
week | +0.155 |
please | +0.154 |
help | +0.149 |
reward | +0.148 |
Neg logit contributions | |
aron | -0.404 |
ping | -0.396 |
necks | -0.395 |
opes | -0.394 |
uted | -0.390 |
Token | decided |
Token ID | 3066 |
Feature activation | +6.45e-04 |
Pos logit contributions | |
t | +0.251 |
happened | +0.234 |
awaited | +0.232 |
help | +0.228 |
week | +0.223 |
Neg logit contributions | |
necks | -0.339 |
aron | -0.330 |
opes | -0.324 |
valleys | -0.323 |
uted | -0.321 |
Token | he |
Token ID | 339 |
Feature activation | -5.68e+00 |
Pos logit contributions | |
necks | +0.000 |
ping | +0.000 |
uted | +0.000 |
valleys | +0.000 |
aron | +0.000 |
Neg logit contributions | |
t | -0.000 |
happened | -0.000 |
day | -0.000 |
awaited | -0.000 |
reward | -0.000 |
Token | would |
Token ID | 561 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
t | +0.148 |
week | +0.136 |
day | +0.136 |
happened | +0.135 |
help | +0.133 |
Neg logit contributions | |
necks | -0.419 |
aron | -0.418 |
opes | -0.416 |
uted | -0.410 |
cks | -0.408 |
Token | try |
Token ID | 1949 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
t | +0.400 |
happened | +0.384 |
day | +0.354 |
help | +0.350 |
please | +0.342 |
Neg logit contributions | |
cks | -0.748 |
necks | -0.748 |
aron | -0.747 |
opes | -0.744 |
ping | -0.739 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
help | +0.120 |
happened | +0.119 |
day | +0.116 |
t | +0.112 |
to | +0.109 |
Neg logit contributions | |
aron | -0.361 |
rily | -0.355 |
uted | -0.355 |
aters | -0.355 |
edly | -0.353 |
Token | |
Token ID | 220 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
cks | +0.098 |
ping | +0.097 |
opes | +0.096 |
uted | +0.096 |
necks | +0.095 |
Neg logit contributions | |
t | -0.062 |
day | -0.057 |
happened | -0.056 |
help | -0.055 |
week | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
necks | +0.189 |
cks | +0.188 |
opes | +0.188 |
ping | +0.188 |
aron | +0.187 |
Neg logit contributions | |
t | -0.137 |
happened | -0.128 |
help | -0.123 |
day | -0.122 |
please | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
t | +0.032 |
happened | +0.028 |
day | +0.028 |
help | +0.028 |
week | +0.027 |
Neg logit contributions | |
opes | -0.047 |
necks | -0.047 |
cks | -0.047 |
ping | -0.047 |
uted | -0.046 |
Token | He |
Token ID | 1544 |
Feature activation | +9.27e+00 |
Pos logit contributions | |
t | +0.040 |
day | +0.034 |
week | +0.034 |
would | +0.033 |
ha | +0.033 |
Neg logit contributions | |
rily | -0.046 |
cks | -0.045 |
ags | -0.045 |
aters | -0.044 |
opes | -0.044 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
necks | +0.574 |
valleys | +0.559 |
aron | +0.557 |
opes | +0.556 |
cks | +0.548 |
Neg logit contributions | |
t | -0.391 |
happened | -0.355 |
please | -0.346 |
help | -0.345 |
awaited | -0.343 |
Token | a |
Token ID | 257 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
t | +0.265 |
happened | +0.257 |
help | +0.250 |
day | +0.247 |
please | +0.242 |
Neg logit contributions | |
cks | -0.255 |
aron | -0.255 |
necks | -0.253 |
opes | -0.252 |
ping | -0.250 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
t | +0.366 |
happened | +0.336 |
awaited | +0.306 |
day | +0.304 |
week | +0.298 |
Neg logit contributions | |
cks | -0.616 |
ping | -0.613 |
rily | -0.610 |
aron | -0.608 |
uted | -0.602 |
Token | with |
Token ID | 351 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
day | +0.231 |
help | +0.231 |
t | +0.231 |
week | +0.213 |
please | +0.212 |
Neg logit contributions | |
valleys | -0.384 |
opes | -0.379 |
cks | -0.376 |
uted | -0.373 |
necks | -0.373 |
Token | a |
Token ID | 257 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
cks | +0.226 |
necks | +0.223 |
ping | +0.220 |
opes | +0.219 |
aron | +0.219 |
Neg logit contributions | |
t | -0.222 |
happened | -0.200 |
day | -0.197 |
week | -0.195 |
awaited | -0.193 |
Token | big |
Token ID | 1263 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
aron | +0.270 |
rily | +0.266 |
necks | +0.265 |
cks | +0.259 |
aters | +0.258 |
Neg logit contributions | |
t | -0.238 |
happened | -0.221 |
awaited | -0.215 |
day | -0.214 |
week | -0.209 |
Token | smile |
Token ID | 8212 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
t | +0.154 |
happened | +0.144 |
day | +0.135 |
awaited | +0.133 |
week | +0.132 |
Neg logit contributions | |
aron | -0.225 |
necks | -0.225 |
cks | -0.222 |
ping | -0.220 |
opes | -0.220 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
aron | +0.143 |
ping | +0.142 |
cks | +0.141 |
necks | +0.140 |
rily | +0.139 |
Neg logit contributions | |
t | -0.140 |
happened | -0.132 |
help | -0.130 |
please | -0.127 |
day | -0.127 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
cks | +0.091 |
necks | +0.090 |
ping | +0.090 |
opes | +0.090 |
uted | +0.089 |
Neg logit contributions | |
t | -0.062 |
happened | -0.059 |
day | -0.056 |
help | -0.056 |
please | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
t | +0.194 |
happened | +0.186 |
help | +0.177 |
would | +0.173 |
day | +0.171 |
Neg logit contributions | |
cks | -0.425 |
valleys | -0.415 |
ags | -0.412 |
opes | -0.411 |
aters | -0.411 |
Token | so |
Token ID | 523 |
Feature activation | +6.72e+00 |
Pos logit contributions | |
t | +0.034 |
help | +0.033 |
happened | +0.033 |
day | +0.033 |
please | +0.032 |
Neg logit contributions | |
opes | -0.047 |
necks | -0.046 |
valleys | -0.046 |
cks | -0.045 |
aters | -0.044 |
Token | happy |
Token ID | 3772 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
uted | +0.355 |
aron | +0.354 |
cks | +0.353 |
ping | +0.349 |
necks | +0.343 |
Neg logit contributions | |
t | -0.332 |
happened | -0.318 |
help | -0.304 |
awaited | -0.299 |
day | -0.299 |
Token | ! |
Token ID | 0 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
t | +0.045 |
happened | +0.043 |
help | +0.042 |
day | +0.041 |
please | +0.041 |
Neg logit contributions | |
aron | -0.050 |
ping | -0.049 |
necks | -0.049 |
cks | -0.049 |
uted | -0.049 |
Token | a |
Token ID | 257 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
t | +0.174 |
please | +0.154 |
day | +0.154 |
awaited | +0.153 |
help | +0.152 |
Neg logit contributions | |
necks | -0.220 |
valleys | -0.218 |
cks | -0.216 |
opes | -0.215 |
ping | -0.213 |
Token | good |
Token ID | 922 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
neck | +0.297 |
necks | +0.294 |
piles | +0.292 |
unison | +0.287 |
valleys | +0.287 |
Neg logit contributions | |
t | -0.267 |
awaited | -0.231 |
happened | -0.223 |
ha | -0.208 |
ll | -0.205 |
Token | idea |
Token ID | 2126 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
t | +0.407 |
awaited | +0.351 |
happened | +0.348 |
please | +0.345 |
ha | +0.340 |
Neg logit contributions | |
necks | -0.626 |
aron | -0.620 |
ping | -0.610 |
opes | -0.600 |
aters | -0.598 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
t | +0.267 |
happened | +0.256 |
day | +0.247 |
week | +0.247 |
reward | +0.244 |
Neg logit contributions | |
aron | -0.231 |
cks | -0.226 |
ping | -0.224 |
uted | -0.222 |
necks | -0.221 |
Token | He |
Token ID | 679 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
cks | +0.098 |
ping | +0.097 |
opes | +0.095 |
necks | +0.095 |
uted | +0.094 |
Neg logit contributions | |
t | -0.106 |
happened | -0.100 |
day | -0.099 |
please | -0.099 |
help | -0.098 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
necks | +0.241 |
aron | +0.239 |
opes | +0.236 |
uted | +0.234 |
rily | +0.233 |
Neg logit contributions | |
t | -0.169 |
happened | -0.153 |
day | -0.149 |
help | -0.148 |
awaited | -0.148 |
Token | the |
Token ID | 262 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
t | +0.368 |
happened | +0.345 |
awaited | +0.318 |
day | +0.316 |
week | +0.313 |
Neg logit contributions | |
aron | -0.312 |
rily | -0.310 |
ping | -0.307 |
necks | -0.306 |
valleys | -0.304 |
Token | other |
Token ID | 584 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
necks | +0.049 |
valleys | +0.049 |
ping | +0.047 |
aron | +0.047 |
opes | +0.047 |
Neg logit contributions | |
t | -0.041 |
happened | -0.038 |
awaited | -0.036 |
ha | -0.034 |
please | -0.034 |
Token | animals |
Token ID | 4695 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
t | +0.310 |
happened | +0.295 |
awaited | +0.271 |
please | +0.265 |
ha | +0.261 |
Neg logit contributions | |
necks | -0.362 |
aron | -0.349 |
valleys | -0.349 |
ping | -0.348 |
uted | -0.346 |
Token | in |
Token ID | 287 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
uted | +0.303 |
ping | +0.302 |
necks | +0.302 |
valleys | +0.301 |
aron | +0.299 |
Neg logit contributions | |
t | -0.177 |
happened | -0.169 |
ha | -0.157 |
reward | -0.147 |
awaited | -0.147 |
Token | the |
Token ID | 262 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
cks | +0.111 |
necks | +0.111 |
aron | +0.110 |
valleys | +0.109 |
opes | +0.109 |
Neg logit contributions | |
t | -0.079 |
happened | -0.075 |
help | -0.070 |
day | -0.070 |
please | -0.069 |
Token | old |
Token ID | 1468 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
t | +0.047 |
happened | +0.044 |
help | +0.041 |
awaited | +0.041 |
day | +0.040 |
Neg logit contributions | |
aron | -0.049 |
ping | -0.048 |
necks | -0.047 |
uted | -0.047 |
valleys | -0.047 |
Token | bird |
Token ID | 6512 |
Feature activation | -5.75e+00 |
Pos logit contributions | |
t | +0.008 |
happened | +0.007 |
awaited | +0.006 |
help | +0.006 |
please | +0.006 |
Neg logit contributions | |
necks | -0.010 |
aron | -0.010 |
ping | -0.010 |
opes | -0.010 |
valleys | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
t | +0.223 |
reward | +0.202 |
week | +0.197 |
help | +0.197 |
please | +0.195 |
Neg logit contributions | |
cks | -0.378 |
ping | -0.363 |
uted | -0.360 |
necks | -0.358 |
opes | -0.355 |
Token | them |
Token ID | 606 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
t | +0.218 |
happened | +0.207 |
help | +0.200 |
day | +0.199 |
please | +0.195 |
Neg logit contributions | |
cks | -0.267 |
necks | -0.264 |
aron | -0.264 |
opes | -0.263 |
uted | -0.262 |
Token | and |
Token ID | 290 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
aron | +0.107 |
valleys | +0.104 |
rily | +0.104 |
necks | +0.103 |
aters | +0.102 |
Neg logit contributions | |
t | -0.093 |
help | -0.091 |
happened | -0.090 |
day | -0.090 |
please | -0.085 |
Token | said |
Token ID | 531 |
Feature activation | -8.75e+00 |
Pos logit contributions | |
cks | +0.565 |
necks | +0.564 |
uted | +0.560 |
ping | +0.558 |
opes | +0.557 |
Neg logit contributions | |
t | -0.343 |
day | -0.302 |
happened | -0.298 |
week | -0.296 |
please | -0.288 |
Token | , |
Token ID | 11 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
t | +0.313 |
day | +0.297 |
week | +0.292 |
awaited | +0.286 |
reward | +0.269 |
Neg logit contributions | |
uted | -0.561 |
rily | -0.548 |
aron | -0.545 |
opes | -0.540 |
necks | -0.538 |
Token | " |
Token ID | 366 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
t | +0.294 |
happened | +0.280 |
please | +0.272 |
help | +0.271 |
day | +0.261 |
Neg logit contributions | |
cks | -0.416 |
necks | -0.410 |
aters | -0.410 |
opes | -0.404 |
aron | -0.403 |
Token | Stop |
Token ID | 19485 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
aron | +0.087 |
opes | +0.087 |
cks | +0.086 |
necks | +0.085 |
aters | +0.085 |
Neg logit contributions | |
t | -0.091 |
happened | -0.085 |
help | -0.082 |
day | -0.082 |
please | -0.081 |
Token | fighting |
Token ID | 4330 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
t | +0.029 |
week | +0.027 |
day | +0.027 |
happened | +0.026 |
reward | +0.026 |
Neg logit contributions | |
uted | -0.035 |
ping | -0.035 |
cks | -0.035 |
opes | -0.034 |
necks | -0.034 |
Token | ! |
Token ID | 0 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
cks | +0.220 |
necks | +0.219 |
aron | +0.219 |
opes | +0.218 |
ping | +0.217 |
Neg logit contributions | |
t | -0.138 |
happened | -0.131 |
help | -0.126 |
day | -0.124 |
please | -0.122 |
Token | busy |
Token ID | 8179 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
happened | +0.377 |
t | +0.376 |
ha | +0.334 |
day | +0.334 |
week | +0.329 |
Neg logit contributions | |
necks | -0.543 |
cks | -0.531 |
aron | -0.529 |
ping | -0.522 |
aters | -0.518 |
Token | poking |
Token ID | 39048 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
t | +0.070 |
happened | +0.067 |
help | +0.065 |
day | +0.064 |
please | +0.063 |
Neg logit contributions | |
cks | -0.078 |
necks | -0.078 |
aron | -0.078 |
opes | -0.078 |
ping | -0.077 |
Token | around |
Token ID | 1088 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
necks | +0.074 |
aron | +0.074 |
cks | +0.073 |
opes | +0.073 |
uted | +0.073 |
Neg logit contributions | |
t | -0.058 |
happened | -0.057 |
help | -0.055 |
day | -0.054 |
please | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
cks | +0.077 |
aron | +0.076 |
necks | +0.076 |
uted | +0.076 |
opes | +0.076 |
Neg logit contributions | |
t | -0.062 |
happened | -0.060 |
day | -0.059 |
help | -0.059 |
week | -0.057 |
Token | shelves |
Token ID | 20726 |
Feature activation | +9.42e+00 |
Pos logit contributions | |
cks | +0.069 |
uted | +0.066 |
aron | +0.065 |
rily | +0.065 |
opes | +0.065 |
Neg logit contributions | |
day | -0.079 |
help | -0.077 |
t | -0.076 |
happened | -0.075 |
week | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
cks | +0.559 |
opes | +0.552 |
necks | +0.550 |
aron | +0.545 |
ping | +0.541 |
Neg logit contributions | |
t | -0.439 |
happened | -0.399 |
day | -0.397 |
help | -0.391 |
week | -0.382 |
Token | his |
Token ID | 465 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
day | +0.289 |
happened | +0.286 |
help | +0.284 |
t | +0.282 |
please | +0.277 |
Neg logit contributions | |
aters | -0.360 |
cks | -0.357 |
ags | -0.346 |
uted | -0.345 |
opes | -0.344 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.73e+00 |
Pos logit contributions | |
necks | +0.214 |
opes | +0.212 |
cks | +0.212 |
aron | +0.212 |
ping | +0.210 |
Neg logit contributions | |
t | -0.154 |
happened | -0.145 |
help | -0.138 |
day | -0.137 |
please | -0.135 |
Token | my |
Token ID | 1820 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
t | +0.369 |
happened | +0.336 |
help | +0.323 |
day | +0.320 |
reward | +0.319 |
Neg logit contributions | |
aron | -0.536 |
ping | -0.529 |
necks | -0.527 |
cks | -0.526 |
opes | -0.524 |
Token | came |
Token ID | 1625 |
Feature activation | -7.64e+00 |
Pos logit contributions | |
t | +0.050 |
happened | +0.045 |
day | +0.043 |
help | +0.043 |
week | +0.043 |
Neg logit contributions | |
aron | -0.081 |
ping | -0.080 |
necks | -0.080 |
uted | -0.080 |
opes | -0.080 |
Token | into |
Token ID | 656 |
Feature activation | +8.14e+00 |
Pos logit contributions | |
t | +0.289 |
help | +0.286 |
day | +0.277 |
please | +0.277 |
happened | +0.276 |
Neg logit contributions | |
necks | -0.501 |
opes | -0.501 |
cks | -0.499 |
aron | -0.487 |
bes | -0.485 |
Token | paying |
Token ID | 5989 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
cks | +0.031 |
ping | +0.031 |
valleys | +0.030 |
necks | +0.030 |
uted | +0.030 |
Neg logit contributions | |
t | -0.029 |
happened | -0.027 |
please | -0.026 |
help | -0.026 |
awaited | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
ping | +0.145 |
cks | +0.145 |
aron | +0.144 |
necks | +0.144 |
valleys | +0.143 |
Neg logit contributions | |
t | -0.104 |
happened | -0.099 |
please | -0.091 |
day | -0.091 |
awaited | -0.090 |
Token | price |
Token ID | 2756 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
necks | +0.042 |
valleys | +0.042 |
ping | +0.042 |
aron | +0.041 |
opes | +0.041 |
Neg logit contributions | |
t | -0.033 |
happened | -0.031 |
please | -0.029 |
awaited | -0.029 |
ha | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
t | +0.131 |
happened | +0.124 |
please | +0.120 |
day | +0.119 |
help | +0.119 |
Neg logit contributions | |
ping | -0.168 |
necks | -0.168 |
opes | -0.167 |
aron | -0.167 |
cks | -0.167 |
Token | Sadly |
Token ID | 27213 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
cks | +0.105 |
necks | +0.104 |
ping | +0.104 |
opes | +0.104 |
uted | +0.102 |
Neg logit contributions | |
t | -0.078 |
happened | -0.073 |
day | -0.071 |
help | -0.070 |
week | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
t | +0.049 |
please | +0.044 |
help | +0.043 |
happened | +0.042 |
reward | +0.039 |
Neg logit contributions | |
ping | -0.120 |
aron | -0.119 |
rily | -0.119 |
valleys | -0.119 |
opes | -0.119 |
Token | they |
Token ID | 484 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
t | +0.249 |
happened | +0.234 |
help | +0.222 |
please | +0.219 |
day | +0.215 |
Neg logit contributions | |
cks | -0.453 |
necks | -0.452 |
valleys | -0.451 |
opes | -0.449 |
ping | -0.449 |
Token | were |
Token ID | 547 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
t | +0.147 |
please | +0.141 |
happened | +0.140 |
week | +0.137 |
day | +0.133 |
Neg logit contributions | |
valleys | -0.217 |
uted | -0.215 |
necks | -0.214 |
ping | -0.212 |
cks | -0.212 |
Token | stuck |
Token ID | 7819 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
cks | +0.035 |
ping | +0.035 |
uted | +0.034 |
necks | +0.034 |
aron | +0.034 |
Neg logit contributions | |
t | -0.029 |
happened | -0.028 |
awaited | -0.027 |
please | -0.026 |
help | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
cks | +0.274 |
opes | +0.271 |
aron | +0.271 |
necks | +0.271 |
uted | +0.267 |
Neg logit contributions | |
t | -0.221 |
happened | -0.211 |
day | -0.202 |
help | -0.202 |
week | -0.196 |
Token | the |
Token ID | 262 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
aron | +0.112 |
cks | +0.112 |
uted | +0.112 |
opes | +0.111 |
ping | +0.111 |
Neg logit contributions | |
help | -0.076 |
t | -0.076 |
day | -0.075 |
happened | -0.074 |
week | -0.072 |
Token | laughed |
Token ID | 13818 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
necks | +0.558 |
aron | +0.547 |
ping | +0.545 |
cks | +0.544 |
opes | +0.540 |
Neg logit contributions | |
t | -0.358 |
please | -0.316 |
happened | -0.315 |
help | -0.306 |
week | -0.296 |
Token | , |
Token ID | 11 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
day | +0.008 |
thank | +0.008 |
help | +0.008 |
happened | +0.008 |
please | +0.007 |
Neg logit contributions | |
cks | -0.014 |
valleys | -0.013 |
necks | -0.013 |
aters | -0.013 |
ady | -0.013 |
Token | having |
Token ID | 1719 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
day | +0.314 |
thank | +0.312 |
they | +0.307 |
t | +0.301 |
help | +0.295 |
Neg logit contributions | |
aters | -0.404 |
cks | -0.396 |
ady | -0.392 |
efully | -0.390 |
ags | -0.388 |
Token | a |
Token ID | 257 |
Feature activation | +5.39e+00 |
Pos logit contributions | |
cks | +0.517 |
opes | +0.510 |
aron | +0.510 |
rily | +0.509 |
uted | +0.509 |
Neg logit contributions | |
happened | -0.251 |
day | -0.247 |
help | -0.241 |
t | -0.233 |
week | -0.229 |
Token | great |
Token ID | 1049 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
aron | +0.296 |
necks | +0.293 |
valleys | +0.287 |
unison | +0.286 |
cks | +0.282 |
Neg logit contributions | |
t | -0.248 |
happened | -0.234 |
awaited | -0.223 |
please | -0.216 |
help | -0.211 |
Token | time |
Token ID | 640 |
Feature activation | -8.56e+00 |
Pos logit contributions | |
t | +0.127 |
happened | +0.112 |
please | +0.112 |
awaited | +0.107 |
help | +0.106 |
Neg logit contributions | |
necks | -0.347 |
aron | -0.342 |
opes | -0.336 |
ping | -0.336 |
cks | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
t | +0.369 |
happened | +0.357 |
help | +0.348 |
day | +0.347 |
please | +0.328 |
Neg logit contributions | |
rily | -0.506 |
aron | -0.506 |
opes | -0.505 |
cks | -0.505 |
necks | -0.502 |
Token | Bob |
Token ID | 5811 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
rily | +0.094 |
aron | +0.093 |
cks | +0.093 |
aters | +0.092 |
necks | +0.092 |
Neg logit contributions | |
t | -0.095 |
day | -0.092 |
happened | -0.092 |
help | -0.088 |
week | -0.087 |
Token | was |
Token ID | 373 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
t | +0.299 |
happened | +0.290 |
help | +0.280 |
day | +0.280 |
please | +0.273 |
Neg logit contributions | |
cks | -0.252 |
opes | -0.248 |
necks | -0.247 |
aron | -0.247 |
ping | -0.246 |
Token | so |
Token ID | 523 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
t | +0.017 |
happened | +0.017 |
help | +0.016 |
day | +0.016 |
please | +0.016 |
Neg logit contributions | |
opes | -0.025 |
necks | -0.025 |
cks | -0.025 |
aron | -0.024 |
aters | -0.024 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
cks | +0.336 |
uted | +0.328 |
ping | +0.328 |
aron | +0.325 |
valleys | +0.318 |
Neg logit contributions | |
t | -0.371 |
happened | -0.368 |
awaited | -0.354 |
ha | -0.347 |
problem | -0.342 |