Token | ? |
Token ID | 30 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
inver | +0.388 |
Fug | +0.378 |
Fract | +0.377 |
Spiral | +0.365 |
ynes | +0.360 |
Neg logit contributions | |
TIT | -0.437 |
YY | -0.399 |
tz | -0.396 |
ieth | -0.388 |
ucha | -0.382 |
Token | � |
Token ID | 447 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
TIT | +0.174 |
YY | +0.158 |
tz | +0.156 |
ieth | +0.152 |
ucha | +0.150 |
Neg logit contributions | |
inver | -0.178 |
Fug | -0.172 |
Fract | -0.172 |
Spiral | -0.167 |
ynes | -0.166 |
Token | � |
Token ID | 251 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
TIT | +0.080 |
YY | +0.072 |
tz | +0.071 |
ieth | +0.069 |
ucha | +0.068 |
Neg logit contributions | |
inver | -0.106 |
Fug | -0.104 |
Fract | -0.104 |
Spiral | -0.101 |
ynes | -0.100 |
Token | � |
Token ID | 564 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
inver | +0.019 |
Fract | +0.019 |
Fug | +0.019 |
Spiral | +0.018 |
ynes | +0.018 |
Neg logit contributions | |
TIT | -0.024 |
YY | -0.022 |
tz | -0.022 |
ieth | -0.021 |
ucha | -0.021 |
Token | � |
Token ID | 250 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
TIT | +0.087 |
YY | +0.078 |
tz | +0.077 |
ieth | +0.075 |
ucha | +0.074 |
Neg logit contributions | |
inver | -0.117 |
Fug | -0.114 |
Fract | -0.114 |
Spiral | -0.111 |
ynes | -0.110 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
inver | +0.003 |
Fug | +0.003 |
Fract | +0.003 |
Spiral | +0.003 |
ynes | +0.003 |
Neg logit contributions | |
TIT | -0.003 |
YY | -0.003 |
tz | -0.003 |
ieth | -0.002 |
ucha | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
inver | +2.597 |
Fug | +2.553 |
Fract | +2.503 |
ynes | +2.417 |
Spiral | +2.416 |
Neg logit contributions | |
TIT | -3.672 |
YY | -3.346 |
tz | -3.341 |
ieth | -3.295 |
ucha | -3.283 |
Token | She |
Token ID | 1375 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
TIT | +0.192 |
YY | +0.175 |
tz | +0.173 |
ieth | +0.169 |
ucha | +0.166 |
Neg logit contributions | |
inver | -0.182 |
Fug | -0.175 |
Fract | -0.175 |
Spiral | -0.170 |
ynes | -0.169 |
Token | left |
Token ID | 1364 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
TIT | +0.049 |
YY | +0.045 |
tz | +0.045 |
ieth | +0.044 |
ucha | +0.043 |
Neg logit contributions | |
inver | -0.043 |
Fract | -0.042 |
Fug | -0.042 |
Spiral | -0.041 |
ynes | -0.040 |
Token | with |
Token ID | 351 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
TIT | +0.537 |
YY | +0.497 |
tz | +0.492 |
ieth | +0.484 |
ucha | +0.477 |
Neg logit contributions | |
inver | -0.377 |
Fract | -0.365 |
Fug | -0.363 |
Spiral | -0.351 |
ynes | -0.346 |
Token | Y |
Token ID | 575 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
TIT | +0.564 |
YY | +0.520 |
tz | +0.517 |
ieth | +0.508 |
ucha | +0.503 |
Neg logit contributions | |
inver | -0.364 |
Fract | -0.351 |
Fug | -0.351 |
Spiral | -0.338 |
ynes | -0.333 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
TIT | +0.422 |
YY | +0.386 |
tz | +0.383 |
ieth | +0.373 |
ucha | +0.367 |
Neg logit contributions | |
inver | -0.392 |
Fug | -0.377 |
Fract | -0.375 |
ynes | -0.364 |
Spiral | -0.364 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
TIT | +0.885 |
YY | +0.808 |
tz | +0.801 |
ieth | +0.781 |
ucha | +0.770 |
Neg logit contributions | |
inver | -0.833 |
Fug | -0.807 |
Fract | -0.803 |
Spiral | -0.780 |
ynes | -0.773 |
Token | Charles |
Token ID | 28711 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
TIT | +0.921 |
YY | +0.831 |
tz | +0.826 |
ieth | +0.807 |
ucha | +0.793 |
Neg logit contributions | |
inver | -1.022 |
Fug | -0.998 |
Fract | -0.995 |
Spiral | -0.968 |
ynes | -0.956 |
Token | Burns |
Token ID | 23592 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
TIT | +0.078 |
YY | +0.072 |
tz | +0.071 |
ieth | +0.070 |
ucha | +0.069 |
Neg logit contributions | |
inver | -0.067 |
Fug | -0.065 |
Fract | -0.065 |
Spiral | -0.063 |
ynes | -0.062 |
Token | : |
Token ID | 1058 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
TIT | +0.295 |
YY | +0.268 |
tz | +0.266 |
ieth | +0.261 |
ucha | +0.257 |
Neg logit contributions | |
inver | -0.282 |
Fug | -0.276 |
Fract | -0.274 |
Spiral | -0.266 |
ynes | -0.263 |
Token | Yeah |
Token ID | 9425 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
inver | +0.541 |
Fug | +0.528 |
Fract | +0.525 |
Spiral | +0.510 |
ynes | +0.504 |
Neg logit contributions | |
TIT | -0.571 |
YY | -0.519 |
tz | -0.516 |
ieth | -0.506 |
ucha | -0.497 |
Token | , |
Token ID | 11 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
inver | +2.354 |
Fug | +2.300 |
Fract | +2.272 |
ynes | +2.181 |
Spiral | +2.179 |
Neg logit contributions | |
TIT | -3.630 |
tz | -3.292 |
YY | -3.290 |
ieth | -3.259 |
ucha | -3.239 |
Token | it |
Token ID | 340 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
inver | +0.164 |
Fug | +0.159 |
Fract | +0.158 |
Spiral | +0.153 |
ynes | +0.150 |
Neg logit contributions | |
TIT | -0.228 |
YY | -0.210 |
tz | -0.209 |
ieth | -0.205 |
ucha | -0.202 |
Token | � |
Token ID | 447 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
inver | +0.244 |
Fug | +0.237 |
Fract | +0.236 |
Spiral | +0.228 |
ynes | +0.224 |
Neg logit contributions | |
TIT | -0.337 |
YY | -0.312 |
tz | -0.310 |
ieth | -0.306 |
ucha | -0.302 |
Token | � |
Token ID | 247 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
TIT | +0.176 |
YY | +0.153 |
tz | +0.152 |
ieth | +0.147 |
ucha | +0.145 |
Neg logit contributions | |
inver | -0.300 |
Fug | -0.294 |
Fract | -0.293 |
Spiral | -0.287 |
ynes | -0.283 |
Token | s |
Token ID | 82 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
inver | +0.274 |
Fug | +0.266 |
Fract | +0.265 |
Spiral | +0.258 |
ynes | +0.254 |
Neg logit contributions | |
TIT | -0.296 |
YY | -0.270 |
tz | -0.269 |
ieth | -0.263 |
ucha | -0.259 |
Token | familiar |
Token ID | 5385 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
inver | +0.138 |
Fug | +0.134 |
Fract | +0.133 |
Spiral | +0.129 |
ynes | +0.127 |
Neg logit contributions | |
TIT | -0.198 |
YY | -0.183 |
tz | -0.182 |
ieth | -0.179 |
ucha | -0.176 |
Token | pattern |
Token ID | 3912 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
inver | +1.365 |
Fug | +1.325 |
Fract | +1.318 |
Spiral | +1.273 |
ynes | +1.250 |
Neg logit contributions | |
TIT | -1.932 |
YY | -1.779 |
tz | -1.769 |
ieth | -1.739 |
ucha | -1.715 |
Token | ? |
Token ID | 30 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
inver | +0.291 |
Fug | +0.284 |
Fract | +0.283 |
Spiral | +0.274 |
ynes | +0.271 |
Neg logit contributions | |
TIT | -0.347 |
YY | -0.319 |
tz | -0.317 |
ieth | -0.311 |
ucha | -0.306 |
Token |
|
Token ID | 198 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
inver | +0.616 |
Fug | +0.594 |
Fract | +0.592 |
Spiral | +0.574 |
ynes | +0.571 |
Neg logit contributions | |
TIT | -0.726 |
YY | -0.664 |
tz | -0.661 |
ieth | -0.646 |
ucha | -0.637 |
Token |
|
Token ID | 198 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
inver | +0.156 |
Fug | +0.152 |
Fract | +0.151 |
Spiral | +0.147 |
ynes | +0.144 |
Neg logit contributions | |
TIT | -0.181 |
YY | -0.165 |
tz | -0.164 |
ieth | -0.161 |
ucha | -0.159 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
TIT | +0.049 |
YY | +0.045 |
tz | +0.044 |
ieth | +0.043 |
ucha | +0.043 |
Neg logit contributions | |
inver | -0.056 |
Fug | -0.055 |
Fract | -0.054 |
Spiral | -0.053 |
ynes | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
inver | +2.387 |
Fug | +2.334 |
Fract | +2.319 |
Spiral | +2.224 |
ynes | +2.174 |
Neg logit contributions | |
TIT | -3.457 |
YY | -3.154 |
tz | -3.127 |
ieth | -3.099 |
ucha | -3.072 |
Token | but |
Token ID | 475 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
TIT | +0.035 |
YY | +0.032 |
tz | +0.032 |
ieth | +0.031 |
ucha | +0.031 |
Neg logit contributions | |
inver | -0.025 |
Fug | -0.024 |
Fract | -0.024 |
Spiral | -0.023 |
ynes | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
inver | +0.187 |
Fug | +0.180 |
Fract | +0.180 |
Spiral | +0.173 |
ynes | +0.172 |
Neg logit contributions | |
TIT | -0.270 |
YY | -0.249 |
tz | -0.249 |
ieth | -0.243 |
ucha | -0.240 |
Token | is |
Token ID | 318 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
inver | +0.060 |
Fug | +0.058 |
Fract | +0.058 |
ynes | +0.056 |
Spiral | +0.055 |
Neg logit contributions | |
TIT | -0.104 |
YY | -0.097 |
tz | -0.096 |
ieth | -0.095 |
ucha | -0.094 |
Token | why |
Token ID | 1521 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
inver | +0.417 |
Fug | +0.405 |
Fract | +0.403 |
Spiral | +0.389 |
ynes | +0.388 |
Neg logit contributions | |
TIT | -0.587 |
YY | -0.543 |
tz | -0.540 |
ieth | -0.528 |
ucha | -0.522 |
Token | I |
Token ID | 314 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
TIT | +0.019 |
YY | +0.018 |
tz | +0.017 |
ieth | +0.017 |
ucha | +0.017 |
Neg logit contributions | |
inver | -0.013 |
Fract | -0.013 |
Fug | -0.013 |
Spiral | -0.013 |
ynes | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
inver | +0.041 |
Fract | +0.040 |
Fug | +0.040 |
Spiral | +0.039 |
ynes | +0.038 |
Neg logit contributions | |
TIT | -0.048 |
YY | -0.045 |
tz | -0.045 |
ieth | -0.043 |
ucha | -0.043 |
Token | like |
Token ID | 588 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
TIT | +0.130 |
YY | +0.120 |
tz | +0.119 |
ieth | +0.117 |
ucha | +0.116 |
Neg logit contributions | |
inver | -0.080 |
Fug | -0.079 |
Fract | -0.079 |
Spiral | -0.076 |
ynes | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
inver | +0.045 |
Fug | +0.044 |
Fract | +0.043 |
Spiral | +0.042 |
ynes | +0.041 |
Neg logit contributions | |
TIT | -0.068 |
YY | -0.063 |
tz | -0.062 |
ieth | -0.061 |
ucha | -0.061 |
Token | " |
Token ID | 366 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
TIT | +0.051 |
YY | +0.047 |
tz | +0.047 |
ieth | +0.047 |
ucha | +0.046 |
Neg logit contributions | |
inver | -0.024 |
Fug | -0.023 |
Fract | -0.023 |
Spiral | -0.022 |
ynes | -0.021 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
TIT | +0.429 |
YY | +0.387 |
tz | +0.384 |
ieth | +0.374 |
ucha | +0.367 |
Neg logit contributions | |
inver | -0.479 |
Fug | -0.467 |
Fract | -0.466 |
Spiral | -0.454 |
ynes | -0.447 |
Token | , |
Token ID | 11 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
inver | +2.176 |
Fug | +2.131 |
Fract | +2.097 |
Spiral | +1.999 |
ynes | +1.992 |
Neg logit contributions | |
TIT | -3.567 |
YY | -3.252 |
tz | -3.238 |
ucha | -3.218 |
ieth | -3.170 |
Token | that |
Token ID | 326 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
inver | +0.025 |
Fug | +0.025 |
Fract | +0.024 |
Spiral | +0.024 |
ynes | +0.023 |
Neg logit contributions | |
TIT | -0.035 |
YY | -0.033 |
tz | -0.032 |
ieth | -0.032 |
ucha | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
TIT | +0.223 |
YY | +0.207 |
tz | +0.206 |
ieth | +0.204 |
ucha | +0.201 |
Neg logit contributions | |
inver | -0.119 |
Fug | -0.114 |
Fract | -0.114 |
Spiral | -0.109 |
ynes | -0.108 |
Token | what |
Token ID | 644 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
inver | +0.420 |
Fug | +0.407 |
Fract | +0.406 |
Spiral | +0.392 |
ynes | +0.389 |
Neg logit contributions | |
TIT | -0.580 |
YY | -0.534 |
tz | -0.531 |
ieth | -0.522 |
ucha | -0.514 |
Token | makes |
Token ID | 1838 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
TIT | +0.137 |
YY | +0.127 |
tz | +0.126 |
ieth | +0.125 |
ucha | +0.122 |
Neg logit contributions | |
inver | -0.085 |
Fract | -0.082 |
Fug | -0.082 |
Spiral | -0.079 |
ynes | -0.078 |
Token | ? |
Token ID | 30 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
TIT | +0.280 |
YY | +0.255 |
tz | +0.254 |
ieth | +0.249 |
ucha | +0.245 |
Neg logit contributions | |
inver | -0.254 |
Fug | -0.248 |
Fract | -0.247 |
Spiral | -0.240 |
ynes | -0.236 |
Token | � |
Token ID | 447 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
inver | +0.060 |
Fug | +0.059 |
Fract | +0.058 |
Spiral | +0.057 |
ynes | +0.056 |
Neg logit contributions | |
TIT | -0.044 |
YY | -0.039 |
tz | -0.039 |
ieth | -0.038 |
ucha | -0.037 |
Token | � |
Token ID | 251 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
inver | +0.171 |
Fug | +0.168 |
Fract | +0.167 |
Spiral | +0.163 |
ynes | +0.161 |
Neg logit contributions | |
TIT | -0.130 |
YY | -0.116 |
tz | -0.115 |
ieth | -0.112 |
ucha | -0.110 |
Token | � |
Token ID | 564 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
inver | +0.076 |
Fug | +0.074 |
Fract | +0.074 |
Spiral | +0.072 |
ynes | +0.071 |
Neg logit contributions | |
TIT | -0.082 |
YY | -0.074 |
tz | -0.074 |
ieth | -0.072 |
ucha | -0.071 |
Token | � |
Token ID | 250 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
inver | +0.139 |
Fug | +0.136 |
Fract | +0.135 |
Spiral | +0.132 |
ynes | +0.130 |
Neg logit contributions | |
TIT | -0.107 |
YY | -0.096 |
tz | -0.095 |
ieth | -0.092 |
ucha | -0.090 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
inver | +0.256 |
Fug | +0.250 |
Fract | +0.249 |
Spiral | +0.243 |
ynes | +0.240 |
Neg logit contributions | |
TIT | -0.229 |
YY | -0.207 |
tz | -0.206 |
ieth | -0.202 |
ucha | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
inver | +2.394 |
Fug | +2.342 |
Fract | +2.306 |
ynes | +2.236 |
Spiral | +2.224 |
Neg logit contributions | |
TIT | -3.289 |
YY | -2.993 |
tz | -2.979 |
ieth | -2.944 |
ucha | -2.922 |
Token | no |
Token ID | 645 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
inver | +0.311 |
Fug | +0.302 |
Fract | +0.299 |
Spiral | +0.289 |
ynes | +0.284 |
Neg logit contributions | |
TIT | -0.449 |
YY | -0.415 |
tz | -0.413 |
ieth | -0.406 |
ucha | -0.400 |
Token | problem |
Token ID | 1917 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
inver | +0.354 |
Fug | +0.344 |
Fract | +0.342 |
Spiral | +0.330 |
ynes | +0.325 |
Neg logit contributions | |
TIT | -0.501 |
YY | -0.462 |
tz | -0.459 |
ieth | -0.451 |
ucha | -0.445 |
Token | ! |
Token ID | 0 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
TIT | +1.097 |
YY | +1.002 |
tz | +0.998 |
ieth | +0.975 |
ucha | +0.961 |
Neg logit contributions | |
inver | -0.984 |
Fract | -0.957 |
Fug | -0.956 |
Spiral | -0.929 |
ynes | -0.914 |
Token | � |
Token ID | 447 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
inver | +0.018 |
Fug | +0.018 |
Fract | +0.017 |
Spiral | +0.017 |
ynes | +0.017 |
Neg logit contributions | |
TIT | -0.019 |
YY | -0.017 |
tz | -0.017 |
ieth | -0.017 |
ucha | -0.016 |
Token | Ker |
Token ID | 17337 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
TIT | +0.082 |
YY | +0.075 |
tz | +0.075 |
ieth | +0.073 |
ucha | +0.072 |
Neg logit contributions | |
inver | -0.062 |
Fug | -0.060 |
Fract | -0.060 |
Spiral | -0.058 |
ynes | -0.057 |
Token | mit |
Token ID | 2781 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
inver | +0.390 |
Fug | +0.379 |
Fract | +0.378 |
Spiral | +0.366 |
ynes | +0.361 |
Neg logit contributions | |
TIT | -0.451 |
YY | -0.413 |
tz | -0.411 |
ieth | -0.403 |
ucha | -0.397 |
Token | !" |
Token ID | 2474 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
TIT | +0.938 |
YY | +0.865 |
tz | +0.860 |
ieth | +0.840 |
ucha | +0.827 |
Neg logit contributions | |
inver | -0.796 |
Fract | -0.774 |
Fug | -0.771 |
Spiral | -0.748 |
ynes | -0.737 |
Token | and |
Token ID | 290 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
TIT | +0.699 |
YY | +0.643 |
tz | +0.640 |
ieth | +0.628 |
ucha | +0.617 |
Neg logit contributions | |
inver | -0.531 |
Fug | -0.514 |
Fract | -0.513 |
Spiral | -0.496 |
ynes | -0.489 |
Token | " |
Token ID | 366 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
TIT | +0.532 |
YY | +0.496 |
tz | +0.494 |
ieth | +0.486 |
ucha | +0.480 |
Neg logit contributions | |
inver | -0.256 |
Fug | -0.246 |
Fract | -0.246 |
Spiral | -0.234 |
ynes | -0.230 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
TIT | +0.065 |
YY | +0.059 |
tz | +0.059 |
ieth | +0.057 |
ucha | +0.056 |
Neg logit contributions | |
inver | -0.067 |
Fug | -0.065 |
Fract | -0.065 |
Spiral | -0.063 |
ynes | -0.063 |
Token | ! |
Token ID | 0 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
inver | +2.287 |
Fug | +2.234 |
Fract | +2.199 |
Spiral | +2.134 |
ynes | +2.104 |
Neg logit contributions | |
TIT | -3.247 |
YY | -2.956 |
tz | -2.932 |
ieth | -2.910 |
ucha | -2.879 |
Token | He |
Token ID | 679 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
TIT | +0.075 |
YY | +0.068 |
tz | +0.068 |
ieth | +0.067 |
ucha | +0.066 |
Neg logit contributions | |
inver | -0.065 |
Fug | -0.063 |
Fract | -0.063 |
Spiral | -0.061 |
ynes | -0.060 |
Token | h |
Token ID | 71 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
inver | +0.259 |
Fug | +0.250 |
Fract | +0.250 |
Spiral | +0.239 |
ynes | +0.235 |
Neg logit contributions | |
TIT | -0.457 |
YY | -0.425 |
tz | -0.424 |
ieth | -0.416 |
ucha | -0.411 |
Token | , |
Token ID | 11 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
inver | +0.644 |
Fug | +0.626 |
Fract | +0.624 |
Spiral | +0.604 |
ynes | +0.595 |
Neg logit contributions | |
TIT | -0.784 |
YY | -0.718 |
tz | -0.715 |
ieth | -0.701 |
ucha | -0.690 |
Token | he |
Token ID | 339 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
inver | +0.030 |
Fug | +0.029 |
Fract | +0.029 |
Spiral | +0.028 |
ynes | +0.027 |
Neg logit contributions | |
TIT | -0.041 |
YY | -0.038 |
tz | -0.038 |
ieth | -0.037 |
ucha | -0.037 |
Token | I |
Token ID | 314 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
inver | +0.104 |
Fug | +0.101 |
Fract | +0.100 |
Spiral | +0.097 |
ynes | +0.096 |
Neg logit contributions | |
TIT | -0.154 |
YY | -0.142 |
tz | -0.141 |
ieth | -0.139 |
ucha | -0.137 |
Token | was |
Token ID | 373 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
inver | +0.049 |
Fug | +0.048 |
Fract | +0.048 |
Spiral | +0.046 |
ynes | +0.046 |
Neg logit contributions | |
TIT | -0.061 |
YY | -0.056 |
tz | -0.056 |
ieth | -0.055 |
ucha | -0.054 |
Token | like |
Token ID | 588 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
TIT | +0.318 |
YY | +0.295 |
tz | +0.293 |
ieth | +0.288 |
ucha | +0.285 |
Neg logit contributions | |
inver | -0.191 |
Fract | -0.186 |
Fug | -0.186 |
Spiral | -0.178 |
ynes | -0.177 |
Token | , |
Token ID | 11 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
inver | +0.090 |
Fug | +0.087 |
Fract | +0.086 |
Spiral | +0.083 |
ynes | +0.081 |
Neg logit contributions | |
TIT | -0.142 |
YY | -0.131 |
tz | -0.129 |
ieth | -0.128 |
ucha | -0.126 |
Token | " |
Token ID | 366 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
inver | +0.069 |
Fug | +0.067 |
Fract | +0.066 |
Spiral | +0.063 |
ynes | +0.061 |
Neg logit contributions | |
TIT | -0.161 |
YY | -0.150 |
tz | -0.148 |
ieth | -0.147 |
ucha | -0.146 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
TIT | +0.136 |
YY | +0.123 |
tz | +0.122 |
ieth | +0.120 |
ucha | +0.118 |
Neg logit contributions | |
inver | -0.147 |
Fug | -0.143 |
Fract | -0.143 |
Spiral | -0.139 |
ynes | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
inver | +2.077 |
Fug | +2.040 |
Fract | +2.001 |
Spiral | +1.913 |
ynes | +1.902 |
Neg logit contributions | |
TIT | -3.373 |
YY | -3.100 |
tz | -3.082 |
ucha | -3.060 |
ieth | -3.032 |
Token | no |
Token ID | 645 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
inver | +0.131 |
Fug | +0.128 |
Fract | +0.127 |
Spiral | +0.122 |
ynes | +0.120 |
Neg logit contributions | |
TIT | -0.189 |
YY | -0.174 |
tz | -0.173 |
ieth | -0.170 |
ucha | -0.168 |
Token | brain |
Token ID | 3632 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
inver | +0.255 |
Fug | +0.248 |
Fract | +0.247 |
Spiral | +0.238 |
ynes | +0.234 |
Neg logit contributions | |
TIT | -0.347 |
YY | -0.319 |
tz | -0.317 |
ieth | -0.311 |
ucha | -0.308 |
Token | ier |
Token ID | 959 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
TIT | +0.211 |
YY | +0.188 |
tz | +0.187 |
ieth | +0.182 |
ucha | +0.179 |
Neg logit contributions | |
inver | -0.285 |
Fug | -0.279 |
Fract | -0.278 |
Spiral | -0.271 |
ynes | -0.269 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
TIT | +0.599 |
YY | +0.547 |
tz | +0.545 |
ieth | +0.534 |
ucha | +0.524 |
Neg logit contributions | |
inver | -0.531 |
Fug | -0.517 |
Fract | -0.515 |
Spiral | -0.500 |
ynes | -0.493 |
Token | 255 |
Token ID | 13381 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
TIT | +0.474 |
YY | +0.422 |
tz | +0.418 |
ieth | +0.405 |
ucha | +0.398 |
Neg logit contributions | |
inver | -0.669 |
Fug | -0.659 |
Fract | -0.654 |
Spiral | -0.637 |
ynes | -0.631 |
Token | ) |
Token ID | 8 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
TIT | +0.514 |
YY | +0.474 |
tz | +0.472 |
ieth | +0.460 |
ucha | +0.455 |
Neg logit contributions | |
inver | -0.385 |
Fug | -0.377 |
Fract | -0.374 |
Spiral | -0.361 |
ynes | -0.356 |
Token | $ |
Token ID | 720 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
TIT | +0.244 |
YY | +0.223 |
tz | +0.222 |
ieth | +0.217 |
ucha | +0.214 |
Neg logit contributions | |
inver | -0.210 |
Fug | -0.204 |
Fract | -0.203 |
Spiral | -0.197 |
ynes | -0.194 |
Token | FS |
Token ID | 10652 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
TIT | +0.339 |
YY | +0.305 |
tz | +0.303 |
ieth | +0.296 |
ucha | +0.291 |
Neg logit contributions | |
inver | -0.393 |
Fug | -0.384 |
Fract | -0.383 |
Spiral | -0.373 |
ynes | -0.368 |
Token | 1 |
Token ID | 16 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
inver | +0.685 |
Fug | +0.669 |
Fract | +0.666 |
Spiral | +0.647 |
ynes | +0.639 |
Neg logit contributions | |
TIT | -0.665 |
YY | -0.602 |
tz | -0.599 |
ieth | -0.586 |
ucha | -0.576 |
Token | =$ |
Token ID | 43641 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
TIT | +0.419 |
YY | +0.382 |
tz | +0.378 |
ieth | +0.367 |
ucha | +0.363 |
Neg logit contributions | |
inver | -0.408 |
Fug | -0.399 |
Fract | -0.396 |
Spiral | -0.385 |
ynes | -0.382 |
Token | FS |
Token ID | 10652 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
inver | +2.992 |
Fract | +2.916 |
Fug | +2.913 |
Spiral | +2.848 |
ynes | +2.798 |
Neg logit contributions | |
TIT | -2.457 |
YY | -2.197 |
tz | -2.183 |
ieth | -2.175 |
ucha | -2.121 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
inver | +0.833 |
Fug | +0.815 |
Fract | +0.812 |
Spiral | +0.793 |
ynes | +0.783 |
Neg logit contributions | |
TIT | -0.618 |
YY | -0.550 |
tz | -0.548 |
ieth | -0.535 |
ucha | -0.524 |
Token | =$ |
Token ID | 43641 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
TIT | +1.300 |
YY | +1.184 |
tz | +1.178 |
ieth | +1.144 |
ucha | +1.131 |
Neg logit contributions | |
inver | -1.171 |
Fug | -1.146 |
Fract | -1.136 |
Spiral | -1.102 |
ynes | -1.097 |
Token | FontSize |
Token ID | 38160 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
inver | +2.703 |
Fract | +2.638 |
Fug | +2.636 |
Spiral | +2.571 |
ynes | +2.536 |
Neg logit contributions | |
TIT | -2.139 |
YY | -1.908 |
tz | -1.904 |
ieth | -1.888 |
ucha | -1.843 |
Token | } |
Token ID | 1782 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
inver | +0.619 |
Fug | +0.605 |
Fract | +0.602 |
Spiral | +0.586 |
ynes | +0.579 |
Neg logit contributions | |
TIT | -0.567 |
YY | -0.512 |
tz | -0.509 |
ieth | -0.498 |
ucha | -0.489 |
Token | off |
Token ID | 572 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
inver | +0.346 |
Fug | +0.336 |
Fract | +0.335 |
Spiral | +0.323 |
ynes | +0.318 |
Neg logit contributions | |
TIT | -0.499 |
YY | -0.460 |
tz | -0.459 |
ieth | -0.449 |
ucha | -0.442 |
Token | of |
Token ID | 286 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
TIT | +0.521 |
YY | +0.477 |
tz | +0.476 |
ieth | +0.467 |
ucha | +0.460 |
Neg logit contributions | |
inver | -0.407 |
Fug | -0.394 |
Fract | -0.393 |
Spiral | -0.379 |
ynes | -0.377 |
Token | ? |
Token ID | 30 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
TIT | +0.202 |
YY | +0.184 |
tz | +0.184 |
ieth | +0.180 |
ucha | +0.177 |
Neg logit contributions | |
inver | -0.173 |
Fug | -0.168 |
Fract | -0.168 |
Spiral | -0.163 |
ynes | -0.161 |
Token |
|
Token ID | 198 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
inver | +0.404 |
Fug | +0.397 |
Fract | +0.395 |
Spiral | +0.382 |
ynes | +0.375 |
Neg logit contributions | |
TIT | -0.490 |
YY | -0.449 |
tz | -0.445 |
ieth | -0.438 |
ucha | -0.431 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
inver | +0.136 |
Fug | +0.133 |
Fract | +0.132 |
Spiral | +0.128 |
ynes | +0.126 |
Neg logit contributions | |
TIT | -0.154 |
YY | -0.140 |
tz | -0.140 |
ieth | -0.137 |
ucha | -0.135 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
TIT | +0.109 |
YY | +0.099 |
tz | +0.098 |
ieth | +0.096 |
ucha | +0.094 |
Neg logit contributions | |
inver | -0.111 |
Fug | -0.108 |
Fract | -0.108 |
Spiral | -0.105 |
ynes | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
inver | +2.153 |
Fug | +2.085 |
Fract | +2.065 |
Spiral | +1.982 |
ynes | +1.946 |
Neg logit contributions | |
TIT | -3.323 |
YY | -3.031 |
tz | -3.015 |
ieth | -2.969 |
ucha | -2.954 |
Token | absolutely |
Token ID | 5543 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
TIT | +0.320 |
YY | +0.296 |
tz | +0.294 |
ieth | +0.289 |
ucha | +0.285 |
Neg logit contributions | |
inver | -0.212 |
Fug | -0.205 |
Fract | -0.204 |
Spiral | -0.197 |
ynes | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | -7.45e-03 |
Pos logit contributions | |
TIT | +0.090 |
YY | +0.083 |
tz | +0.082 |
ieth | +0.080 |
ucha | +0.079 |
Neg logit contributions | |
inver | -0.081 |
Fug | -0.078 |
Fract | -0.078 |
Spiral | -0.076 |
ynes | -0.075 |
Token | Once |
Token ID | 4874 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
TIT | +0.007 |
YY | +0.006 |
tz | +0.006 |
ieth | +0.006 |
ucha | +0.006 |
Neg logit contributions | |
inver | -0.005 |
Fug | -0.005 |
Fract | -0.005 |
ynes | -0.004 |
Spiral | -0.004 |
Token | we |
Token ID | 356 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
TIT | +0.026 |
YY | +0.024 |
tz | +0.024 |
ieth | +0.023 |
ucha | +0.023 |
Neg logit contributions | |
inver | -0.015 |
Fug | -0.015 |
Fract | -0.015 |
Spiral | -0.014 |
ynes | -0.014 |
Token | PH |
Token ID | 11909 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
inver | +0.176 |
Fug | +0.172 |
Fract | +0.171 |
Spiral | +0.167 |
ynes | +0.165 |
Neg logit contributions | |
TIT | -0.165 |
tz | -0.148 |
YY | -0.148 |
ieth | -0.145 |
ucha | -0.143 |
Token | : |
Token ID | 25 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
TIT | +0.819 |
YY | +0.747 |
tz | +0.740 |
ieth | +0.721 |
ucha | +0.707 |
Neg logit contributions | |
inver | -0.812 |
Fug | -0.784 |
Fract | -0.782 |
Spiral | -0.760 |
ynes | -0.754 |
Token | Pretty |
Token ID | 20090 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
inver | +0.080 |
Fug | +0.077 |
Fract | +0.077 |
Spiral | +0.074 |
ynes | +0.074 |
Neg logit contributions | |
TIT | -0.094 |
YY | -0.086 |
tz | -0.085 |
ieth | -0.084 |
ucha | -0.082 |
Token | faithful |
Token ID | 17074 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
TIT | +1.001 |
YY | +0.929 |
tz | +0.924 |
ieth | +0.901 |
ucha | +0.890 |
Neg logit contributions | |
inver | -0.782 |
Fug | -0.771 |
Fract | -0.761 |
Spiral | -0.743 |
ynes | -0.736 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
inver | +0.128 |
Fug | +0.124 |
Fract | +0.123 |
Spiral | +0.119 |
ynes | +0.117 |
Neg logit contributions | |
TIT | -0.154 |
YY | -0.140 |
tz | -0.139 |
ieth | -0.137 |
ucha | -0.135 |
Token | Yeah |
Token ID | 9425 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
inver | +0.115 |
Fug | +0.112 |
Fract | +0.111 |
Spiral | +0.108 |
ynes | +0.107 |
Neg logit contributions | |
TIT | -0.140 |
YY | -0.128 |
tz | -0.128 |
ieth | -0.125 |
ucha | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
inver | +2.075 |
Fug | +1.996 |
Fract | +1.987 |
Spiral | +1.897 |
ynes | +1.890 |
Neg logit contributions | |
TIT | -3.269 |
YY | -2.985 |
tz | -2.952 |
ieth | -2.922 |
ucha | -2.920 |
Token | there |
Token ID | 612 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
inver | +0.127 |
Fug | +0.123 |
Fract | +0.123 |
Spiral | +0.118 |
ynes | +0.116 |
Neg logit contributions | |
TIT | -0.178 |
YY | -0.164 |
tz | -0.163 |
ieth | -0.161 |
ucha | -0.159 |
Token | � |
Token ID | 447 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
inver | +0.049 |
Fug | +0.047 |
Fract | +0.047 |
Spiral | +0.045 |
ynes | +0.045 |
Neg logit contributions | |
TIT | -0.073 |
YY | -0.068 |
tz | -0.068 |
ieth | -0.066 |
ucha | -0.065 |
Token | � |
Token ID | 247 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
inver | +0.044 |
Fug | +0.043 |
Fract | +0.043 |
Spiral | +0.042 |
ynes | +0.041 |
Neg logit contributions | |
TIT | -0.026 |
YY | -0.023 |
tz | -0.023 |
ieth | -0.022 |
ucha | -0.021 |
Token | s |
Token ID | 82 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
inver | +0.258 |
Fug | +0.252 |
Fract | +0.251 |
Spiral | +0.243 |
ynes | +0.241 |
Neg logit contributions | |
TIT | -0.280 |
YY | -0.255 |
tz | -0.253 |
ieth | -0.248 |
ucha | -0.244 |
Token | opened |
Token ID | 26350 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
TIT | +0.250 |
tz | +0.232 |
YY | +0.231 |
ieth | +0.227 |
ucha | +0.224 |
Neg logit contributions | |
inver | -0.150 |
Fug | -0.146 |
Fract | -0.145 |
Spiral | -0.140 |
ynes | -0.136 |
Token | on |
Token ID | 319 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
TIT | +0.512 |
YY | +0.475 |
tz | +0.469 |
ieth | +0.463 |
Judaism | +0.453 |
Neg logit contributions | |
inver | -0.426 |
Fug | -0.417 |
Fract | -0.414 |
Spiral | -0.404 |
ynes | -0.403 |
Token | political |
Token ID | 1964 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
TIT | +0.084 |
YY | +0.077 |
tz | +0.077 |
ieth | +0.075 |
ucha | +0.074 |
Neg logit contributions | |
inver | -0.072 |
Fug | -0.070 |
Fract | -0.070 |
Spiral | -0.068 |
ynes | -0.068 |
Token | grounds |
Token ID | 9384 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
inver | +0.086 |
Fract | +0.085 |
Fug | +0.084 |
Spiral | +0.082 |
ynes | +0.080 |
Neg logit contributions | |
TIT | -0.146 |
YY | -0.135 |
tz | -0.135 |
ieth | -0.133 |
Judaism | -0.131 |
Token | after |
Token ID | 706 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
inver | +0.143 |
Fug | +0.140 |
Fract | +0.139 |
Spiral | +0.135 |
ynes | +0.133 |
Neg logit contributions | |
TIT | -0.166 |
YY | -0.153 |
tz | -0.152 |
ieth | -0.149 |
ucha | -0.147 |
Token | Wikileaks |
Token ID | 35828 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
inver | +0.258 |
Fug | +0.251 |
Fract | +0.250 |
Spiral | +0.243 |
ynes | +0.240 |
Neg logit contributions | |
TIT | -0.396 |
YY | -0.369 |
tz | -0.365 |
ieth | -0.360 |
ucha | -0.356 |
Token | published |
Token ID | 3199 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
inver | +2.076 |
Fug | +2.008 |
Fract | +1.996 |
Spiral | +1.921 |
ynes | +1.881 |
Neg logit contributions | |
TIT | -3.296 |
YY | -3.042 |
tz | -3.032 |
ieth | -2.979 |
ucha | -2.946 |
Token | material |
Token ID | 2587 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
inver | +0.800 |
Fug | +0.778 |
Fract | +0.775 |
Spiral | +0.747 |
ynes | +0.738 |
Neg logit contributions | |
TIT | -1.181 |
YY | -1.088 |
tz | -1.082 |
ieth | -1.065 |
ucha | -1.051 |
Token | embarrassing |
Token ID | 18997 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
inver | +0.495 |
Fug | +0.482 |
Fract | +0.481 |
Spiral | +0.465 |
ynes | +0.460 |
Neg logit contributions | |
TIT | -0.725 |
YY | -0.671 |
tz | -0.667 |
ieth | -0.656 |
ucha | -0.646 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
TIT | +0.689 |
YY | +0.638 |
tz | +0.632 |
ieth | +0.619 |
ucha | +0.612 |
Neg logit contributions | |
inver | -0.507 |
Fug | -0.494 |
Fract | -0.493 |
Spiral | -0.475 |
ynes | -0.469 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
inver | +0.061 |
Fract | +0.059 |
Fug | +0.059 |
Spiral | +0.057 |
ynes | +0.056 |
Neg logit contributions | |
TIT | -0.090 |
YY | -0.084 |
tz | -0.083 |
ieth | -0.081 |
ucha | -0.081 |
Token | ill |
Token ID | 359 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
inver | +0.505 |
Fug | +0.488 |
Fract | +0.486 |
Spiral | +0.467 |
ynes | +0.459 |
Neg logit contributions | |
TIT | -0.870 |
YY | -0.806 |
tz | -0.802 |
ieth | -0.789 |
ucha | -0.779 |
Token | an |
Token ID | 272 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
inver | +0.264 |
Fug | +0.256 |
Fract | +0.255 |
Spiral | +0.247 |
ynes | +0.243 |
Neg logit contributions | |
TIT | -0.339 |
YY | -0.312 |
tz | -0.311 |
ieth | -0.305 |
ucha | -0.301 |
Token | told |
Token ID | 1297 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
inver | +0.274 |
Fug | +0.266 |
Fract | +0.264 |
Spiral | +0.255 |
ynes | +0.251 |
Neg logit contributions | |
TIT | -0.401 |
YY | -0.369 |
tz | -0.367 |
ieth | -0.361 |
ucha | -0.356 |
Token | Polit |
Token ID | 7793 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
TIT | +0.307 |
YY | +0.284 |
tz | +0.283 |
ieth | +0.275 |
ucha | +0.273 |
Neg logit contributions | |
inver | -0.199 |
Fract | -0.193 |
Fug | -0.193 |
Spiral | -0.186 |
ynes | -0.185 |
Token | i |
Token ID | 72 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
TIT | +0.020 |
YY | +0.018 |
tz | +0.018 |
ieth | +0.018 |
ucha | +0.017 |
Neg logit contributions | |
inver | -0.024 |
Fug | -0.023 |
Fract | -0.023 |
Spiral | -0.023 |
ynes | -0.022 |
Token | Fact |
Token ID | 29054 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
inver | +1.547 |
Fug | +1.512 |
Fract | +1.508 |
Spiral | +1.469 |
ynes | +1.453 |
Neg logit contributions | |
TIT | -1.184 |
YY | -1.059 |
tz | -1.047 |
ieth | -1.023 |
ucha | -1.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
inver | +2.045 |
Fug | +1.987 |
Fract | +1.965 |
Spiral | +1.902 |
ynes | +1.852 |
Neg logit contributions | |
TIT | -3.312 |
YY | -3.044 |
tz | -3.030 |
ieth | -2.997 |
ucha | -2.966 |
Token | March |
Token ID | 2805 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
TIT | +0.096 |
tz | +0.088 |
YY | +0.088 |
ieth | +0.087 |
ucha | +0.086 |
Neg logit contributions | |
inver | -0.077 |
Fug | -0.075 |
Fract | -0.075 |
ynes | -0.074 |
Spiral | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
TIT | +0.455 |
YY | +0.419 |
tz | +0.416 |
ieth | +0.406 |
ucha | +0.399 |
Neg logit contributions | |
inver | -0.424 |
Fug | -0.415 |
Fract | -0.413 |
Spiral | -0.402 |
ynes | -0.396 |
Token | " |
Token ID | 366 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
TIT | +0.171 |
YY | +0.159 |
tz | +0.158 |
ieth | +0.155 |
ucha | +0.153 |
Neg logit contributions | |
inver | -0.096 |
Fug | -0.092 |
Fract | -0.091 |
Spiral | -0.087 |
ynes | -0.087 |
Token | AIR |
Token ID | 42149 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
TIT | +0.145 |
YY | +0.133 |
tz | +0.132 |
ieth | +0.129 |
ucha | +0.127 |
Neg logit contributions | |
inver | -0.121 |
Fug | -0.118 |
Fract | -0.117 |
Spiral | -0.113 |
ynes | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
inver | +0.030 |
Fug | +0.029 |
Fract | +0.029 |
Spiral | +0.028 |
ynes | +0.027 |
Neg logit contributions | |
TIT | -0.033 |
YY | -0.030 |
tz | -0.030 |
ieth | -0.029 |
ucha | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
TIT | +0.196 |
YY | +0.179 |
tz | +0.178 |
ieth | +0.174 |
ucha | +0.172 |
Neg logit contributions | |
inver | -0.174 |
Fug | -0.170 |
Fract | -0.169 |
Spiral | -0.164 |
ynes | -0.162 |
Token | [ |
Token ID | 58 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
TIT | +0.414 |
YY | +0.375 |
tz | +0.372 |
ieth | +0.363 |
ucha | +0.357 |
Neg logit contributions | |
inver | -0.443 |
Fug | -0.431 |
Fract | -0.430 |
Spiral | -0.418 |
ynes | -0.413 |
Token | Laughs |
Token ID | 34610 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
TIT | +0.601 |
YY | +0.544 |
tz | +0.540 |
ieth | +0.525 |
ucha | +0.515 |
Neg logit contributions | |
inver | -0.624 |
Fract | -0.606 |
Fug | -0.606 |
Spiral | -0.589 |
ynes | -0.581 |
Token | ] |
Token ID | 60 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
inver | +2.258 |
Fug | +2.191 |
Fract | +2.169 |
Spiral | +2.112 |
ynes | +2.093 |
Neg logit contributions | |
TIT | -2.420 |
YY | -2.197 |
tz | -2.184 |
ieth | -2.154 |
ucha | -2.110 |
Token | Yeah |
Token ID | 9425 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
TIT | +0.180 |
YY | +0.165 |
tz | +0.164 |
ieth | +0.160 |
ucha | +0.158 |
Neg logit contributions | |
inver | -0.152 |
Fug | -0.147 |
Fract | -0.146 |
Spiral | -0.142 |
ynes | -0.141 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
inver | +2.134 |
Fug | +2.066 |
Fract | +2.041 |
Spiral | +1.972 |
ynes | +1.950 |
Neg logit contributions | |
TIT | -3.209 |
YY | -2.906 |
tz | -2.900 |
ieth | -2.874 |
ucha | -2.851 |
Token | every |
Token ID | 790 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
inver | +0.095 |
Fug | +0.092 |
Fract | +0.092 |
Spiral | +0.088 |
ynes | +0.087 |
Neg logit contributions | |
TIT | -0.146 |
YY | -0.134 |
tz | -0.134 |
ieth | -0.132 |
ucha | -0.130 |
Token | language |
Token ID | 3303 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
TIT | +0.314 |
YY | +0.285 |
tz | +0.284 |
ieth | +0.278 |
ucha | +0.273 |
Neg logit contributions | |
inver | -0.300 |
Fug | -0.293 |
Fract | -0.292 |
Spiral | -0.284 |
ynes | -0.280 |
Token | was |
Token ID | 373 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
TIT | +0.336 |
YY | +0.310 |
tz | +0.309 |
ieth | +0.303 |
ucha | +0.299 |
Neg logit contributions | |
inver | -0.223 |
Fug | -0.217 |
Fract | -0.216 |
Spiral | -0.208 |
ynes | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
inver | +0.210 |
Fug | +0.205 |
Fract | +0.205 |
Spiral | +0.198 |
ynes | +0.197 |
Neg logit contributions | |
TIT | -0.275 |
YY | -0.253 |
tz | -0.252 |
ieth | -0.247 |
ucha | -0.244 |
Token | collapsed |
Token ID | 14707 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
inver | +0.328 |
Fug | +0.319 |
Fract | +0.318 |
Spiral | +0.307 |
ynes | +0.303 |
Neg logit contributions | |
TIT | -0.431 |
YY | -0.396 |
tz | -0.394 |
ieth | -0.387 |
ucha | -0.381 |
Token | ?」 |
Token ID | 42943 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
inver | +0.562 |
Fug | +0.546 |
Fract | +0.545 |
Spiral | +0.529 |
ynes | +0.517 |
Neg logit contributions | |
TIT | -0.705 |
YY | -0.650 |
tz | -0.643 |
ieth | -0.636 |
ucha | -0.625 |
Token |
|
Token ID | 198 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
TIT | +0.747 |
YY | +0.680 |
tz | +0.677 |
ieth | +0.662 |
ucha | +0.651 |
Neg logit contributions | |
inver | -0.677 |
Fract | -0.655 |
Fug | -0.654 |
Spiral | -0.633 |
ynes | -0.628 |
Token |
|
Token ID | 198 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
TIT | +0.323 |
YY | +0.295 |
tz | +0.293 |
ieth | +0.286 |
ucha | +0.282 |
Neg logit contributions | |
inver | -0.293 |
Fug | -0.285 |
Fract | -0.283 |
Spiral | -0.275 |
ynes | -0.272 |
Token | " |
Token ID | 1 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
TIT | +0.345 |
YY | +0.306 |
tz | +0.303 |
ieth | +0.294 |
ucha | +0.288 |
Neg logit contributions | |
inver | -0.473 |
Fract | -0.461 |
Fug | -0.461 |
Spiral | -0.448 |
ynes | -0.443 |
Token | Yes |
Token ID | 5297 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
inver | +0.336 |
Fug | +0.328 |
Fract | +0.327 |
Spiral | +0.318 |
ynes | +0.314 |
Neg logit contributions | |
TIT | -0.287 |
YY | -0.259 |
tz | -0.256 |
ieth | -0.250 |
ucha | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
inver | +2.425 |
Fug | +2.378 |
Fract | +2.338 |
Spiral | +2.264 |
ynes | +2.254 |
Neg logit contributions | |
TIT | -2.914 |
YY | -2.636 |
tz | -2.627 |
ieth | -2.585 |
ucha | -2.557 |
Token | At |
Token ID | 1629 |
Feature activation | +8.37e-01 |
Pos logit contributions | |
inver | +0.052 |
Fug | +0.049 |
Fract | +0.049 |
ynes | +0.048 |
Spiral | +0.047 |
Neg logit contributions | |
TIT | -0.064 |
YY | -0.058 |
tz | -0.058 |
ieth | -0.057 |
ucha | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
inver | +0.536 |
Fug | +0.518 |
Fract | +0.516 |
Spiral | +0.499 |
ynes | +0.494 |
Neg logit contributions | |
TIT | -0.733 |
YY | -0.674 |
tz | -0.672 |
ieth | -0.660 |
ucha | -0.652 |
Token | moment |
Token ID | 2589 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
inver | +0.199 |
Fug | +0.193 |
Fract | +0.192 |
Spiral | +0.186 |
ynes | +0.184 |
Neg logit contributions | |
TIT | -0.242 |
YY | -0.222 |
tz | -0.221 |
ieth | -0.217 |
ucha | -0.213 |
Token | , |
Token ID | 11 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
inver | +0.781 |
Fug | +0.758 |
Fract | +0.754 |
Spiral | +0.727 |
ynes | +0.715 |
Neg logit contributions | |
TIT | -1.170 |
YY | -1.079 |
tz | -1.074 |
ieth | -1.056 |
ucha | -1.041 |
Token | 64 |
Token ID | 5598 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
inver | +0.179 |
Fug | +0.174 |
Fract | +0.173 |
Spiral | +0.169 |
ynes | +0.167 |
Neg logit contributions | |
TIT | -0.165 |
YY | -0.149 |
tz | -0.149 |
ieth | -0.145 |
ucha | -0.143 |
Token | 104 |
Token ID | 14436 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
inver | +0.412 |
Fug | +0.401 |
Fract | +0.399 |
Spiral | +0.390 |
ynes | +0.386 |
Neg logit contributions | |
TIT | -0.333 |
YY | -0.298 |
tz | -0.297 |
ieth | -0.288 |
ucha | -0.283 |
Token | 80 |
Token ID | 4019 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
inver | +0.222 |
Fug | +0.214 |
Fract | +0.213 |
Spiral | +0.208 |
ynes | +0.207 |
Neg logit contributions | |
TIT | -0.194 |
YY | -0.175 |
tz | -0.174 |
ieth | -0.168 |
ucha | -0.166 |
Token | 120 |
Token ID | 7982 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
inver | +0.214 |
Fug | +0.208 |
Fract | +0.206 |
Spiral | +0.202 |
ynes | +0.201 |
Neg logit contributions | |
TIT | -0.174 |
YY | -0.157 |
tz | -0.156 |
ieth | -0.151 |
ucha | -0.148 |
Token | 160 |
Token ID | 13454 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
inver | +0.875 |
Fug | +0.853 |
Fract | +0.848 |
Spiral | +0.827 |
ynes | +0.819 |
Neg logit contributions | |
TIT | -0.777 |
YY | -0.702 |
tz | -0.698 |
ieth | -0.680 |
ucha | -0.668 |
Token | Texture |
Token ID | 44409 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
inver | +0.950 |
Fug | +0.922 |
Fract | +0.916 |
Spiral | +0.894 |
ynes | +0.888 |
Neg logit contributions | |
TIT | -0.899 |
YY | -0.816 |
tz | -0.812 |
ieth | -0.789 |
ucha | -0.776 |
Token | fill |
Token ID | 6070 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
inver | +2.860 |
Fug | +2.806 |
Fract | +2.799 |
Spiral | +2.716 |
ynes | +2.675 |
Neg logit contributions | |
TIT | -2.416 |
YY | -2.182 |
tz | -2.146 |
ieth | -2.119 |
ucha | -2.072 |
Token | - |
Token ID | 12 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
inver | +0.878 |
Fug | +0.849 |
Fract | +0.848 |
Spiral | +0.814 |
ynes | +0.800 |
Neg logit contributions | |
TIT | -1.322 |
YY | -1.217 |
tz | -1.210 |
ieth | -1.194 |
ucha | -1.175 |
Token | rate |
Token ID | 4873 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
TIT | +0.539 |
YY | +0.497 |
tz | +0.496 |
ieth | +0.484 |
ucha | +0.477 |
Neg logit contributions | |
inver | -0.407 |
Fug | -0.399 |
Fract | -0.395 |
Spiral | -0.382 |
ynes | -0.376 |
Token | GT |
Token ID | 7963 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
inver | +0.474 |
Fug | +0.462 |
Fract | +0.460 |
Spiral | +0.448 |
ynes | +0.443 |
Neg logit contributions | |
TIT | -0.474 |
YY | -0.431 |
tz | -0.428 |
ieth | -0.418 |
ucha | -0.411 |
Token | / |
Token ID | 14 |
Feature activation | -7.64e-01 |
Pos logit contributions | |
inver | +0.705 |
Fug | +0.688 |
Fract | +0.686 |
Spiral | +0.667 |
ynes | +0.659 |
Neg logit contributions | |
TIT | -0.669 |
YY | -0.605 |
tz | -0.601 |
ieth | -0.588 |
ucha | -0.578 |
Token | weeks |
Token ID | 2745 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
TIT | +0.097 |
YY | +0.090 |
tz | +0.089 |
ieth | +0.087 |
ucha | +0.087 |
Neg logit contributions | |
inver | -0.064 |
Fug | -0.062 |
Fract | -0.062 |
Spiral | -0.060 |
ynes | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
inver | +0.324 |
Fug | +0.314 |
Fract | +0.313 |
Spiral | +0.302 |
ynes | +0.298 |
Neg logit contributions | |
TIT | -0.453 |
YY | -0.417 |
tz | -0.415 |
ieth | -0.408 |
ucha | -0.402 |
Token | weeks |
Token ID | 2745 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
inver | +0.093 |
Fract | +0.090 |
Fug | +0.090 |
Spiral | +0.086 |
ynes | +0.085 |
Neg logit contributions | |
TIT | -0.164 |
YY | -0.152 |
tz | -0.152 |
ieth | -0.149 |
ucha | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
inver | +0.423 |
Fug | +0.412 |
Fract | +0.408 |
Spiral | +0.395 |
ynes | +0.389 |
Neg logit contributions | |
TIT | -0.564 |
YY | -0.517 |
tz | -0.515 |
ieth | -0.506 |
ucha | -0.499 |
Token | [ |
Token ID | 685 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
inver | +0.248 |
Fug | +0.240 |
Fract | +0.240 |
Spiral | +0.231 |
ynes | +0.228 |
Neg logit contributions | |
TIT | -0.378 |
YY | -0.349 |
tz | -0.348 |
ieth | -0.342 |
ucha | -0.337 |
Token | laughs |
Token ID | 28124 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
inver | +0.117 |
Fug | +0.114 |
Fract | +0.114 |
Spiral | +0.110 |
ynes | +0.109 |
Neg logit contributions | |
TIT | -0.115 |
YY | -0.105 |
tz | -0.104 |
ieth | -0.102 |
ucha | -0.100 |
Token | ] |
Token ID | 60 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
inver | +2.475 |
Fug | +2.393 |
Fract | +2.352 |
Spiral | +2.294 |
ynes | +2.267 |
Neg logit contributions | |
TIT | -2.772 |
YY | -2.517 |
tz | -2.511 |
ieth | -2.478 |
ucha | -2.429 |
Token | I |
Token ID | 314 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
inver | +0.045 |
Fract | +0.044 |
Fug | +0.044 |
Spiral | +0.042 |
ynes | +0.042 |
Neg logit contributions | |
TIT | -0.068 |
YY | -0.063 |
tz | -0.062 |
ieth | -0.061 |
ucha | -0.060 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
inver | +0.124 |
Fract | +0.121 |
Fug | +0.121 |
Spiral | +0.117 |
ynes | +0.114 |
Neg logit contributions | |
TIT | -0.193 |
YY | -0.180 |
tz | -0.179 |
ieth | -0.176 |
ucha | -0.174 |
Token | getting |
Token ID | 1972 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
inver | +0.118 |
Fract | +0.115 |
Fug | +0.115 |
Spiral | +0.111 |
ynes | +0.110 |
Neg logit contributions | |
TIT | -0.176 |
YY | -0.162 |
tz | -0.162 |
ieth | -0.159 |
ucha | -0.157 |
Token | so |
Token ID | 523 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
TIT | +0.670 |
YY | +0.617 |
tz | +0.613 |
ieth | +0.604 |
ucha | +0.594 |
Neg logit contributions | |
inver | -0.496 |
Fug | -0.482 |
Fract | -0.481 |
Spiral | -0.463 |
ynes | -0.460 |
Token | olve |
Token ID | 6442 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
TIT | +0.295 |
YY | +0.276 |
ieth | +0.274 |
tz | +0.272 |
ucha | +0.268 |
Neg logit contributions | |
inver | -0.116 |
Fug | -0.112 |
Fract | -0.111 |
Spiral | -0.105 |
ynes | -0.101 |
Token | in |
Token ID | 287 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
TIT | +0.395 |
YY | +0.362 |
tz | +0.359 |
ieth | +0.352 |
ucha | +0.346 |
Neg logit contributions | |
inver | -0.354 |
Fug | -0.347 |
Fract | -0.344 |
Spiral | -0.335 |
ynes | -0.330 |
Token | a |
Token ID | 257 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
TIT | +0.120 |
YY | +0.110 |
tz | +0.110 |
ieth | +0.108 |
ucha | +0.106 |
Neg logit contributions | |
inver | -0.084 |
Fug | -0.082 |
Fract | -0.082 |
Spiral | -0.079 |
ynes | -0.078 |
Token | P |
Token ID | 350 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
TIT | +0.099 |
YY | +0.091 |
tz | +0.091 |
ieth | +0.089 |
ucha | +0.088 |
Neg logit contributions | |
inver | -0.072 |
Fug | -0.070 |
Fract | -0.070 |
Spiral | -0.068 |
ynes | -0.067 |
Token | to |
Token ID | 1462 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
TIT | +0.599 |
YY | +0.549 |
tz | +0.545 |
ieth | +0.534 |
ucha | +0.527 |
Neg logit contributions | |
inver | -0.554 |
Fug | -0.540 |
Fract | -0.538 |
Spiral | -0.522 |
ynes | -0.512 |
Token | le |
Token ID | 293 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
inver | +0.246 |
Fug | +0.240 |
Fract | +0.238 |
Spiral | +0.231 |
ynes | +0.227 |
Neg logit contributions | |
TIT | -0.301 |
YY | -0.276 |
tz | -0.273 |
ieth | -0.269 |
ucha | -0.265 |
Token | ma |
Token ID | 2611 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
inver | +2.224 |
Fug | +2.177 |
Fract | +2.165 |
Spiral | +2.085 |
ynes | +2.070 |
Neg logit contributions | |
TIT | -2.972 |
YY | -2.748 |
tz | -2.684 |
ieth | -2.678 |
ucha | -2.610 |
Token | ic |
Token ID | 291 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
inver | +0.618 |
Fug | +0.604 |
Fract | +0.600 |
Spiral | +0.584 |
ynes | +0.578 |
Neg logit contributions | |
TIT | -0.600 |
YY | -0.544 |
tz | -0.543 |
ieth | -0.529 |
ucha | -0.521 |
Token | system |
Token ID | 1080 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
inver | +0.345 |
Fug | +0.335 |
Fract | +0.333 |
Spiral | +0.322 |
ynes | +0.318 |
Neg logit contributions | |
TIT | -0.446 |
YY | -0.409 |
tz | -0.407 |
ieth | -0.400 |
ucha | -0.394 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
TIT | +0.200 |
YY | +0.184 |
tz | +0.183 |
ieth | +0.180 |
ucha | +0.177 |
Neg logit contributions | |
inver | -0.156 |
Fug | -0.152 |
Fract | -0.151 |
Spiral | -0.146 |
ynes | -0.144 |
Token | It |
Token ID | 632 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
inver | +0.128 |
Fug | +0.123 |
Fract | +0.123 |
Spiral | +0.119 |
ynes | +0.118 |
Neg logit contributions | |
TIT | -0.145 |
YY | -0.133 |
tz | -0.132 |
ieth | -0.129 |
ucha | -0.127 |
Token | lett |
Token ID | 15503 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
inver | +0.533 |
Fug | +0.522 |
Fract | +0.520 |
Spiral | +0.505 |
ynes | +0.497 |
Neg logit contributions | |
TIT | -0.491 |
YY | -0.444 |
tz | -0.443 |
ieth | -0.433 |
ucha | -0.425 |
Token | Foundation |
Token ID | 5693 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
inver | +0.136 |
Fract | +0.132 |
Fug | +0.132 |
Spiral | +0.127 |
ynes | +0.125 |
Neg logit contributions | |
TIT | -0.184 |
YY | -0.170 |
tz | -0.169 |
ieth | -0.167 |
ucha | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
TIT | +0.177 |
YY | +0.163 |
tz | +0.162 |
ieth | +0.159 |
ucha | +0.156 |
Neg logit contributions | |
inver | -0.137 |
Fug | -0.133 |
Fract | -0.133 |
Spiral | -0.128 |
ynes | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
TIT | +0.428 |
YY | +0.390 |
tz | +0.388 |
ieth | +0.379 |
ucha | +0.374 |
Neg logit contributions | |
inver | -0.386 |
Fug | -0.375 |
Fract | -0.373 |
Spiral | -0.362 |
ynes | -0.358 |
Token | F |
Token ID | 37 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
TIT | +0.457 |
YY | +0.413 |
tz | +0.409 |
ieth | +0.399 |
ucha | +0.392 |
Neg logit contributions | |
inver | -0.476 |
Fug | -0.465 |
Fract | -0.463 |
Spiral | -0.450 |
ynes | -0.443 |
Token | ounded |
Token ID | 6302 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
TIT | +0.777 |
YY | +0.713 |
tz | +0.705 |
ieth | +0.698 |
ucha | +0.680 |
Neg logit contributions | |
inver | -0.692 |
Fug | -0.681 |
Fract | -0.677 |
Spiral | -0.653 |
ynes | -0.632 |
Token | in |
Token ID | 287 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
inver | +2.079 |
Fug | +2.019 |
Fract | +2.008 |
Spiral | +1.931 |
ynes | +1.885 |
Neg logit contributions | |
TIT | -3.096 |
YY | -2.841 |
tz | -2.836 |
ieth | -2.786 |
ucha | -2.767 |
Token | 1966 |
Token ID | 19322 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
TIT | +0.009 |
YY | +0.008 |
tz | +0.008 |
ieth | +0.008 |
ucha | +0.008 |
Neg logit contributions | |
inver | -0.009 |
Fug | -0.009 |
Fract | -0.009 |
ynes | -0.008 |
Spiral | -0.008 |
Token | by |
Token ID | 416 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
TIT | +0.075 |
YY | +0.069 |
tz | +0.069 |
ieth | +0.068 |
ucha | +0.067 |
Neg logit contributions | |
inver | -0.052 |
Fug | -0.050 |
Fract | -0.050 |
Spiral | -0.048 |
ynes | -0.047 |
Token | William |
Token ID | 3977 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
inver | +0.142 |
Fug | +0.138 |
Fract | +0.138 |
Spiral | +0.133 |
ynes | +0.131 |
Neg logit contributions | |
TIT | -0.188 |
YY | -0.173 |
tz | -0.171 |
ieth | -0.169 |
ucha | -0.166 |
Token | Hew |
Token ID | 30446 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
TIT | +1.021 |
YY | +0.947 |
tz | +0.941 |
ieth | +0.928 |
ucha | +0.911 |
Neg logit contributions | |
inver | -0.694 |
Fract | -0.670 |
Fug | -0.668 |
Spiral | -0.643 |
ynes | -0.633 |
Token | broken |
Token ID | 5445 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
inver | +0.120 |
Fug | +0.116 |
Fract | +0.116 |
Spiral | +0.112 |
ynes | +0.110 |
Neg logit contributions | |
TIT | -0.173 |
YY | -0.160 |
tz | -0.159 |
ieth | -0.156 |
ucha | -0.154 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
inver | +1.220 |
Fug | +1.192 |
Fract | +1.177 |
Spiral | +1.145 |
ynes | +1.123 |
Neg logit contributions | |
TIT | -1.373 |
YY | -1.255 |
tz | -1.248 |
ieth | -1.218 |
ucha | -1.207 |
Token | : |
Token ID | 25 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
inver | +0.119 |
Fug | +0.116 |
Fract | +0.116 |
Spiral | +0.112 |
ynes | +0.110 |
Neg logit contributions | |
TIT | -0.145 |
YY | -0.133 |
tz | -0.132 |
ieth | -0.129 |
ucha | -0.127 |
Token | � |
Token ID | 564 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
inver | +0.657 |
Fug | +0.644 |
Fract | +0.639 |
Spiral | +0.619 |
ynes | +0.609 |
Neg logit contributions | |
TIT | -0.742 |
YY | -0.677 |
tz | -0.674 |
ieth | -0.662 |
ucha | -0.650 |
Token | � |
Token ID | 250 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
inver | +0.191 |
Fug | +0.187 |
Fract | +0.186 |
Spiral | +0.182 |
ynes | +0.179 |
Neg logit contributions | |
TIT | -0.145 |
YY | -0.130 |
tz | -0.129 |
ieth | -0.125 |
ucha | -0.123 |
Token | Yes |
Token ID | 5297 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
inver | +0.123 |
Fug | +0.120 |
Fract | +0.120 |
Spiral | +0.116 |
ynes | +0.114 |
Neg logit contributions | |
TIT | -0.126 |
YY | -0.115 |
tz | -0.113 |
ieth | -0.111 |
ucha | -0.109 |
Token | , |
Token ID | 11 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
inver | +2.281 |
Fug | +2.234 |
Fract | +2.204 |
Spiral | +2.142 |
ynes | +2.121 |
Neg logit contributions | |
TIT | -2.842 |
tz | -2.579 |
YY | -2.576 |
ieth | -2.525 |
ucha | -2.509 |
Token | we |
Token ID | 356 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
inver | +0.545 |
Fug | +0.533 |
Fract | +0.531 |
Spiral | +0.518 |
ynes | +0.512 |
Neg logit contributions | |
TIT | -0.434 |
YY | -0.388 |
tz | -0.386 |
ieth | -0.377 |
ucha | -0.370 |
Token | did |
Token ID | 750 |
Feature activation | +7.86e-02 |
Pos logit contributions | |
inver | +0.142 |
Fug | +0.136 |
Fract | +0.136 |
Spiral | +0.129 |
ynes | +0.126 |
Neg logit contributions | |
TIT | -0.322 |
YY | -0.302 |
tz | -0.301 |
ieth | -0.296 |
ucha | -0.293 |
Token | it |
Token ID | 340 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
inver | +0.049 |
Fug | +0.047 |
Fract | +0.047 |
Spiral | +0.045 |
ynes | +0.045 |
Neg logit contributions | |
TIT | -0.071 |
YY | -0.065 |
tz | -0.065 |
ieth | -0.064 |
ucha | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
inver | +0.220 |
Fug | +0.214 |
Fract | +0.213 |
Spiral | +0.207 |
ynes | +0.204 |
Neg logit contributions | |
TIT | -0.233 |
YY | -0.212 |
tz | -0.211 |
ieth | -0.207 |
ucha | -0.203 |
Token | Hall |
Token ID | 34194 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
TIT | +0.650 |
YY | +0.588 |
tz | +0.583 |
ieth | +0.567 |
ucha | +0.558 |
Neg logit contributions | |
inver | -0.711 |
Fug | -0.694 |
Fract | -0.690 |
Spiral | -0.672 |
ynes | -0.663 |
Token | responded |
Token ID | 7082 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
TIT | +0.001 |
YY | +0.001 |
tz | +0.001 |
ieth | +0.001 |
ucha | +0.001 |
Neg logit contributions | |
inver | -0.001 |
Fug | -0.001 |
Fract | -0.001 |
Spiral | -0.001 |
ynes | -0.001 |
Token | : |
Token ID | 25 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
inver | +0.107 |
Fug | +0.104 |
Fract | +0.104 |
Spiral | +0.101 |
ynes | +0.099 |
Neg logit contributions | |
TIT | -0.136 |
YY | -0.125 |
tz | -0.125 |
ieth | -0.122 |
ucha | -0.120 |
Token |
|
Token ID | 198 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
TIT | +0.076 |
YY | +0.069 |
tz | +0.069 |
ieth | +0.068 |
ucha | +0.067 |
Neg logit contributions | |
inver | -0.065 |
Fug | -0.063 |
Fract | -0.063 |
Spiral | -0.061 |
ynes | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
TIT | +0.524 |
YY | +0.478 |
tz | +0.475 |
ieth | +0.464 |
ucha | +0.458 |
Neg logit contributions | |
inver | -0.478 |
Fug | -0.464 |
Fract | -0.462 |
Spiral | -0.449 |
ynes | -0.443 |
Token | Yeah |
Token ID | 10995 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
TIT | +0.582 |
YY | +0.527 |
tz | +0.521 |
ieth | +0.505 |
ucha | +0.497 |
Neg logit contributions | |
inver | -0.647 |
Fug | -0.630 |
Fract | -0.628 |
Spiral | -0.612 |
ynes | -0.601 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
inver | +2.020 |
Fug | +1.956 |
Fract | +1.941 |
ynes | +1.863 |
Spiral | +1.856 |
Neg logit contributions | |
TIT | -3.089 |
YY | -2.822 |
tz | -2.797 |
ieth | -2.788 |
ucha | -2.757 |
Token | it |
Token ID | 340 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
TIT | +0.107 |
YY | +0.099 |
tz | +0.098 |
ieth | +0.097 |
ucha | +0.095 |
Neg logit contributions | |
inver | -0.074 |
Fug | -0.072 |
Fract | -0.072 |
Spiral | -0.069 |
ynes | -0.068 |
Token | � |
Token ID | 447 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
inver | +0.057 |
Fug | +0.055 |
Fract | +0.055 |
Spiral | +0.053 |
ynes | +0.052 |
Neg logit contributions | |
TIT | -0.081 |
YY | -0.075 |
tz | -0.075 |
ieth | -0.074 |
ucha | -0.073 |
Token | � |
Token ID | 247 |
Feature activation | -8.49e-02 |
Pos logit contributions | |
TIT | +0.050 |
YY | +0.044 |
tz | +0.043 |
ieth | +0.042 |
ucha | +0.041 |
Neg logit contributions | |
inver | -0.081 |
Fug | -0.080 |
Fract | -0.079 |
Spiral | -0.078 |
ynes | -0.077 |
Token | s |
Token ID | 82 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
TIT | +0.067 |
YY | +0.061 |
tz | +0.061 |
ieth | +0.060 |
ucha | +0.059 |
Neg logit contributions | |
inver | -0.062 |
Fug | -0.060 |
Fract | -0.060 |
Spiral | -0.058 |
ynes | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
inver | +0.129 |
Fug | +0.126 |
Fract | +0.125 |
Spiral | +0.121 |
ynes | +0.119 |
Neg logit contributions | |
TIT | -0.189 |
YY | -0.174 |
tz | -0.173 |
ieth | -0.170 |
ucha | -0.168 |
Token | I |
Token ID | 314 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
TIT | +0.183 |
YY | +0.168 |
tz | +0.168 |
ieth | +0.165 |
ucha | +0.163 |
Neg logit contributions | |
inver | -0.136 |
Fug | -0.132 |
Fract | -0.131 |
Spiral | -0.127 |
ynes | -0.124 |
Token | think |
Token ID | 892 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
TIT | +0.256 |
YY | +0.232 |
tz | +0.231 |
ieth | +0.225 |
ucha | +0.222 |
Neg logit contributions | |
inver | -0.250 |
Fug | -0.244 |
Fract | -0.243 |
Spiral | -0.237 |
ynes | -0.233 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
TIT | +0.329 |
YY | +0.301 |
tz | +0.299 |
ieth | +0.293 |
ucha | +0.289 |
Neg logit contributions | |
inver | -0.283 |
Fug | -0.276 |
Fract | -0.275 |
Spiral | -0.266 |
ynes | -0.262 |
Token |
|
Token ID | 198 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
TIT | +0.574 |
YY | +0.524 |
tz | +0.521 |
ieth | +0.509 |
ucha | +0.501 |
Neg logit contributions | |
inver | -0.524 |
Fug | -0.509 |
Fract | -0.507 |
Spiral | -0.492 |
ynes | -0.486 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
TIT | +0.941 |
YY | +0.875 |
tz | +0.871 |
ieth | +0.859 |
ucha | +0.848 |
Neg logit contributions | |
inver | -0.497 |
Fug | -0.479 |
Fract | -0.477 |
Spiral | -0.457 |
ynes | -0.449 |
Token | : |
Token ID | 25 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
TIT | +3.140 |
tz | +2.829 |
YY | +2.829 |
ieth | +2.711 |
Judaism | +2.679 |
Neg logit contributions | |
inver | -3.527 |
Fug | -3.385 |
Fract | -3.376 |
ynes | -3.291 |
awa | -3.271 |
Token | B |
Token ID | 347 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
TIT | +0.778 |
YY | +0.713 |
tz | +0.709 |
ieth | +0.694 |
ucha | +0.684 |
Neg logit contributions | |
inver | -0.649 |
Fug | -0.631 |
Fract | -0.629 |
Spiral | -0.609 |
ynes | -0.603 |
Token | iz |
Token ID | 528 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
inver | +0.008 |
Fug | +0.008 |
Fract | +0.008 |
Spiral | +0.008 |
ynes | +0.008 |
Neg logit contributions | |
TIT | -0.008 |
YY | -0.008 |
tz | -0.008 |
ieth | -0.007 |
ucha | -0.007 |
Token | r |
Token ID | 81 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
TIT | +1.175 |
YY | +1.071 |
tz | +1.063 |
ieth | +1.034 |
ucha | +1.016 |
Neg logit contributions | |
inver | -1.249 |
Fug | -1.214 |
Fract | -1.209 |
Spiral | -1.177 |
ynes | -1.159 |
Token | Pix |
Token ID | 21642 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
inver | +0.072 |
Fug | +0.070 |
Fract | +0.070 |
Spiral | +0.068 |
ynes | +0.067 |
Neg logit contributions | |
TIT | -0.071 |
YY | -0.064 |
tz | -0.064 |
ieth | -0.063 |
ucha | -0.062 |
Token | iff |
Token ID | 733 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
inver | +0.261 |
Fug | +0.253 |
Fract | +0.252 |
Spiral | +0.243 |
ynes | +0.241 |
Neg logit contributions | |
TIT | -0.392 |
YY | -0.361 |
tz | -0.359 |
ieth | -0.353 |
ucha | -0.348 |
Token | Tra |
Token ID | 15721 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
TIT | +1.859 |
YY | +1.692 |
tz | +1.679 |
Tag | +1.608 |
ieth | +1.608 |
Neg logit contributions | |
inver | -1.687 |
Fug | -1.623 |
Fract | -1.605 |
Spiral | -1.561 |
ynes | -1.558 |
Token | x |
Token ID | 87 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
inver | +1.032 |
Fug | +1.008 |
Fract | +1.004 |
Spiral | +0.977 |
ynes | +0.968 |
Neg logit contributions | |
TIT | -0.956 |
YY | -0.862 |
tz | -0.855 |
ieth | -0.839 |
ucha | -0.823 |
Token |
|
Token ID | 198 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
TIT | +0.083 |
YY | +0.076 |
tz | +0.075 |
ieth | +0.074 |
ucha | +0.073 |
Neg logit contributions | |
inver | -0.070 |
Fug | -0.068 |
Fract | -0.067 |
Spiral | -0.066 |
ynes | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
TIT | +0.647 |
YY | +0.590 |
tz | +0.588 |
ieth | +0.574 |
ucha | +0.566 |
Neg logit contributions | |
inver | -0.579 |
Fug | -0.563 |
Fract | -0.561 |
Spiral | -0.544 |
ynes | -0.537 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
TIT | +1.069 |
YY | +0.995 |
tz | +0.989 |
ieth | +0.981 |
ucha | +0.970 |
Neg logit contributions | |
inver | -0.538 |
Fug | -0.520 |
Fract | -0.516 |
Spiral | -0.494 |
ynes | -0.486 |
Token | : |
Token ID | 25 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
TIT | +3.021 |
tz | +2.729 |
YY | +2.725 |
ieth | +2.617 |
Judaism | +2.577 |
Neg logit contributions | |
inver | -3.357 |
Fug | -3.232 |
Fract | -3.226 |
ynes | -3.131 |
Spiral | -3.109 |
Token | V |
Token ID | 569 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
TIT | +0.726 |
YY | +0.664 |
tz | +0.661 |
ieth | +0.647 |
ucha | +0.637 |
Neg logit contributions | |
inver | -0.604 |
Fug | -0.587 |
Fract | -0.584 |
Spiral | -0.566 |
ynes | -0.560 |
Token | the |
Token ID | 1169 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
TIT | +0.775 |
YY | +0.706 |
tz | +0.701 |
ieth | +0.687 |
ucha | +0.675 |
Neg logit contributions | |
inver | -0.758 |
Fug | -0.740 |
Fract | -0.737 |
Spiral | -0.715 |
ynes | -0.702 |
Token | Happy |
Token ID | 25082 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
TIT | +0.301 |
YY | +0.272 |
tz | +0.271 |
ieth | +0.264 |
ucha | +0.260 |
Neg logit contributions | |
inver | -0.320 |
Fug | -0.312 |
Fract | -0.311 |
Spiral | -0.302 |
ynes | -0.298 |
Token | L |
Token ID | 43 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
inver | +0.313 |
Fug | +0.306 |
Fract | +0.305 |
Spiral | +0.296 |
ynes | +0.293 |
Neg logit contributions | |
TIT | -0.308 |
YY | -0.279 |
tz | -0.278 |
ieth | -0.272 |
ucha | -0.267 |
Token | bad |
Token ID | 2089 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
TIT | +0.016 |
YY | +0.015 |
tz | +0.015 |
ieth | +0.014 |
ucha | +0.014 |
Neg logit contributions | |
inver | -0.017 |
Fug | -0.016 |
Fract | -0.016 |
Spiral | -0.016 |
ynes | -0.015 |
Token | idea |
Token ID | 2126 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
TIT | +0.488 |
YY | +0.448 |
tz | +0.447 |
ieth | +0.438 |
ucha | +0.432 |
Neg logit contributions | |
inver | -0.361 |
Fug | -0.351 |
Fract | -0.350 |
Spiral | -0.337 |
ynes | -0.333 |
Token | . |
Token ID | 13 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
inver | +0.262 |
Fug | +0.256 |
Fract | +0.255 |
Spiral | +0.247 |
ynes | +0.243 |
Neg logit contributions | |
TIT | -0.295 |
YY | -0.269 |
tz | -0.267 |
ieth | -0.263 |
ucha | -0.259 |
Token |
|
Token ID | 198 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
TIT | +0.348 |
YY | +0.317 |
tz | +0.315 |
ieth | +0.310 |
ucha | +0.305 |
Neg logit contributions | |
inver | -0.298 |
Fug | -0.294 |
Fract | -0.291 |
Spiral | -0.284 |
ynes | -0.278 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
TIT | +0.580 |
YY | +0.530 |
tz | +0.527 |
ieth | +0.514 |
ucha | +0.506 |
Neg logit contributions | |
inver | -0.535 |
Fug | -0.520 |
Fract | -0.517 |
Spiral | -0.502 |
ynes | -0.496 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
TIT | +0.988 |
YY | +0.915 |
tz | +0.913 |
ieth | +0.892 |
ucha | +0.881 |
Neg logit contributions | |
inver | -0.561 |
Fug | -0.541 |
Fract | -0.538 |
Spiral | -0.517 |
ynes | -0.504 |
Token | : |
Token ID | 25 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
TIT | +2.977 |
tz | +2.687 |
YY | +2.683 |
ieth | +2.580 |
Judaism | +2.543 |
Neg logit contributions | |
inver | -3.334 |
Fug | -3.209 |
Fract | -3.204 |
ynes | -3.114 |
awa | -3.090 |
Token | Mike |
Token ID | 4995 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
TIT | +0.498 |
YY | +0.456 |
tz | +0.454 |
ieth | +0.445 |
ucha | +0.438 |
Neg logit contributions | |
inver | -0.417 |
Fug | -0.405 |
Fract | -0.404 |
Spiral | -0.391 |
ynes | -0.386 |
Token | M |
Token ID | 44 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
TIT | +0.377 |
YY | +0.342 |
tz | +0.340 |
ieth | +0.332 |
ucha | +0.326 |
Neg logit contributions | |
inver | -0.381 |
Fug | -0.372 |
Fract | -0.370 |
Spiral | -0.360 |
ynes | -0.355 |
Token | anners |
Token ID | 15672 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
TIT | +0.145 |
YY | +0.131 |
tz | +0.130 |
ieth | +0.127 |
ucha | +0.125 |
Neg logit contributions | |
inver | -0.159 |
Fug | -0.155 |
Fract | -0.154 |
Spiral | -0.150 |
ynes | -0.149 |
Token | - |
Token ID | 532 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
TIT | +1.363 |
YY | +1.255 |
tz | +1.247 |
ieth | +1.224 |
ucha | +1.206 |
Neg logit contributions | |
inver | -0.988 |
Fug | -0.958 |
Fract | -0.954 |
Spiral | -0.921 |
ynes | -0.907 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
TIT | +0.207 |
YY | +0.187 |
tz | +0.186 |
ieth | +0.182 |
ucha | +0.179 |
Neg logit contributions | |
inver | -0.214 |
Fug | -0.209 |
Fract | -0.208 |
Spiral | -0.202 |
ynes | -0.200 |
Token | boys |
Token ID | 13202 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
TIT | +0.195 |
YY | +0.179 |
tz | +0.177 |
ieth | +0.176 |
ucha | +0.173 |
Neg logit contributions | |
inver | -0.135 |
Fug | -0.130 |
Fract | -0.130 |
Spiral | -0.125 |
ynes | -0.125 |
Token | beware |
Token ID | 40600 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
TIT | +0.168 |
YY | +0.158 |
tz | +0.156 |
ieth | +0.154 |
ucha | +0.153 |
Neg logit contributions | |
inver | -0.075 |
Fract | -0.073 |
Fug | -0.073 |
Spiral | -0.069 |
ynes | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
inver | +0.122 |
Fug | +0.119 |
Fract | +0.118 |
Spiral | +0.115 |
ynes | +0.113 |
Neg logit contributions | |
TIT | -0.142 |
YY | -0.130 |
tz | -0.129 |
ieth | -0.127 |
ucha | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
TIT | +0.887 |
YY | +0.809 |
tz | +0.806 |
ieth | +0.783 |
ucha | +0.772 |
Neg logit contributions | |
inver | -0.830 |
Fug | -0.805 |
Fract | -0.801 |
Spiral | -0.779 |
ynes | -0.770 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
TIT | +1.334 |
YY | +1.240 |
tz | +1.234 |
ieth | +1.216 |
ucha | +1.202 |
Neg logit contributions | |
inver | -0.705 |
Fug | -0.681 |
Fract | -0.677 |
Spiral | -0.649 |
ynes | -0.637 |
Token | : |
Token ID | 25 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
TIT | +2.915 |
tz | +2.636 |
YY | +2.631 |
ieth | +2.529 |
Judaism | +2.489 |
Neg logit contributions | |
inver | -3.202 |
Fug | -3.081 |
Fract | -3.077 |
ynes | -2.983 |
Spiral | -2.964 |
Token | j |
Token ID | 474 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
TIT | +0.581 |
YY | +0.532 |
tz | +0.529 |
ieth | +0.518 |
ucha | +0.511 |
Neg logit contributions | |
inver | -0.483 |
Fug | -0.470 |
Fract | -0.468 |
Spiral | -0.453 |
ynes | -0.448 |
Token | wt |
Token ID | 46569 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
TIT | +0.490 |
YY | +0.445 |
tz | +0.444 |
ieth | +0.434 |
ucha | +0.426 |
Neg logit contributions | |
inver | -0.501 |
Fug | -0.489 |
Fract | -0.487 |
Spiral | -0.473 |
ynes | -0.466 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
TIT | +0.348 |
YY | +0.316 |
tz | +0.315 |
ieth | +0.309 |
ucha | +0.302 |
Neg logit contributions | |
inver | -0.353 |
Fug | -0.345 |
Fract | -0.344 |
Spiral | -0.334 |
ynes | -0.328 |
Token | - |
Token ID | 532 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
TIT | +0.966 |
YY | +0.893 |
tz | +0.889 |
ieth | +0.872 |
ucha | +0.861 |
Neg logit contributions | |
inver | -0.630 |
Fug | -0.610 |
Fract | -0.607 |
Spiral | -0.586 |
ynes | -0.576 |
Token | PNG |
Token ID | 36182 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
TIT | +0.591 |
YY | +0.535 |
tz | +0.534 |
ieth | +0.520 |
ucha | +0.512 |
Neg logit contributions | |
inver | -0.599 |
Fug | -0.583 |
Fract | -0.581 |
Spiral | -0.562 |
ynes | -0.560 |
Token | larger |
Token ID | 4025 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
TIT | +1.220 |
tz | +1.074 |
YY | +1.069 |
ucha | +1.038 |
Judaism | +1.030 |
Neg logit contributions | |
inver | -1.192 |
Fug | -1.174 |
Fract | -1.147 |
ynes | -1.127 |
Spiral | -1.101 |
Token | image |
Token ID | 2939 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
TIT | +0.183 |
tz | +0.166 |
YY | +0.166 |
ieth | +0.159 |
ucha | +0.159 |
Neg logit contributions | |
inver | -0.172 |
Fug | -0.169 |
Fract | -0.167 |
ynes | -0.163 |
Spiral | -0.162 |
Token |
|
Token ID | 198 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
TIT | +0.634 |
YY | +0.575 |
tz | +0.572 |
ieth | +0.552 |
ucha | +0.546 |
Neg logit contributions | |
inver | -0.607 |
Fug | -0.585 |
Fract | -0.578 |
ynes | -0.568 |
Spiral | -0.566 |
Token |
|
Token ID | 198 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
TIT | +0.317 |
YY | +0.289 |
tz | +0.288 |
ieth | +0.282 |
ucha | +0.278 |
Neg logit contributions | |
inver | -0.275 |
Fug | -0.268 |
Fract | -0.267 |
Spiral | -0.258 |
ynes | -0.255 |
Token | larg |
Token ID | 15521 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
TIT | +0.320 |
YY | +0.286 |
ieth | +0.284 |
tz | +0.283 |
ucha | +0.276 |
Neg logit contributions | |
inver | -0.400 |
Fract | -0.389 |
Fug | -0.388 |
Spiral | -0.377 |
ynes | -0.373 |
Token | er |
Token ID | 263 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
TIT | +1.940 |
tz | +1.658 |
YY | +1.649 |
ucha | +1.586 |
ieth | +1.585 |
Neg logit contributions | |
inver | -4.125 |
Fug | -4.093 |
Fract | -4.051 |
Spiral | -3.973 |
ynes | -3.924 |
Token | image |
Token ID | 2939 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
TIT | +0.052 |
tz | +0.047 |
YY | +0.047 |
ieth | +0.046 |
ucha | +0.045 |
Neg logit contributions | |
inver | -0.047 |
Fug | -0.046 |
Fract | -0.045 |
Spiral | -0.044 |
ynes | -0.043 |
Token | T |
Token ID | 309 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
TIT | +0.450 |
tz | +0.392 |
YY | +0.388 |
Tag | +0.368 |
ieth | +0.367 |
Neg logit contributions | |
inver | -0.658 |
Fug | -0.641 |
Fract | -0.636 |
ynes | -0.632 |
Spiral | -0.630 |
Token | IFF |
Token ID | 29267 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
TIT | +0.403 |
YY | +0.354 |
tz | +0.350 |
ieth | +0.338 |
ucha | +0.331 |
Neg logit contributions | |
inver | -0.640 |
Fug | -0.628 |
Fract | -0.623 |
Spiral | -0.612 |
ynes | -0.603 |
Token | original |
Token ID | 2656 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
TIT | +0.633 |
YY | +0.557 |
tz | +0.550 |
Judaism | +0.544 |
ucha | +0.535 |
Neg logit contributions | |
inver | -0.669 |
Fug | -0.655 |
Fract | -0.652 |
ynes | -0.637 |
Spiral | -0.634 |
Token | . |
Token ID | 13 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
TIT | +0.274 |
YY | +0.250 |
tz | +0.248 |
ieth | +0.243 |
ucha | +0.239 |
Neg logit contributions | |
inver | -0.251 |
Fug | -0.244 |
Fract | -0.243 |
Spiral | -0.236 |
ynes | -0.233 |
Token | youtube |
Token ID | 11604 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
TIT | +0.435 |
YY | +0.375 |
tz | +0.372 |
ieth | +0.360 |
ucha | +0.350 |
Neg logit contributions | |
inver | -0.856 |
Fug | -0.840 |
Fract | -0.838 |
Spiral | -0.820 |
ynes | -0.813 |
Token | . |
Token ID | 13 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
TIT | +0.098 |
YY | +0.090 |
tz | +0.089 |
ieth | +0.087 |
ucha | +0.086 |
Neg logit contributions | |
inver | -0.091 |
Fug | -0.089 |
Fract | -0.088 |
Spiral | -0.086 |
ynes | -0.085 |
Token | com |
Token ID | 785 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
TIT | +0.434 |
YY | +0.390 |
tz | +0.388 |
ieth | +0.379 |
ucha | +0.372 |
Neg logit contributions | |
inver | -0.505 |
Fug | -0.493 |
Fract | -0.491 |
Spiral | -0.478 |
ynes | -0.472 |
Token | / |
Token ID | 14 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
inver | +0.069 |
Fug | +0.067 |
Fract | +0.067 |
Spiral | +0.065 |
ynes | +0.064 |
Neg logit contributions | |
TIT | -0.072 |
YY | -0.066 |
tz | -0.066 |
ieth | -0.064 |
ucha | -0.063 |
Token | channel |
Token ID | 17620 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
TIT | +0.623 |
YY | +0.569 |
tz | +0.566 |
ieth | +0.556 |
ucha | +0.548 |
Neg logit contributions | |
inver | -0.535 |
Fug | -0.521 |
Fract | -0.520 |
Spiral | -0.503 |
ynes | -0.497 |
Token | / |
Token ID | 14 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
TIT | +2.781 |
YY | +2.497 |
tz | +2.477 |
Tag | +2.370 |
ieth | +2.349 |
Neg logit contributions | |
inver | -3.320 |
Fug | -3.238 |
Fract | -3.210 |
ynes | -3.125 |
Spiral | -3.080 |
Token | UC |
Token ID | 9598 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
TIT | +0.418 |
YY | +0.375 |
tz | +0.373 |
ieth | +0.362 |
ucha | +0.356 |
Neg logit contributions | |
inver | -0.511 |
Fug | -0.500 |
Fract | -0.498 |
Spiral | -0.485 |
ynes | -0.478 |
Token | _ |
Token ID | 62 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
inver | +0.132 |
Fug | +0.129 |
Fract | +0.129 |
Spiral | +0.125 |
ynes | +0.124 |
Neg logit contributions | |
TIT | -0.110 |
YY | -0.099 |
tz | -0.098 |
ieth | -0.096 |
ucha | -0.094 |
Token | K |
Token ID | 42 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
inver | +0.635 |
Fug | +0.621 |
Fract | +0.619 |
Spiral | +0.602 |
ynes | +0.597 |
Neg logit contributions | |
TIT | -0.533 |
YY | -0.477 |
tz | -0.474 |
ieth | -0.465 |
ucha | -0.457 |
Token | k |
Token ID | 74 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
inver | +0.055 |
Fug | +0.053 |
Fract | +0.053 |
Spiral | +0.052 |
ynes | +0.051 |
Neg logit contributions | |
TIT | -0.046 |
YY | -0.042 |
tz | -0.041 |
ieth | -0.040 |
ucha | -0.040 |
Token | Flag |
Token ID | 34227 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
TIT | +0.220 |
YY | +0.195 |
tz | +0.194 |
ieth | +0.191 |
ucha | +0.187 |
Neg logit contributions | |
inver | -0.333 |
Fug | -0.328 |
Fract | -0.327 |
Spiral | -0.319 |
ynes | -0.316 |
Token | Reply |
Token ID | 14883 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
TIT | +0.965 |
tz | +0.873 |
YY | +0.871 |
ieth | +0.851 |
Judaism | +0.835 |
Neg logit contributions | |
inver | -1.086 |
Fug | -1.044 |
Fract | -1.039 |
ynes | -1.031 |
Spiral | -1.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
TIT | +2.301 |
YY | +2.095 |
tz | +2.089 |
ieth | +2.013 |
ucha | +1.997 |
Neg logit contributions | |
inver | -2.385 |
Fug | -2.289 |
Fract | -2.281 |
ynes | -2.222 |
Spiral | -2.214 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
TIT | +1.065 |
YY | +0.971 |
tz | +0.965 |
ieth | +0.941 |
ucha | +0.927 |
Neg logit contributions | |
inver | -0.994 |
Fug | -0.964 |
Fract | -0.959 |
Spiral | -0.932 |
ynes | -0.923 |
Token | 27 |
Token ID | 1983 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
TIT | +0.804 |
YY | +0.706 |
tz | +0.699 |
ieth | +0.679 |
ucha | +0.663 |
Neg logit contributions | |
inver | -1.315 |
Fug | -1.288 |
Fract | -1.284 |
Spiral | -1.254 |
ynes | -1.242 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
TIT | +0.634 |
YY | +0.573 |
tz | +0.568 |
ieth | +0.556 |
ucha | +0.545 |
Neg logit contributions | |
inver | -0.696 |
Fug | -0.677 |
Fract | -0.674 |
Spiral | -0.656 |
ynes | -0.651 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
TIT | +2.901 |
YY | +2.636 |
tz | +2.632 |
ieth | +2.542 |
Judaism | +2.511 |
Neg logit contributions | |
inver | -3.125 |
Fract | -2.993 |
Fug | -2.989 |
ynes | -2.924 |
Spiral | -2.904 |
Token |
|
Token ID | 198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
TIT | +0.863 |
YY | +0.787 |
tz | +0.784 |
ieth | +0.764 |
ucha | +0.753 |
Neg logit contributions | |
inver | -0.801 |
Fug | -0.778 |
Fract | -0.774 |
Spiral | -0.752 |
ynes | -0.744 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
TIT | +0.734 |
YY | +0.660 |
tz | +0.656 |
ieth | +0.643 |
ucha | +0.633 |
Neg logit contributions | |
inver | -0.879 |
Fug | -0.863 |
Fract | -0.859 |
Spiral | -0.836 |
ynes | -0.828 |
Token | Share |
Token ID | 8734 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
TIT | +2.275 |
YY | +2.032 |
tz | +2.029 |
ieth | +1.995 |
Judaism | +1.947 |
Neg logit contributions | |
inver | -2.871 |
Fract | -2.741 |
Fug | -2.739 |
ynes | -2.687 |
Spiral | -2.682 |
Token | this |
Token ID | 428 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
TIT | +2.971 |
tz | +2.766 |
YY | +2.763 |
ieth | +2.690 |
ucha | +2.664 |
Neg logit contributions | |
inver | -2.156 |
Fract | -2.097 |
Fug | -2.093 |
ynes | -2.047 |
Spiral | -2.025 |
Token | Flag |
Token ID | 34227 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
inver | +0.034 |
Fug | +0.034 |
Fract | +0.034 |
Spiral | +0.033 |
ynes | +0.033 |
Neg logit contributions | |
TIT | -0.024 |
YY | -0.021 |
tz | -0.021 |
ieth | -0.021 |
ucha | -0.021 |
Token | Reply |
Token ID | 14883 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
TIT | +0.921 |
tz | +0.836 |
YY | +0.830 |
ieth | +0.813 |
ucha | +0.795 |
Neg logit contributions | |
inver | -1.040 |
Fug | -1.004 |
Fract | -1.002 |
ynes | -0.998 |
Spiral | -0.977 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
TIT | +2.302 |
tz | +2.101 |
YY | +2.092 |
ieth | +2.012 |
ucha | +2.001 |
Neg logit contributions | |
inver | -2.417 |
Fug | -2.309 |
Fract | -2.297 |
ynes | -2.268 |
Spiral | -2.231 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
TIT | +0.897 |
YY | +0.818 |
tz | +0.814 |
ieth | +0.793 |
ucha | +0.781 |
Neg logit contributions | |
inver | -0.829 |
Fug | -0.805 |
Fract | -0.800 |
Spiral | -0.778 |
ynes | -0.770 |
Token | 55 |
Token ID | 2816 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
TIT | +0.708 |
YY | +0.625 |
tz | +0.620 |
ieth | +0.603 |
ucha | +0.590 |
Neg logit contributions | |
inver | -1.082 |
Fug | -1.059 |
Fract | -1.056 |
Spiral | -1.031 |
ynes | -1.021 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
TIT | +0.606 |
YY | +0.546 |
tz | +0.541 |
ieth | +0.532 |
ucha | +0.520 |
Neg logit contributions | |
inver | -0.693 |
Fug | -0.672 |
Fract | -0.668 |
Spiral | -0.653 |
ynes | -0.651 |
Token |
|
Token ID | 198 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
TIT | +2.891 |
tz | +2.630 |
YY | +2.629 |
ieth | +2.537 |
ucha | +2.508 |
Neg logit contributions | |
inver | -3.086 |
Fract | -2.954 |
Fug | -2.953 |
ynes | -2.881 |
Spiral | -2.865 |
Token |
|
Token ID | 198 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
TIT | +0.674 |
YY | +0.615 |
tz | +0.612 |
ieth | +0.598 |
ucha | +0.589 |
Neg logit contributions | |
inver | -0.613 |
Fug | -0.596 |
Fract | -0.593 |
Spiral | -0.576 |
ynes | -0.569 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
TIT | +0.605 |
YY | +0.545 |
tz | +0.543 |
ieth | +0.536 |
ucha | +0.531 |
Neg logit contributions | |
inver | -0.672 |
Fug | -0.662 |
Fract | -0.659 |
Spiral | -0.641 |
ynes | -0.637 |
Token | Share |
Token ID | 8734 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
TIT | +2.330 |
YY | +2.079 |
tz | +2.079 |
ieth | +2.049 |
ucha | +1.999 |
Neg logit contributions | |
inver | -2.858 |
Fug | -2.742 |
Fract | -2.742 |
Spiral | -2.678 |
ynes | -2.672 |
Token | this |
Token ID | 428 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
TIT | +3.111 |
tz | +2.894 |
YY | +2.890 |
ieth | +2.827 |
ucha | +2.804 |
Neg logit contributions | |
inver | -2.259 |
Fract | -2.205 |
Fug | -2.205 |
ynes | -2.155 |
Spiral | -2.133 |
Token |
|
Token ID | 198 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
TIT | +0.245 |
YY | +0.224 |
tz | +0.222 |
ieth | +0.217 |
ucha | +0.214 |
Neg logit contributions | |
inver | -0.222 |
Fug | -0.216 |
Fract | -0.214 |
Spiral | -0.208 |
ynes | -0.206 |
Token | Book |
Token ID | 10482 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
TIT | +0.351 |
YY | +0.317 |
tz | +0.314 |
ieth | +0.307 |
ucha | +0.301 |
Neg logit contributions | |
inver | -0.385 |
Fug | -0.376 |
Fract | -0.374 |
Spiral | -0.364 |
ynes | -0.359 |
Token | mark |
Token ID | 4102 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
TIT | +0.676 |
YY | +0.584 |
tz | +0.577 |
ieth | +0.562 |
ucha | +0.543 |
Neg logit contributions | |
inver | -1.240 |
Fug | -1.215 |
Fract | -1.211 |
Spiral | -1.181 |
ynes | -1.173 |
Token | with |
Token ID | 351 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
TIT | +1.498 |
tz | +1.389 |
YY | +1.382 |
ieth | +1.339 |
Judaism | +1.323 |
Neg logit contributions | |
inver | -1.120 |
Fug | -1.097 |
Fract | -1.092 |
Spiral | -1.064 |
ynes | -1.042 |
Token | : |
Token ID | 25 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
TIT | +0.296 |
YY | +0.270 |
tz | +0.268 |
ieth | +0.263 |
ucha | +0.259 |
Neg logit contributions | |
inver | -0.268 |
Fug | -0.261 |
Fract | -0.260 |
Spiral | -0.252 |
ynes | -0.249 |
Token | Delicious |
Token ID | 39528 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
TIT | +0.315 |
tz | +0.293 |
YY | +0.292 |
ieth | +0.286 |
ucha | +0.283 |
Neg logit contributions | |
inver | -0.201 |
Fug | -0.198 |
Fract | -0.196 |
Spiral | -0.188 |
ynes | -0.183 |
Token |
|
Token ID | 198 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
TIT | +2.898 |
YY | +2.610 |
tz | +2.566 |
ucha | +2.470 |
Tag | +2.449 |
Neg logit contributions | |
inver | -3.111 |
Fug | -2.973 |
Fract | -2.943 |
Spiral | -2.879 |
ynes | -2.864 |
Token |
|
Token ID | 198 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
TIT | +0.541 |
YY | +0.493 |
tz | +0.489 |
ieth | +0.476 |
ucha | +0.471 |
Neg logit contributions | |
inver | -0.497 |
Fug | -0.481 |
Fract | -0.479 |
Spiral | -0.465 |
ynes | -0.461 |
Token | D |
Token ID | 35 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
TIT | +0.632 |
YY | +0.579 |
tz | +0.576 |
ieth | +0.566 |
ucha | +0.557 |
Neg logit contributions | |
inver | -0.525 |
Fug | -0.511 |
Fract | -0.509 |
Spiral | -0.493 |
ynes | -0.485 |
Token | igg |
Token ID | 6950 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
inver | +0.098 |
Fug | +0.095 |
Fract | +0.095 |
Spiral | +0.092 |
ynes | +0.090 |
Neg logit contributions | |
TIT | -0.140 |
YY | -0.130 |
tz | -0.129 |
ieth | -0.127 |
ucha | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
TIT | +0.987 |
YY | +0.892 |
tz | +0.855 |
ieth | +0.852 |
Judaism | +0.842 |
Neg logit contributions | |
inver | -1.067 |
Fug | -1.012 |
Fract | -0.991 |
ynes | -0.979 |
awa | -0.970 |
Token | comment |
Token ID | 2912 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
inver | +0.381 |
Fug | +0.371 |
Fract | +0.369 |
Spiral | +0.358 |
ynes | +0.353 |
Neg logit contributions | |
TIT | -0.435 |
YY | -0.397 |
tz | -0.395 |
ieth | -0.388 |
ucha | -0.382 |
Token | on |
Token ID | 319 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
inver | +0.265 |
Fug | +0.256 |
Fract | +0.254 |
Spiral | +0.245 |
ynes | +0.241 |
Neg logit contributions | |
TIT | -0.443 |
YY | -0.410 |
tz | -0.409 |
ieth | -0.401 |
ucha | -0.396 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
inver | +0.207 |
Fug | +0.203 |
Fract | +0.203 |
Spiral | +0.197 |
ynes | +0.194 |
Neg logit contributions | |
TIT | -0.174 |
YY | -0.156 |
tz | -0.154 |
ieth | -0.152 |
ucha | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
inver | +0.484 |
Fug | +0.472 |
Fract | +0.470 |
Spiral | +0.454 |
ynes | +0.446 |
Neg logit contributions | |
TIT | -0.594 |
YY | -0.545 |
tz | -0.541 |
ieth | -0.534 |
ucha | -0.523 |
Token |
|
Token ID | 198 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
TIT | +0.590 |
YY | +0.538 |
tz | +0.536 |
ieth | +0.523 |
ucha | +0.516 |
Neg logit contributions | |
inver | -0.530 |
Fug | -0.516 |
Fract | -0.513 |
Spiral | -0.498 |
ynes | -0.492 |
Token | NY |
Token ID | 12805 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
TIT | +0.424 |
YY | +0.365 |
tz | +0.364 |
ieth | +0.356 |
ucha | +0.346 |
Neg logit contributions | |
inver | -0.816 |
Fug | -0.801 |
Fract | -0.799 |
Spiral | -0.782 |
ynes | -0.778 |
Token | T |
Token ID | 51 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
TIT | +2.283 |
YY | +2.001 |
tz | +1.979 |
Tag | +1.848 |
ieth | +1.846 |
Neg logit contributions | |
inver | -3.658 |
Fug | -3.564 |
Fract | -3.533 |
Spiral | -3.451 |
ynes | -3.445 |
Token | Pick |
Token ID | 12346 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
TIT | +0.894 |
YY | +0.816 |
tz | +0.812 |
ieth | +0.794 |
ucha | +0.781 |
Neg logit contributions | |
inver | -0.802 |
Fug | -0.779 |
Fract | -0.775 |
Spiral | -0.753 |
ynes | -0.745 |
Token | Stephen |
Token ID | 7970 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
TIT | +0.410 |
YY | +0.375 |
tz | +0.373 |
ieth | +0.366 |
ucha | +0.361 |
Neg logit contributions | |
inver | -0.339 |
Fug | -0.330 |
Fract | -0.328 |
Spiral | -0.318 |
ynes | -0.314 |
Token | East |
Token ID | 3687 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
TIT | +0.309 |
YY | +0.283 |
tz | +0.282 |
ieth | +0.276 |
ucha | +0.273 |
Neg logit contributions | |
inver | -0.260 |
Fug | -0.252 |
Fract | -0.251 |
Spiral | -0.243 |
ynes | -0.240 |
Token | on |
Token ID | 261 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
inver | +0.426 |
Fug | +0.415 |
Fract | +0.414 |
Spiral | +0.401 |
ynes | +0.396 |
Neg logit contributions | |
TIT | -0.472 |
YY | -0.430 |
tz | -0.427 |
ieth | -0.419 |
ucha | -0.413 |
Token | comment |
Token ID | 2912 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
inver | +0.381 |
Fug | +0.371 |
Fract | +0.370 |
Spiral | +0.358 |
ynes | +0.353 |
Neg logit contributions | |
TIT | -0.438 |
YY | -0.399 |
tz | -0.396 |
ieth | -0.390 |
ucha | -0.384 |
Token | on |
Token ID | 319 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
inver | +0.261 |
Fug | +0.252 |
Fract | +0.251 |
Spiral | +0.242 |
ynes | +0.238 |
Neg logit contributions | |
TIT | -0.437 |
YY | -0.405 |
tz | -0.403 |
ieth | -0.396 |
ucha | -0.391 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
inver | +0.215 |
Fug | +0.211 |
Fract | +0.210 |
Spiral | +0.205 |
ynes | +0.201 |
Neg logit contributions | |
TIT | -0.180 |
YY | -0.161 |
tz | -0.160 |
ieth | -0.157 |
ucha | -0.154 |
Token |
|
Token ID | 198 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
inver | +0.731 |
Fug | +0.713 |
Fract | +0.711 |
Spiral | +0.686 |
ynes | +0.672 |
Neg logit contributions | |
TIT | -0.901 |
YY | -0.827 |
tz | -0.820 |
ieth | -0.812 |
ucha | -0.792 |
Token |
|
Token ID | 198 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
TIT | +0.589 |
YY | +0.538 |
tz | +0.535 |
ieth | +0.523 |
ucha | +0.515 |
Neg logit contributions | |
inver | -0.530 |
Fug | -0.515 |
Fract | -0.513 |
Spiral | -0.498 |
ynes | -0.492 |
Token | NY |
Token ID | 12805 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
TIT | +0.423 |
YY | +0.366 |
tz | +0.364 |
ieth | +0.355 |
ucha | +0.345 |
Neg logit contributions | |
inver | -0.804 |
Fug | -0.789 |
Fract | -0.787 |
Spiral | -0.770 |
ynes | -0.765 |
Token | T |
Token ID | 51 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
TIT | +2.299 |
YY | +2.018 |
tz | +1.998 |
ieth | +1.874 |
Tag | +1.861 |
Neg logit contributions | |
inver | -3.624 |
Fug | -3.544 |
Fract | -3.511 |
Spiral | -3.429 |
ynes | -3.416 |
Token | Pick |
Token ID | 12346 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
TIT | +0.756 |
YY | +0.690 |
tz | +0.686 |
ieth | +0.673 |
ucha | +0.663 |
Neg logit contributions | |
inver | -0.660 |
Fug | -0.644 |
Fract | -0.641 |
Spiral | -0.621 |
ynes | -0.612 |
Token | M |
Token ID | 337 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
TIT | +0.485 |
YY | +0.444 |
tz | +0.442 |
ieth | +0.433 |
ucha | +0.427 |
Neg logit contributions | |
inver | -0.407 |
Fug | -0.396 |
Fract | -0.395 |
Spiral | -0.382 |
ynes | -0.377 |
Token | . |
Token ID | 13 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
TIT | +0.166 |
YY | +0.150 |
tz | +0.149 |
ieth | +0.146 |
ucha | +0.144 |
Neg logit contributions | |
inver | -0.173 |
Fug | -0.169 |
Fract | -0.168 |
Spiral | -0.164 |
ynes | -0.162 |
Token | G |
Token ID | 402 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
TIT | +0.029 |
YY | +0.027 |
tz | +0.027 |
ieth | +0.026 |
ucha | +0.026 |
Neg logit contributions | |
inver | -0.027 |
Fug | -0.026 |
Fract | -0.026 |
Spiral | -0.025 |
ynes | -0.025 |
Token | er |
Token ID | 263 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
TIT | +0.581 |
YY | +0.507 |
tz | +0.505 |
ieth | +0.486 |
ucha | +0.476 |
Neg logit contributions | |
inver | -1.138 |
Fug | -1.118 |
Fract | -1.113 |
Spiral | -1.085 |
ynes | -1.070 |
Token | magnet |
Token ID | 19972 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
TIT | +1.157 |
YY | +1.087 |
tz | +1.084 |
ieth | +1.064 |
Judaism | +1.054 |
Neg logit contributions | |
inver | -0.422 |
Fug | -0.406 |
Fract | -0.400 |
ynes | -0.379 |
Spiral | -0.374 |
Token | ? |
Token ID | 30 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
inver | +0.038 |
Fug | +0.037 |
Fract | +0.036 |
Spiral | +0.035 |
ynes | +0.035 |
Neg logit contributions | |
TIT | -0.042 |
YY | -0.038 |
tz | -0.038 |
ieth | -0.037 |
ucha | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
TIT | +0.023 |
YY | +0.021 |
tz | +0.021 |
ieth | +0.021 |
ucha | +0.021 |
Neg logit contributions | |
inver | -0.020 |
Fug | -0.019 |
Fract | -0.019 |
Spiral | -0.018 |
ynes | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
TIT | +0.299 |
YY | +0.273 |
tz | +0.272 |
ieth | +0.265 |
ucha | +0.262 |
Neg logit contributions | |
inver | -0.270 |
Fug | -0.262 |
Fract | -0.261 |
Spiral | -0.253 |
ynes | -0.250 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
TIT | +0.640 |
YY | +0.594 |
tz | +0.592 |
ieth | +0.583 |
ucha | +0.576 |
Neg logit contributions | |
inver | -0.339 |
Fug | -0.327 |
Fract | -0.325 |
Spiral | -0.312 |
ynes | -0.306 |
Token | : |
Token ID | 25 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
TIT | +2.782 |
tz | +2.510 |
YY | +2.509 |
ieth | +2.412 |
Judaism | +2.377 |
Neg logit contributions | |
inver | -3.067 |
Fug | -2.950 |
Fract | -2.943 |
ynes | -2.862 |
Spiral | -2.839 |
Token | hey |
Token ID | 17207 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
TIT | +0.461 |
YY | +0.422 |
tz | +0.420 |
ieth | +0.411 |
ucha | +0.405 |
Neg logit contributions | |
inver | -0.386 |
Fug | -0.375 |
Fract | -0.374 |
Spiral | -0.362 |
ynes | -0.358 |
Token | _ |
Token ID | 62 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
inver | +1.397 |
Fug | +1.362 |
Fract | +1.356 |
Spiral | +1.319 |
ynes | +1.309 |
Neg logit contributions | |
TIT | -1.289 |
YY | -1.158 |
tz | -1.148 |
ieth | -1.130 |
ucha | -1.110 |
Token | ler |
Token ID | 1754 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
inver | +0.924 |
Fug | +0.901 |
Fract | +0.896 |
Spiral | +0.873 |
ynes | +0.868 |
Neg logit contributions | |
TIT | -0.842 |
YY | -0.758 |
tz | -0.750 |
ieth | -0.738 |
ucha | -0.725 |
Token | oy |
Token ID | 726 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
inver | +0.559 |
Fug | +0.546 |
Fract | +0.544 |
Spiral | +0.529 |
ynes | +0.520 |
Neg logit contributions | |
TIT | -0.561 |
tz | -0.510 |
YY | -0.510 |
ieth | -0.497 |
ucha | -0.490 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
TIT | +0.009 |
YY | +0.008 |
tz | +0.008 |
ieth | +0.008 |
ucha | +0.007 |
Neg logit contributions | |
inver | -0.008 |
Fug | -0.008 |
Fract | -0.007 |
Spiral | -0.007 |
ynes | -0.007 |
Token | Book |
Token ID | 10482 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
TIT | +0.171 |
YY | +0.154 |
tz | +0.153 |
ieth | +0.149 |
ucha | +0.147 |
Neg logit contributions | |
inver | -0.196 |
Fug | -0.191 |
Fract | -0.190 |
Spiral | -0.185 |
ynes | -0.183 |
Token | mark |
Token ID | 4102 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
TIT | +0.392 |
YY | +0.339 |
tz | +0.335 |
ieth | +0.328 |
ucha | +0.315 |
Neg logit contributions | |
inver | -0.700 |
Fug | -0.687 |
Fract | -0.686 |
Spiral | -0.669 |
ynes | -0.662 |
Token | with |
Token ID | 351 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
TIT | +1.423 |
tz | +1.321 |
YY | +1.313 |
ieth | +1.271 |
ucha | +1.255 |
Neg logit contributions | |
inver | -1.056 |
Fug | -1.038 |
Fract | -1.033 |
Spiral | -1.007 |
ynes | -0.984 |
Token | : |
Token ID | 25 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
TIT | +0.171 |
YY | +0.156 |
tz | +0.155 |
ieth | +0.153 |
ucha | +0.150 |
Neg logit contributions | |
inver | -0.151 |
Fug | -0.147 |
Fract | -0.147 |
Spiral | -0.142 |
ynes | -0.140 |
Token | Delicious |
Token ID | 39528 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
TIT | +0.268 |
tz | +0.247 |
YY | +0.247 |
ieth | +0.243 |
ucha | +0.239 |
Neg logit contributions | |
inver | -0.178 |
Fug | -0.174 |
Fract | -0.173 |
Spiral | -0.166 |
ynes | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
TIT | +2.795 |
YY | +2.509 |
tz | +2.461 |
ucha | +2.366 |
Tag | +2.365 |
Neg logit contributions | |
inver | -3.083 |
Fug | -2.949 |
Fract | -2.907 |
Spiral | -2.846 |
ynes | -2.842 |
Token |
|
Token ID | 198 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
TIT | +0.406 |
YY | +0.370 |
tz | +0.367 |
ieth | +0.358 |
ucha | +0.353 |
Neg logit contributions | |
inver | -0.373 |
Fug | -0.361 |
Fract | -0.359 |
Spiral | -0.349 |
ynes | -0.346 |
Token | D |
Token ID | 35 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
TIT | +0.534 |
YY | +0.489 |
tz | +0.487 |
ieth | +0.479 |
ucha | +0.471 |
Neg logit contributions | |
inver | -0.440 |
Fug | -0.429 |
Fract | -0.427 |
Spiral | -0.413 |
ynes | -0.406 |
Token | igg |
Token ID | 6950 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
inver | +0.137 |
Fug | +0.132 |
Fract | +0.132 |
Spiral | +0.127 |
ynes | +0.125 |
Neg logit contributions | |
TIT | -0.191 |
YY | -0.177 |
tz | -0.175 |
ieth | -0.172 |
ucha | -0.170 |
Token |
|
Token ID | 198 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
TIT | +0.876 |
YY | +0.791 |
tz | +0.763 |
ieth | +0.757 |
Judaism | +0.746 |
Neg logit contributions | |
inver | -0.914 |
Fug | -0.868 |
Fract | -0.852 |
ynes | -0.842 |
Spiral | -0.830 |
Token | this |
Token ID | 428 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
TIT | +0.497 |
YY | +0.458 |
tz | +0.456 |
ieth | +0.448 |
ucha | +0.441 |
Neg logit contributions | |
inver | -0.358 |
Fug | -0.347 |
Fract | -0.346 |
Spiral | -0.334 |
ynes | -0.329 |
Token | ). |
Token ID | 737 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
inver | +0.163 |
Fug | +0.159 |
Fract | +0.158 |
Spiral | +0.153 |
ynes | +0.151 |
Neg logit contributions | |
TIT | -0.186 |
YY | -0.170 |
tz | -0.169 |
ieth | -0.166 |
ucha | -0.163 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
inver | +0.100 |
Fug | +0.098 |
Fract | +0.097 |
Spiral | +0.094 |
ynes | +0.093 |
Neg logit contributions | |
TIT | -0.124 |
YY | -0.114 |
tz | -0.113 |
ieth | -0.111 |
ucha | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
TIT | +0.182 |
YY | +0.166 |
tz | +0.165 |
ieth | +0.162 |
ucha | +0.159 |
Neg logit contributions | |
inver | -0.163 |
Fug | -0.158 |
Fract | -0.158 |
Spiral | -0.153 |
ynes | -0.151 |
Token | H |
Token ID | 39 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
TIT | +0.370 |
YY | +0.334 |
tz | +0.332 |
ieth | +0.324 |
ucha | +0.319 |
Neg logit contributions | |
inver | -0.412 |
Fug | -0.403 |
Fract | -0.401 |
Spiral | -0.390 |
ynes | -0.386 |
Token | azel |
Token ID | 41319 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
inver | +0.817 |
Fug | +0.797 |
Fract | +0.793 |
Spiral | +0.773 |
ynes | +0.768 |
Neg logit contributions | |
TIT | -0.791 |
YY | -0.711 |
tz | -0.707 |
ieth | -0.691 |
ucha | -0.680 |
Token | nut |
Token ID | 14930 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
TIT | +2.326 |
tz | +2.105 |
YY | +2.096 |
ieth | +2.089 |
ucha | +2.072 |
Neg logit contributions | |
inver | -3.362 |
Fug | -3.251 |
Fract | -3.244 |
ynes | -3.176 |
Spiral | -3.137 |
Token | Fl |
Token ID | 1610 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
TIT | +1.464 |
YY | +1.340 |
tz | +1.339 |
ieth | +1.311 |
ucha | +1.289 |
Neg logit contributions | |
inver | -1.407 |
Fug | -1.358 |
Fract | -1.346 |
ynes | -1.316 |
Spiral | -1.302 |
Token | our |
Token ID | 454 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
TIT | +1.788 |
YY | +1.668 |
tz | +1.661 |
ieth | +1.653 |
ucha | +1.628 |
Neg logit contributions | |
inver | -1.315 |
Fug | -1.297 |
Fract | -1.282 |
Spiral | -1.245 |
ynes | -1.190 |
Token | — |
Token ID | 960 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
TIT | +1.057 |
YY | +0.973 |
tz | +0.968 |
ieth | +0.951 |
ucha | +0.937 |
Neg logit contributions | |
inver | -0.757 |
Fug | -0.735 |
Fract | -0.732 |
Spiral | -0.707 |
ynes | -0.695 |
Token | This |
Token ID | 1212 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
inver | +0.153 |
Fug | +0.149 |
Fract | +0.149 |
Spiral | +0.145 |
ynes | +0.143 |
Neg logit contributions | |
TIT | -0.143 |
YY | -0.129 |
tz | -0.129 |
ieth | -0.126 |
ucha | -0.124 |
Token | bind |
Token ID | 21653 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
TIT | +0.424 |
YY | +0.372 |
tz | +0.369 |
ieth | +0.357 |
ucha | +0.349 |
Neg logit contributions | |
inver | -0.705 |
Fug | -0.693 |
Fract | -0.691 |
Spiral | -0.675 |
ynes | -0.667 |
Token | directive |
Token ID | 22644 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
inver | +0.308 |
Fug | +0.300 |
Fract | +0.299 |
Spiral | +0.290 |
ynes | +0.286 |
Neg logit contributions | |
TIT | -0.352 |
YY | -0.322 |
tz | -0.320 |
ieth | -0.314 |
ucha | -0.309 |
Token | : |
Token ID | 25 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
inver | +0.239 |
Fug | +0.234 |
Fract | +0.233 |
Spiral | +0.225 |
ynes | +0.223 |
Neg logit contributions | |
TIT | -0.274 |
YY | -0.251 |
tz | -0.249 |
ieth | -0.245 |
ucha | -0.240 |
Token |
|
Token ID | 198 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
TIT | +0.472 |
YY | +0.431 |
tz | +0.429 |
ieth | +0.421 |
ucha | +0.415 |
Neg logit contributions | |
inver | -0.402 |
Fug | -0.390 |
Fract | -0.389 |
Spiral | -0.377 |
ynes | -0.371 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
TIT | +0.660 |
YY | +0.603 |
tz | +0.599 |
ieth | +0.585 |
ucha | +0.577 |
Neg logit contributions | |
inver | -0.601 |
Fug | -0.585 |
Fract | -0.581 |
Spiral | -0.564 |
ynes | -0.558 |
Token | < |
Token ID | 27 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
TIT | +0.622 |
YY | +0.550 |
tz | +0.545 |
ieth | +0.530 |
ucha | +0.518 |
Neg logit contributions | |
inver | -0.929 |
Fug | -0.910 |
Fract | -0.907 |
Spiral | -0.885 |
ynes | -0.873 |
Token | body |
Token ID | 2618 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
TIT | +2.413 |
YY | +2.105 |
tz | +2.097 |
ieth | +2.039 |
Tag | +2.001 |
Neg logit contributions | |
inver | -3.361 |
Fract | -3.288 |
Fug | -3.280 |
Spiral | -3.184 |
ynes | -3.153 |
Token | ng |
Token ID | 23370 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
TIT | +0.089 |
YY | +0.081 |
tz | +0.080 |
ieth | +0.078 |
ucha | +0.077 |
Neg logit contributions | |
inver | -0.102 |
Fug | -0.100 |
Fract | -0.099 |
Spiral | -0.097 |
ynes | -0.096 |
Token | - |
Token ID | 12 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
TIT | +1.168 |
YY | +1.066 |
tz | +1.059 |
ieth | +1.039 |
ucha | +1.023 |
Neg logit contributions | |
inver | -0.890 |
Fug | -0.868 |
Fract | -0.861 |
Spiral | -0.833 |
ynes | -0.820 |
Token | controller |
Token ID | 36500 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
TIT | +0.550 |
YY | +0.487 |
tz | +0.485 |
ieth | +0.472 |
ucha | +0.462 |
Neg logit contributions | |
inver | -0.796 |
Fug | -0.781 |
Fract | -0.778 |
Spiral | -0.760 |
ynes | -0.749 |
Token | =" |
Token ID | 2625 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
TIT | +0.027 |
YY | +0.024 |
tz | +0.024 |
ieth | +0.023 |
ucha | +0.022 |
Neg logit contributions | |
inver | -0.039 |
Fug | -0.038 |
Fract | -0.038 |
Spiral | -0.037 |
ynes | -0.037 |
Token | success |
Token ID | 1943 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
TIT | +0.182 |
YY | +0.167 |
tz | +0.166 |
ieth | +0.163 |
ucha | +0.161 |
Neg logit contributions | |
inver | -0.136 |
Fug | -0.133 |
Fract | -0.132 |
Spiral | -0.128 |
ynes | -0.127 |
Token | ". |
Token ID | 1911 |
Feature activation | -8.11e-02 |
Pos logit contributions | |
inver | +0.664 |
Fug | +0.649 |
Fract | +0.647 |
Spiral | +0.630 |
ynes | +0.623 |
Neg logit contributions | |
TIT | -0.532 |
YY | -0.477 |
tz | -0.474 |
ieth | -0.462 |
ucha | -0.454 |
Token |
|
Token ID | 198 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
TIT | +0.066 |
YY | +0.060 |
tz | +0.060 |
ieth | +0.059 |
ucha | +0.058 |
Neg logit contributions | |
inver | -0.057 |
Fug | -0.055 |
Fract | -0.055 |
Spiral | -0.053 |
ynes | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
inver | +0.222 |
Fug | +0.216 |
Fract | +0.215 |
Spiral | +0.208 |
ynes | +0.206 |
Neg logit contributions | |
TIT | -0.248 |
YY | -0.227 |
tz | -0.225 |
ieth | -0.221 |
ucha | -0.217 |
Token | L |
Token ID | 43 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
inver | +0.052 |
Fug | +0.050 |
Fract | +0.050 |
Spiral | +0.049 |
ynes | +0.048 |
Neg logit contributions | |
TIT | -0.051 |
YY | -0.047 |
tz | -0.047 |
ieth | -0.046 |
ucha | -0.045 |
Token | ever |
Token ID | 964 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
inver | +0.753 |
Fug | +0.730 |
Fract | +0.714 |
ynes | +0.712 |
Spiral | +0.709 |
Neg logit contributions | |
TIT | -0.598 |
YY | -0.538 |
tz | -0.527 |
ieth | -0.515 |
Judaism | -0.512 |
Token | , |
Token ID | 11 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
TIT | +3.308 |
tz | +3.089 |
YY | +3.075 |
ieth | +3.012 |
ucha | +2.949 |
Neg logit contributions | |
inver | -2.308 |
Fract | -2.292 |
Fug | -2.275 |
Spiral | -2.223 |
ynes | -2.190 |
Token | like |
Token ID | 588 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
TIT | +0.361 |
YY | +0.330 |
tz | +0.328 |
ieth | +0.322 |
ucha | +0.317 |
Neg logit contributions | |
inver | -0.309 |
Fug | -0.301 |
Fract | -0.300 |
Spiral | -0.291 |
ynes | -0.287 |
Token | Gibbs |
Token ID | 41071 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
TIT | +0.024 |
YY | +0.022 |
tz | +0.022 |
ieth | +0.021 |
ucha | +0.021 |
Neg logit contributions | |
inver | -0.026 |
Fug | -0.026 |
Fract | -0.026 |
Spiral | -0.025 |
ynes | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
inver | +0.701 |
Fug | +0.678 |
Fract | +0.673 |
Spiral | +0.650 |
ynes | +0.639 |
Neg logit contributions | |
TIT | -1.045 |
YY | -0.963 |
tz | -0.958 |
ieth | -0.942 |
ucha | -0.931 |
Token | was |
Token ID | 373 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
TIT | +0.514 |
YY | +0.475 |
tz | +0.473 |
ieth | +0.465 |
ucha | +0.459 |
Neg logit contributions | |
inver | -0.335 |
Fug | -0.325 |
Fract | -0.323 |
Spiral | -0.312 |
ynes | -0.307 |
Token | PT |
Token ID | 11571 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
TIT | +1.143 |
YY | +1.044 |
tz | +1.036 |
ieth | +1.015 |
ucha | +0.999 |
Neg logit contributions | |
inver | -1.067 |
Fug | -1.044 |
Fract | -1.038 |
Spiral | -1.006 |
ynes | -0.992 |
Token | PowerPoint |
Token ID | 43563 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
TIT | +0.492 |
YY | +0.438 |
tz | +0.435 |
ieth | +0.422 |
ucha | +0.419 |
Neg logit contributions | |
inver | -0.661 |
Fug | -0.647 |
Fract | -0.645 |
Spiral | -0.628 |
ynes | -0.627 |
Token | slide |
Token ID | 10649 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
inver | +0.018 |
Fract | +0.017 |
Fug | +0.017 |
ynes | +0.016 |
Spiral | +0.016 |
Neg logit contributions | |
TIT | -0.034 |
tz | -0.031 |
YY | -0.031 |
Tag | -0.031 |
ucha | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
TIT | +0.211 |
YY | +0.193 |
tz | +0.192 |
ieth | +0.187 |
ucha | +0.185 |
Neg logit contributions | |
inver | -0.193 |
Fug | -0.187 |
Fract | -0.186 |
Spiral | -0.180 |
ynes | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
TIT | +0.080 |
YY | +0.073 |
tz | +0.073 |
ieth | +0.072 |
ucha | +0.071 |
Neg logit contributions | |
inver | -0.070 |
Fug | -0.068 |
Fract | -0.068 |
Spiral | -0.066 |
ynes | -0.065 |
Token | Power |
Token ID | 13434 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
TIT | +0.215 |
YY | +0.194 |
tz | +0.193 |
ieth | +0.189 |
ucha | +0.185 |
Neg logit contributions | |
inver | -0.235 |
Fug | -0.230 |
Fract | -0.229 |
Spiral | -0.223 |
ynes | -0.220 |
Token | Point |
Token ID | 12727 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
TIT | +2.060 |
YY | +1.826 |
tz | +1.773 |
ieth | +1.723 |
Judaism | +1.699 |
Neg logit contributions | |
inver | -3.613 |
Fug | -3.581 |
Fract | -3.556 |
Spiral | -3.472 |
ynes | -3.451 |
Token | slide |
Token ID | 10649 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
TIT | +0.437 |
tz | +0.409 |
YY | +0.406 |
ucha | +0.397 |
Judaism | +0.396 |
Neg logit contributions | |
inver | -0.218 |
Fug | -0.207 |
Fract | -0.206 |
ynes | -0.199 |
Spiral | -0.195 |
Token | PNG |
Token ID | 36182 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
TIT | +0.591 |
YY | +0.535 |
tz | +0.534 |
ieth | +0.520 |
ucha | +0.512 |
Neg logit contributions | |
inver | -0.599 |
Fug | -0.583 |
Fract | -0.581 |
Spiral | -0.562 |
ynes | -0.560 |
Token | larger |
Token ID | 4025 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
TIT | +1.220 |
tz | +1.074 |
YY | +1.069 |
ucha | +1.038 |
Judaism | +1.030 |
Neg logit contributions | |
inver | -1.192 |
Fug | -1.174 |
Fract | -1.147 |
ynes | -1.127 |
Spiral | -1.101 |
Token | image |
Token ID | 2939 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
TIT | +0.183 |
tz | +0.166 |
YY | +0.166 |
ieth | +0.159 |
ucha | +0.159 |
Neg logit contributions | |
inver | -0.172 |
Fug | -0.169 |
Fract | -0.167 |
ynes | -0.163 |
Spiral | -0.162 |
Token | Interior |
Token ID | 19614 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
inver | +0.540 |
Fug | +0.524 |
Fract | +0.521 |
Spiral | +0.503 |
ynes | +0.494 |
Neg logit contributions | |
TIT | -0.785 |
YY | -0.723 |
tz | -0.720 |
ieth | -0.707 |
ucha | -0.698 |
Token | Ministry |
Token ID | 9475 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
inver | +0.448 |
Fug | +0.434 |
Fract | +0.432 |
Spiral | +0.417 |
ynes | +0.410 |
Neg logit contributions | |
TIT | -0.656 |
YY | -0.605 |
tz | -0.602 |
ieth | -0.592 |
ucha | -0.584 |
Token | staff |
Token ID | 3085 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
inver | +0.656 |
Fug | +0.635 |
Fract | +0.634 |
Spiral | +0.612 |
ynes | +0.605 |
Neg logit contributions | |
TIT | -0.913 |
YY | -0.840 |
tz | -0.836 |
ieth | -0.820 |
ucha | -0.808 |
Token | from |
Token ID | 422 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
inver | +0.679 |
Fug | +0.662 |
Fract | +0.658 |
Spiral | +0.637 |
ynes | +0.627 |
Neg logit contributions | |
TIT | -0.802 |
YY | -0.732 |
tz | -0.727 |
ieth | -0.714 |
ucha | -0.703 |
Token | h |
Token ID | 289 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
TIT | +0.335 |
tz | +0.311 |
YY | +0.311 |
ieth | +0.303 |
ucha | +0.300 |
Neg logit contributions | |
inver | -0.200 |
Fract | -0.195 |
Fug | -0.194 |
Spiral | -0.187 |
ynes | -0.187 |
Token | arrass |
Token ID | 9187 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
inver | +0.705 |
Fug | +0.687 |
Fract | +0.684 |
Spiral | +0.663 |
ynes | +0.652 |
Neg logit contributions | |
TIT | -0.832 |
YY | -0.762 |
tz | -0.758 |
ieth | -0.743 |
ucha | -0.732 |
Token | ing |
Token ID | 278 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
TIT | +2.114 |
tz | +1.876 |
YY | +1.872 |
ieth | +1.782 |
ucha | +1.747 |
Neg logit contributions | |
inver | -3.484 |
Fug | -3.424 |
Fract | -3.420 |
ynes | -3.350 |
Spiral | -3.331 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
TIT | +0.570 |
YY | +0.525 |
tz | +0.520 |
ieth | +0.510 |
ucha | +0.502 |
Neg logit contributions | |
inver | -0.433 |
Fract | -0.419 |
Fug | -0.418 |
Spiral | -0.404 |
ynes | -0.401 |
Token | obstruct |
Token ID | 26520 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
TIT | +0.001 |
tz | +0.001 |
YY | +0.001 |
ieth | +0.001 |
ucha | +0.001 |
Neg logit contributions | |
inver | -0.001 |
Fract | -0.001 |
Fug | -0.001 |
Spiral | -0.001 |
ynes | -0.001 |
Token | ing |
Token ID | 278 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
inver | +0.982 |
Fug | +0.960 |
Fract | +0.958 |
Spiral | +0.934 |
ynes | +0.926 |
Neg logit contributions | |
TIT | -0.696 |
YY | -0.619 |
tz | -0.615 |
ieth | -0.599 |
ucha | -0.586 |
Token | Jane |
Token ID | 12091 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
inver | +0.077 |
Fug | +0.075 |
Fract | +0.074 |
Spiral | +0.072 |
ynes | +0.071 |
Neg logit contributions | |
TIT | -0.112 |
YY | -0.103 |
tz | -0.103 |
ieth | -0.101 |
ucha | -0.099 |
Token | Flag |
Token ID | 34227 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
TIT | +0.534 |
YY | +0.474 |
tz | +0.466 |
ieth | +0.464 |
ucha | +0.453 |
Neg logit contributions | |
inver | -0.742 |
Fug | -0.728 |
Fract | -0.727 |
Spiral | -0.707 |
ynes | -0.704 |
Token | Reply |
Token ID | 14883 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
TIT | +0.931 |
YY | +0.847 |
tz | +0.843 |
ieth | +0.824 |
ucha | +0.811 |
Neg logit contributions | |
inver | -0.916 |
Fug | -0.892 |
Fract | -0.889 |
Spiral | -0.864 |
ynes | -0.859 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
TIT | +2.488 |
tz | +2.252 |
YY | +2.251 |
ieth | +2.185 |
ucha | +2.157 |
Neg logit contributions | |
inver | -2.501 |
Fug | -2.402 |
Fract | -2.381 |
ynes | -2.360 |
Spiral | -2.322 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
TIT | +1.243 |
YY | +1.132 |
tz | +1.127 |
ieth | +1.093 |
ucha | +1.078 |
Neg logit contributions | |
inver | -1.182 |
Fug | -1.143 |
Fract | -1.135 |
Spiral | -1.105 |
ynes | -1.098 |
Token | 14 |
Token ID | 1415 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
TIT | +1.009 |
YY | +0.897 |
tz | +0.890 |
ieth | +0.867 |
ucha | +0.849 |
Neg logit contributions | |
inver | -1.417 |
Fug | -1.386 |
Fract | -1.382 |
Spiral | -1.348 |
ynes | -1.334 |
Token | Recommend |
Token ID | 30361 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
TIT | +0.849 |
YY | +0.768 |
tz | +0.763 |
ieth | +0.746 |
ucha | +0.734 |
Neg logit contributions | |
inver | -0.926 |
Fug | -0.903 |
Fract | -0.899 |
Spiral | -0.875 |
ynes | -0.867 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
TIT | +2.766 |
YY | +2.516 |
tz | +2.515 |
ieth | +2.437 |
Judaism | +2.403 |
Neg logit contributions | |
inver | -2.913 |
Fug | -2.775 |
Fract | -2.772 |
ynes | -2.700 |
Spiral | -2.695 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
TIT | +0.982 |
YY | +0.896 |
tz | +0.892 |
ieth | +0.868 |
ucha | +0.856 |
Neg logit contributions | |
inver | -0.914 |
Fug | -0.887 |
Fract | -0.882 |
Spiral | -0.858 |
ynes | -0.848 |
Token | Recommend |
Token ID | 41248 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
TIT | +0.896 |
YY | +0.802 |
tz | +0.796 |
ieth | +0.793 |
ucha | +0.786 |
Neg logit contributions | |
inver | -0.915 |
Fug | -0.914 |
Fract | -0.907 |
ynes | -0.877 |
Spiral | -0.873 |
Token | Share |
Token ID | 8734 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
TIT | +2.158 |
YY | +1.938 |
tz | +1.937 |
ieth | +1.900 |
ucha | +1.862 |
Neg logit contributions | |
inver | -2.442 |
Fug | -2.369 |
Fract | -2.357 |
Spiral | -2.298 |
ynes | -2.274 |
Token | this |
Token ID | 428 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
TIT | +2.823 |
tz | +2.663 |
YY | +2.631 |
ieth | +2.613 |
ucha | +2.579 |
Neg logit contributions | |
inver | -2.120 |
Fug | -2.069 |
Fract | -2.060 |
ynes | -2.011 |
Spiral | -1.975 |
Token | comment |
Token ID | 2912 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
inver | +0.541 |
Fug | +0.525 |
Fract | +0.524 |
Spiral | +0.507 |
ynes | +0.500 |
Neg logit contributions | |
TIT | -0.625 |
YY | -0.570 |
tz | -0.565 |
ieth | -0.557 |
ucha | -0.548 |
Token | on |
Token ID | 319 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
inver | +0.433 |
Fug | +0.419 |
Fract | +0.416 |
Spiral | +0.401 |
ynes | +0.394 |
Neg logit contributions | |
TIT | -0.735 |
YY | -0.681 |
tz | -0.678 |
ieth | -0.666 |
ucha | -0.658 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
inver | +0.341 |
Fug | +0.334 |
Fract | +0.333 |
Spiral | +0.325 |
ynes | +0.319 |
Neg logit contributions | |
TIT | -0.287 |
YY | -0.258 |
tz | -0.255 |
ieth | -0.251 |
ucha | -0.246 |
Token |
|
Token ID | 198 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
inver | +0.736 |
Fug | +0.718 |
Fract | +0.716 |
Spiral | +0.689 |
ynes | +0.678 |
Neg logit contributions | |
TIT | -0.912 |
YY | -0.838 |
tz | -0.832 |
ieth | -0.822 |
ucha | -0.803 |
Token |
|
Token ID | 198 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
TIT | +0.371 |
YY | +0.338 |
tz | +0.337 |
ieth | +0.330 |
ucha | +0.325 |
Neg logit contributions | |
inver | -0.328 |
Fug | -0.319 |
Fract | -0.317 |
Spiral | -0.308 |
ynes | -0.304 |
Token | NY |
Token ID | 12805 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
TIT | +0.285 |
YY | +0.245 |
tz | +0.244 |
ieth | +0.240 |
ucha | +0.233 |
Neg logit contributions | |
inver | -0.542 |
Fug | -0.532 |
Fract | -0.530 |
Spiral | -0.519 |
ynes | -0.517 |
Token | T |
Token ID | 51 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
TIT | +2.182 |
YY | +1.914 |
tz | +1.894 |
ieth | +1.776 |
Tag | +1.767 |
Neg logit contributions | |
inver | -3.463 |
Fug | -3.380 |
Fract | -3.350 |
Spiral | -3.273 |
ynes | -3.263 |
Token | Pick |
Token ID | 12346 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
TIT | +0.620 |
YY | +0.566 |
tz | +0.563 |
ieth | +0.551 |
ucha | +0.543 |
Neg logit contributions | |
inver | -0.547 |
Fug | -0.532 |
Fract | -0.530 |
Spiral | -0.514 |
ynes | -0.507 |
Token | Peter |
Token ID | 5613 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
TIT | +0.248 |
YY | +0.227 |
tz | +0.226 |
ieth | +0.221 |
ucha | +0.218 |
Neg logit contributions | |
inver | -0.207 |
Fug | -0.201 |
Fract | -0.200 |
Spiral | -0.194 |
ynes | -0.191 |
Token | Syracuse |
Token ID | 29141 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
inver | +0.120 |
Fug | +0.117 |
Fract | +0.116 |
Spiral | +0.113 |
ynes | +0.111 |
Neg logit contributions | |
TIT | -0.141 |
YY | -0.129 |
tz | -0.128 |
ieth | -0.126 |
ucha | -0.124 |
Token | 1 |
Token ID | 352 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
TIT | +0.721 |
YY | +0.662 |
tz | +0.658 |
ieth | +0.645 |
ucha | +0.636 |
Neg logit contributions | |
inver | -0.577 |
Fug | -0.561 |
Fract | -0.559 |
Spiral | -0.541 |
ynes | -0.534 |
Token | more |
Token ID | 517 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
TIT | +0.000 |
YY | +0.000 |
tz | +0.000 |
ieth | +0.000 |
ucha | +0.000 |
Neg logit contributions | |
inver | -0.000 |
Fug | -0.000 |
Fract | -0.000 |
Spiral | -0.000 |
ynes | -0.000 |
Token | or |
Token ID | 393 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
inver | +0.183 |
Fug | +0.178 |
Fract | +0.177 |
Spiral | +0.172 |
ynes | +0.169 |
Neg logit contributions | |
TIT | -0.219 |
YY | -0.201 |
tz | -0.200 |
ieth | -0.196 |
ucha | -0.193 |
Token | less |
Token ID | 1342 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
inver | +0.166 |
Fug | +0.161 |
Fract | +0.161 |
Spiral | +0.155 |
ynes | +0.153 |
Neg logit contributions | |
TIT | -0.231 |
YY | -0.213 |
tz | -0.212 |
ieth | -0.208 |
ucha | -0.205 |
Token | tweets |
Token ID | 12665 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
TIT | +0.384 |
YY | +0.354 |
tz | +0.352 |
ieth | +0.345 |
ucha | +0.340 |
Neg logit contributions | |
inver | -0.298 |
Fug | -0.290 |
Fract | -0.288 |
Spiral | -0.279 |
ynes | -0.277 |
Token | per |
Token ID | 583 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
inver | +0.226 |
Fug | +0.220 |
Fract | +0.219 |
Spiral | +0.212 |
ynes | +0.208 |
Neg logit contributions | |
TIT | -0.316 |
YY | -0.291 |
tz | -0.290 |
ieth | -0.285 |
ucha | -0.281 |
Token | capita |
Token ID | 21344 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
inver | +1.167 |
Fug | +1.131 |
Fract | +1.129 |
Spiral | +1.091 |
ynes | +1.076 |
Neg logit contributions | |
TIT | -1.309 |
YY | -1.192 |
tz | -1.183 |
ieth | -1.164 |
ucha | -1.145 |
Token | would |
Token ID | 561 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
inver | +1.352 |
Fug | +1.307 |
Fract | +1.305 |
Spiral | +1.254 |
ynes | +1.230 |
Neg logit contributions | |
TIT | -1.961 |
YY | -1.800 |
tz | -1.790 |
ieth | -1.758 |
ucha | -1.734 |
Token | be |
Token ID | 307 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
inver | +0.180 |
Fug | +0.176 |
Fract | +0.174 |
Spiral | +0.169 |
ynes | +0.166 |
Neg logit contributions | |
TIT | -0.275 |
YY | -0.256 |
tz | -0.255 |
ieth | -0.250 |
ucha | -0.247 |
Token | interesting |
Token ID | 3499 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
inver | +0.058 |
Fug | +0.057 |
Fract | +0.057 |
Spiral | +0.055 |
ynes | +0.054 |
Neg logit contributions | |
TIT | -0.080 |
YY | -0.074 |
tz | -0.074 |
ieth | -0.072 |
ucha | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
inver | +0.359 |
Fug | +0.348 |
Fract | +0.347 |
Spiral | +0.335 |
ynes | +0.329 |
Neg logit contributions | |
TIT | -0.486 |
YY | -0.447 |
tz | -0.444 |
ieth | -0.437 |
ucha | -0.431 |
Token | for |
Token ID | 329 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
inver | +0.252 |
Fug | +0.246 |
Fract | +0.244 |
Spiral | +0.237 |
ynes | +0.233 |
Neg logit contributions | |
TIT | -0.309 |
YY | -0.283 |
tz | -0.282 |
ieth | -0.276 |
ucha | -0.272 |
Token | President |
Token ID | 1992 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
inver | +0.495 |
Fug | +0.480 |
Fract | +0.477 |
Spiral | +0.463 |
ynes | +0.461 |
Neg logit contributions | |
TIT | -0.573 |
YY | -0.528 |
tz | -0.523 |
ieth | -0.509 |
ucha | -0.504 |
Token | Trump |
Token ID | 1301 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
TIT | +0.701 |
YY | +0.644 |
tz | +0.642 |
ieth | +0.630 |
ucha | +0.621 |
Neg logit contributions | |
inver | -0.529 |
Fug | -0.513 |
Fract | -0.510 |
Spiral | -0.494 |
ynes | -0.488 |
Token | warned |
Token ID | 7728 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
inver | +0.560 |
Fug | +0.543 |
Fract | +0.541 |
Spiral | +0.522 |
ynes | +0.514 |
Neg logit contributions | |
TIT | -0.815 |
YY | -0.752 |
tz | -0.748 |
ieth | -0.735 |
ucha | -0.725 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
TIT | +0.412 |
YY | +0.380 |
tz | +0.378 |
ieth | +0.371 |
ucha | +0.365 |
Neg logit contributions | |
inver | -0.295 |
Fug | -0.286 |
Fract | -0.285 |
Spiral | -0.276 |
ynes | -0.272 |
Token | special |
Token ID | 2041 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
inver | +0.114 |
Fug | +0.110 |
Fract | +0.110 |
Spiral | +0.106 |
ynes | +0.105 |
Neg logit contributions | |
TIT | -0.161 |
YY | -0.148 |
tz | -0.148 |
ieth | -0.145 |
ucha | -0.143 |
Token | counsel |
Token ID | 7739 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
inver | +1.190 |
Fug | +1.138 |
Fract | +1.127 |
Spiral | +1.070 |
ynes | +1.044 |
Neg logit contributions | |
TIT | -2.934 |
YY | -2.743 |
tz | -2.732 |
ieth | -2.691 |
ucha | -2.664 |
Token | investigating |
Token ID | 10240 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
inver | +1.379 |
Fug | +1.337 |
Fract | +1.332 |
Spiral | +1.287 |
ynes | +1.267 |
Neg logit contributions | |
TIT | -1.935 |
YY | -1.782 |
tz | -1.774 |
ieth | -1.743 |
ucha | -1.717 |
Token | Russia |
Token ID | 3284 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
inver | +1.156 |
Fug | +1.123 |
Fract | +1.119 |
Spiral | +1.081 |
ynes | +1.069 |
Neg logit contributions | |
TIT | -1.540 |
YY | -1.413 |
tz | -1.407 |
ieth | -1.384 |
ucha | -1.366 |
Token | not |
Token ID | 407 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
inver | +0.649 |
Fug | +0.626 |
Fract | +0.626 |
Spiral | +0.603 |
ynes | +0.600 |
Neg logit contributions | |
TIT | -1.027 |
YY | -0.954 |
tz | -0.948 |
ieth | -0.932 |
ucha | -0.919 |
Token | to |
Token ID | 284 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
inver | +0.029 |
Fug | +0.028 |
Fract | +0.028 |
Spiral | +0.027 |
ynes | +0.027 |
Neg logit contributions | |
TIT | -0.030 |
tz | -0.027 |
YY | -0.027 |
ieth | -0.026 |
ucha | -0.026 |
Token | ... |
Token ID | 986 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
TIT | +0.488 |
tz | +0.453 |
YY | +0.450 |
ieth | +0.441 |
ucha | +0.436 |
Neg logit contributions | |
inver | -0.317 |
Fug | -0.307 |
Fract | -0.306 |
Spiral | -0.293 |
ynes | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
inver | +0.114 |
Fug | +0.112 |
Fract | +0.111 |
Spiral | +0.108 |
ynes | +0.106 |
Neg logit contributions | |
TIT | -0.126 |
YY | -0.116 |
tz | -0.115 |
ieth | -0.113 |
ucha | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
TIT | +0.125 |
YY | +0.114 |
tz | +0.113 |
ieth | +0.111 |
ucha | +0.109 |
Neg logit contributions | |
inver | -0.114 |
Fug | -0.110 |
Fract | -0.110 |
Spiral | -0.107 |
ynes | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
inver | +0.114 |
Fug | +0.111 |
Fract | +0.111 |
Spiral | +0.108 |
ynes | +0.106 |
Neg logit contributions | |
TIT | -0.131 |
YY | -0.120 |
tz | -0.119 |
ieth | -0.117 |
ucha | -0.115 |
Token | The |
Token ID | 464 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
TIT | +0.060 |
YY | +0.054 |
tz | +0.054 |
ieth | +0.052 |
ucha | +0.051 |
Neg logit contributions | |
inver | -0.066 |
Fug | -0.064 |
Fract | -0.064 |
Spiral | -0.062 |
ynes | -0.061 |
Token | shower |
Token ID | 14643 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
TIT | +0.144 |
YY | +0.132 |
tz | +0.131 |
ieth | +0.129 |
ucha | +0.127 |
Neg logit contributions | |
inver | -0.113 |
Fug | -0.109 |
Fract | -0.109 |
Spiral | -0.105 |
ynes | -0.104 |
Token | scene |
Token ID | 3715 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
inver | +0.303 |
Fug | +0.294 |
Fract | +0.293 |
Spiral | +0.283 |
ynes | +0.279 |
Neg logit contributions | |
TIT | -0.420 |
YY | -0.387 |
tz | -0.385 |
ieth | -0.378 |
ucha | -0.373 |
Token | is |
Token ID | 318 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
inver | +1.283 |
Fug | +1.245 |
Fract | +1.239 |
Spiral | +1.194 |
ynes | +1.175 |
Neg logit contributions | |
TIT | -1.874 |
YY | -1.725 |
tz | -1.718 |
ieth | -1.687 |
ucha | -1.666 |
Token | what |
Token ID | 644 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
inver | +0.139 |
Fug | +0.135 |
Fract | +0.134 |
Spiral | +0.130 |
ynes | +0.128 |
Neg logit contributions | |
TIT | -0.205 |
YY | -0.189 |
tz | -0.188 |
ieth | -0.184 |
ucha | -0.181 |
Token | everyone |
Token ID | 2506 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
TIT | +0.066 |
YY | +0.061 |
tz | +0.061 |
ieth | +0.060 |
ucha | +0.059 |
Neg logit contributions | |
inver | -0.045 |
Fug | -0.044 |
Fract | -0.043 |
Spiral | -0.042 |
ynes | -0.042 |
Token | immediately |
Token ID | 3393 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
inver | +0.261 |
Fug | +0.254 |
Fract | +0.254 |
Spiral | +0.245 |
ynes | +0.241 |
Neg logit contributions | |
TIT | -0.325 |
YY | -0.299 |
tz | -0.298 |
ieth | -0.292 |
ucha | -0.288 |
Token | thinks |
Token ID | 6834 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
inver | +0.480 |
Fug | +0.467 |
Fract | +0.467 |
Spiral | +0.451 |
ynes | +0.443 |
Neg logit contributions | |
TIT | -0.574 |
YY | -0.525 |
tz | -0.524 |
ieth | -0.515 |
ucha | -0.506 |
Token | um |
Token ID | 388 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
inver | +1.615 |
Fug | +1.567 |
Fract | +1.561 |
Spiral | +1.505 |
ynes | +1.487 |
Neg logit contributions | |
TIT | -2.013 |
YY | -1.840 |
tz | -1.831 |
ieth | -1.799 |
ucha | -1.769 |
Token | everything |
Token ID | 2279 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
inver | +0.476 |
Fug | +0.464 |
Fract | +0.461 |
Spiral | +0.447 |
ynes | +0.440 |
Neg logit contributions | |
TIT | -0.600 |
YY | -0.552 |
tz | -0.550 |
ieth | -0.539 |
ucha | -0.532 |
Token | and |
Token ID | 290 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
inver | +0.551 |
Fug | +0.536 |
Fract | +0.533 |
Spiral | +0.516 |
ynes | +0.509 |
Neg logit contributions | |
TIT | -0.669 |
YY | -0.612 |
tz | -0.609 |
ieth | -0.598 |
ucha | -0.589 |
Token | compare |
Token ID | 8996 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
inver | +0.154 |
Fug | +0.150 |
Fract | +0.149 |
Spiral | +0.144 |
ynes | +0.142 |
Neg logit contributions | |
TIT | -0.195 |
YY | -0.179 |
tz | -0.178 |
ieth | -0.175 |
ucha | -0.172 |
Token | the |
Token ID | 262 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
inver | +1.318 |
Fug | +1.274 |
Fract | +1.271 |
Spiral | +1.218 |
ynes | +1.202 |
Neg logit contributions | |
TIT | -1.748 |
YY | -1.596 |
tz | -1.592 |
ieth | -1.570 |
ucha | -1.545 |
Token | checks |
Token ID | 8794 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
inver | +0.219 |
Fug | +0.213 |
Fract | +0.212 |
Spiral | +0.206 |
ynes | +0.203 |
Neg logit contributions | |
TIT | -0.267 |
YY | -0.245 |
tz | -0.243 |
ieth | -0.239 |
ucha | -0.235 |
Token | ums |
Token ID | 5700 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
inver | +1.851 |
Fug | +1.807 |
Fract | +1.803 |
Spiral | +1.750 |
ynes | +1.749 |
Neg logit contributions | |
TIT | -1.440 |
YY | -1.273 |
tz | -1.267 |
ieth | -1.232 |
ucha | -1.205 |
Token | . |
Token ID | 13 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
inver | +0.197 |
Fug | +0.192 |
Fract | +0.191 |
Spiral | +0.185 |
ynes | +0.182 |
Neg logit contributions | |
TIT | -0.235 |
YY | -0.216 |
tz | -0.214 |
ieth | -0.210 |
ucha | -0.207 |
Token | Get |
Token ID | 3497 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
TIT | +0.237 |
YY | +0.216 |
tz | +0.215 |
ieth | +0.210 |
ucha | +0.207 |
Neg logit contributions | |
inver | -0.213 |
Fug | -0.207 |
Fract | -0.206 |
Spiral | -0.200 |
ynes | -0.198 |
Token | it |
Token ID | 340 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
inver | +0.053 |
Fug | +0.051 |
Fract | +0.051 |
Spiral | +0.049 |
ynes | +0.049 |
Neg logit contributions | |
TIT | -0.072 |
YY | -0.066 |
tz | -0.066 |
ieth | -0.065 |
ucha | -0.064 |
Token | back |
Token ID | 736 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
inver | +0.111 |
Fug | +0.107 |
Fract | +0.107 |
Spiral | +0.103 |
ynes | +0.101 |
Neg logit contributions | |
TIT | -0.172 |
YY | -0.159 |
tz | -0.158 |
ieth | -0.155 |
ucha | -0.153 |
Token | transmission |
Token ID | 11478 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
inver | +0.317 |
Fug | +0.309 |
Fract | +0.307 |
Spiral | +0.296 |
ynes | +0.293 |
Neg logit contributions | |
TIT | -0.459 |
YY | -0.423 |
tz | -0.422 |
ieth | -0.414 |
ucha | -0.408 |
Token | of |
Token ID | 286 |
Feature activation | -9.40e-04 |
Pos logit contributions | |
TIT | +0.954 |
YY | +0.879 |
tz | +0.875 |
ieth | +0.859 |
ucha | +0.847 |
Neg logit contributions | |
inver | -0.688 |
Fug | -0.669 |
Fract | -0.664 |
Spiral | -0.641 |
ynes | -0.632 |
Token | criminal |
Token ID | 4301 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
TIT | +0.001 |
YY | +0.001 |
tz | +0.001 |
ieth | +0.001 |
ucha | +0.001 |
Neg logit contributions | |
inver | -0.001 |
Fug | -0.001 |
Fract | -0.001 |
Spiral | -0.001 |
ynes | -0.001 |
Token | convictions |
Token ID | 19131 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
inver | +0.235 |
Fug | +0.227 |
Fract | +0.226 |
Spiral | +0.218 |
ynes | +0.215 |
Neg logit contributions | |
TIT | -0.393 |
YY | -0.365 |
tz | -0.362 |
ieth | -0.358 |
ucha | -0.352 |
Token | . |
Token ID | 764 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
inver | +0.287 |
Fug | +0.280 |
Fract | +0.278 |
Spiral | +0.270 |
ynes | +0.266 |
Neg logit contributions | |
TIT | -0.333 |
YY | -0.305 |
tz | -0.302 |
ieth | -0.297 |
ucha | -0.292 |
Token | Crim |
Token ID | 9822 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
inver | +1.173 |
Fug | +1.145 |
Fract | +1.138 |
Spiral | +1.096 |
ynes | +1.070 |
Neg logit contributions | |
TIT | -1.862 |
YY | -1.721 |
tz | -1.716 |
ieth | -1.683 |
ucha | -1.667 |
Token | in |
Token ID | 259 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
inver | +1.427 |
Fug | +1.384 |
Fract | +1.378 |
Spiral | +1.332 |
ynes | +1.312 |
Neg logit contributions | |
TIT | -2.148 |
YY | -1.977 |
tz | -1.968 |
ieth | -1.926 |
ucha | -1.903 |
Token | ology |
Token ID | 1435 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
inver | +0.110 |
Fug | +0.107 |
Fract | +0.106 |
Spiral | +0.103 |
ynes | +0.101 |
Neg logit contributions | |
TIT | -0.110 |
YY | -0.100 |
tz | -0.099 |
ieth | -0.098 |
ucha | -0.097 |
Token | , |
Token ID | 11 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
TIT | +0.316 |
YY | +0.290 |
tz | +0.289 |
ieth | +0.284 |
ucha | +0.280 |
Neg logit contributions | |
inver | -0.229 |
Fug | -0.223 |
Fract | -0.222 |
Spiral | -0.214 |
ynes | -0.211 |
Token | 35 |
Token ID | 3439 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
inver | +0.428 |
Fug | +0.414 |
Fract | +0.413 |
Spiral | +0.403 |
ynes | +0.403 |
Neg logit contributions | |
TIT | -0.334 |
YY | -0.300 |
tz | -0.297 |
ieth | -0.289 |
ucha | -0.283 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
inver | +0.317 |
Fug | +0.309 |
Fract | +0.307 |
Spiral | +0.296 |
ynes | +0.291 |
Neg logit contributions | |
TIT | -0.484 |
YY | -0.447 |
tz | -0.445 |
ieth | -0.439 |
ucha | -0.434 |
Token | would |
Token ID | 561 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
TIT | +0.518 |
tz | +0.480 |
YY | +0.478 |
ieth | +0.468 |
ucha | +0.462 |
Neg logit contributions | |
inver | -0.386 |
Fug | -0.376 |
Fract | -0.375 |
Spiral | -0.363 |
ynes | -0.358 |
Token | order |
Token ID | 1502 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
TIT | +0.158 |
tz | +0.147 |
YY | +0.146 |
ieth | +0.144 |
ucha | +0.142 |
Neg logit contributions | |
inver | -0.101 |
Fug | -0.099 |
Fract | -0.098 |
Spiral | -0.095 |
ynes | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
inver | +0.646 |
Fug | +0.628 |
Fract | +0.623 |
Spiral | +0.602 |
ynes | +0.593 |
Neg logit contributions | |
TIT | -0.917 |
YY | -0.843 |
tz | -0.841 |
ieth | -0.825 |
ucha | -0.815 |
Token | full |
Token ID | 1336 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
TIT | +0.001 |
YY | +0.001 |
tz | +0.001 |
ieth | +0.001 |
ucha | +0.001 |
Neg logit contributions | |
inver | -0.001 |
Fug | -0.001 |
Fract | -0.001 |
Spiral | -0.001 |
ynes | -0.001 |
Token | - |
Token ID | 12 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
inver | +0.043 |
Fract | +0.042 |
Fug | +0.042 |
Spiral | +0.041 |
ynes | +0.040 |
Neg logit contributions | |
TIT | -0.062 |
YY | -0.058 |
tz | -0.057 |
ieth | -0.056 |
ucha | -0.055 |
Token | on |
Token ID | 261 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
inver | +0.256 |
Fug | +0.250 |
Fract | +0.249 |
Spiral | +0.242 |
ynes | +0.239 |
Neg logit contributions | |
TIT | -0.250 |
YY | -0.227 |
tz | -0.226 |
ieth | -0.221 |
ucha | -0.216 |
Token | war |
Token ID | 1175 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
inver | +0.093 |
Fug | +0.090 |
Fract | +0.090 |
Spiral | +0.087 |
ynes | +0.085 |
Neg logit contributions | |
TIT | -0.141 |
YY | -0.130 |
tz | -0.130 |
ieth | -0.127 |
ucha | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
inver | +0.505 |
Fug | +0.493 |
Fract | +0.490 |
Spiral | +0.473 |
ynes | +0.467 |
Neg logit contributions | |
TIT | -0.649 |
YY | -0.598 |
tz | -0.597 |
ieth | -0.584 |
ucha | -0.575 |
Token | But |
Token ID | 887 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
inver | +0.204 |
Fug | +0.197 |
Fract | +0.196 |
Spiral | +0.190 |
ynes | +0.188 |
Neg logit contributions | |
TIT | -0.280 |
YY | -0.258 |
tz | -0.256 |
ieth | -0.252 |
ucha | -0.248 |
Token | he |
Token ID | 339 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
inver | +0.155 |
Fract | +0.150 |
Fug | +0.149 |
Spiral | +0.144 |
ynes | +0.142 |
Neg logit contributions | |
TIT | -0.237 |
YY | -0.220 |
tz | -0.219 |
ieth | -0.215 |
ucha | -0.211 |
Token | said |
Token ID | 531 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
inver | +0.329 |
Fug | +0.319 |
Fract | +0.317 |
Spiral | +0.306 |
ynes | +0.302 |
Neg logit contributions | |
TIT | -0.442 |
YY | -0.405 |
tz | -0.402 |
ieth | -0.395 |
ucha | -0.390 |
Token | never |
Token ID | 1239 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
inver | +0.645 |
Fug | +0.631 |
Fract | +0.626 |
Spiral | +0.604 |
ynes | +0.593 |
Neg logit contributions | |
TIT | -1.013 |
YY | -0.934 |
tz | -0.933 |
ieth | -0.919 |
ucha | -0.906 |
Token | commend |
Token ID | 35695 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
inver | +0.324 |
Fug | +0.318 |
Fract | +0.317 |
Spiral | +0.305 |
ynes | +0.300 |
Neg logit contributions | |
TIT | -0.503 |
tz | -0.465 |
YY | -0.464 |
ieth | -0.458 |
ucha | -0.449 |
Token | you |
Token ID | 345 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
TIT | +0.244 |
YY | +0.224 |
tz | +0.223 |
ieth | +0.221 |
ucha | +0.217 |
Neg logit contributions | |
inver | -0.171 |
Fug | -0.165 |
Fract | -0.165 |
Spiral | -0.159 |
ynes | -0.156 |
Token | to |
Token ID | 284 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
inver | +0.396 |
Fug | +0.386 |
Fract | +0.384 |
Spiral | +0.372 |
ynes | +0.367 |
Neg logit contributions | |
TIT | -0.469 |
YY | -0.429 |
tz | -0.427 |
ieth | -0.419 |
ucha | -0.412 |
Token | those |
Token ID | 883 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
inver | +0.285 |
Fug | +0.276 |
Fract | +0.275 |
Spiral | +0.266 |
ynes | +0.262 |
Neg logit contributions | |
TIT | -0.392 |
YY | -0.361 |
tz | -0.359 |
ieth | -0.353 |
ucha | -0.347 |
Token | whom |
Token ID | 4150 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
TIT | +0.091 |
YY | +0.084 |
tz | +0.083 |
ieth | +0.082 |
ucha | +0.081 |
Neg logit contributions | |
inver | -0.071 |
Fug | -0.069 |
Fract | -0.068 |
Spiral | -0.066 |
ynes | -0.065 |
Token | you |
Token ID | 345 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
inver | +0.020 |
Fug | +0.020 |
Fract | +0.020 |
Spiral | +0.019 |
ynes | +0.019 |
Neg logit contributions | |
TIT | -0.026 |
YY | -0.024 |
tz | -0.024 |
ieth | -0.024 |
ucha | -0.023 |
Token | address |
Token ID | 2209 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
inver | +0.217 |
Fug | +0.211 |
Fract | +0.210 |
Spiral | +0.203 |
ynes | +0.200 |
Neg logit contributions | |
TIT | -0.318 |
YY | -0.293 |
tz | -0.292 |
ieth | -0.287 |
ucha | -0.283 |
Token | , |
Token ID | 11 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
inver | +0.390 |
Fug | +0.380 |
Fract | +0.378 |
Spiral | +0.366 |
ynes | +0.361 |
Neg logit contributions | |
TIT | -0.488 |
YY | -0.447 |
tz | -0.445 |
ieth | -0.436 |
ucha | -0.430 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
inver | +0.133 |
Fug | +0.130 |
Fract | +0.129 |
Spiral | +0.125 |
ynes | +0.124 |
Neg logit contributions | |
TIT | -0.146 |
YY | -0.133 |
tz | -0.132 |
ieth | -0.130 |
ucha | -0.127 |
Token | may |
Token ID | 743 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
inver | +0.081 |
Fug | +0.079 |
Fract | +0.079 |
Spiral | +0.076 |
ynes | +0.075 |
Neg logit contributions | |
TIT | -0.112 |
YY | -0.103 |
tz | -0.102 |
ieth | -0.101 |
ucha | -0.099 |
Token | � |
Token ID | 247 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
inver | +0.337 |
Fug | +0.331 |
Fract | +0.330 |
Spiral | +0.322 |
ynes | +0.318 |
Neg logit contributions | |
TIT | -0.209 |
YY | -0.184 |
tz | -0.183 |
ieth | -0.177 |
ucha | -0.174 |
Token | t |
Token ID | 83 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
inver | +0.555 |
Fug | +0.544 |
Fract | +0.543 |
Spiral | +0.531 |
ynes | +0.526 |
Neg logit contributions | |
TIT | -0.327 |
YY | -0.285 |
tz | -0.279 |
ieth | -0.274 |
ucha | -0.266 |
Token | always |
Token ID | 1464 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
TIT | +0.526 |
YY | +0.485 |
tz | +0.484 |
ieth | +0.474 |
ucha | +0.467 |
Neg logit contributions | |
inver | -0.373 |
Fug | -0.361 |
Fract | -0.361 |
Spiral | -0.347 |
ynes | -0.345 |
Token | so |
Token ID | 523 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
inver | +0.140 |
Fug | +0.136 |
Fract | +0.136 |
Spiral | +0.131 |
ynes | +0.130 |
Neg logit contributions | |
TIT | -0.197 |
YY | -0.182 |
tz | -0.181 |
ieth | -0.177 |
ucha | -0.175 |
Token | good |
Token ID | 922 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
inver | +0.105 |
Fug | +0.102 |
Fract | +0.102 |
Spiral | +0.098 |
ynes | +0.096 |
Neg logit contributions | |
TIT | -0.144 |
YY | -0.133 |
tz | -0.132 |
ieth | -0.130 |
ucha | -0.128 |
Token | at |
Token ID | 379 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
TIT | +0.313 |
YY | +0.287 |
tz | +0.286 |
ieth | +0.281 |
ucha | +0.276 |
Neg logit contributions | |
inver | -0.248 |
Fug | -0.241 |
Fract | -0.241 |
Spiral | -0.232 |
ynes | -0.229 |
Token | taking |
Token ID | 2263 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
inver | +0.370 |
Fug | +0.359 |
Fract | +0.358 |
Spiral | +0.345 |
ynes | +0.341 |
Neg logit contributions | |
TIT | -0.514 |
YY | -0.473 |
tz | -0.472 |
ieth | -0.462 |
ucha | -0.456 |
Token | care |
Token ID | 1337 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
inver | +0.100 |
Fug | +0.097 |
Fract | +0.097 |
Spiral | +0.094 |
ynes | +0.093 |
Neg logit contributions | |
TIT | -0.139 |
YY | -0.128 |
tz | -0.128 |
ieth | -0.125 |
ucha | -0.123 |
Token | of |
Token ID | 286 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
inver | +0.468 |
Fug | +0.453 |
Fract | +0.451 |
Spiral | +0.435 |
ynes | +0.428 |
Neg logit contributions | |
TIT | -0.696 |
YY | -0.641 |
tz | -0.634 |
ieth | -0.627 |
ucha | -0.616 |
Token | records |
Token ID | 4406 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
TIT | +0.216 |
YY | +0.200 |
tz | +0.199 |
ieth | +0.195 |
ucha | +0.193 |
Neg logit contributions | |
inver | -0.143 |
Fug | -0.138 |
Fract | -0.138 |
Spiral | -0.133 |
ynes | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
TIT | +0.502 |
YY | +0.462 |
tz | +0.458 |
ieth | +0.449 |
ucha | +0.442 |
Neg logit contributions | |
inver | -0.431 |
Fug | -0.419 |
Fract | -0.418 |
Spiral | -0.405 |
ynes | -0.400 |
Token | this |
Token ID | 428 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
inver | +0.432 |
Fug | +0.420 |
Fract | +0.418 |
Spiral | +0.404 |
ynes | +0.396 |
Neg logit contributions | |
TIT | -0.600 |
YY | -0.552 |
tz | -0.549 |
ieth | -0.540 |
ucha | -0.533 |
Token | comic |
Token ID | 9048 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
inver | +0.541 |
Fug | +0.526 |
Fract | +0.524 |
Spiral | +0.506 |
ynes | +0.494 |
Neg logit contributions | |
TIT | -0.759 |
YY | -0.699 |
tz | -0.695 |
ieth | -0.683 |
ucha | -0.674 |
Token | was |
Token ID | 373 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
TIT | +0.052 |
YY | +0.049 |
tz | +0.048 |
ieth | +0.048 |
ucha | +0.047 |
Neg logit contributions | |
inver | -0.033 |
Fug | -0.032 |
Fract | -0.032 |
Spiral | -0.031 |
ynes | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
inver | +0.169 |
Fug | +0.165 |
Fract | +0.164 |
Spiral | +0.159 |
ynes | +0.157 |
Neg logit contributions | |
TIT | -0.194 |
YY | -0.177 |
tz | -0.176 |
ieth | -0.173 |
ucha | -0.170 |
Token | catchy |
Token ID | 46124 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
inver | +0.203 |
Fug | +0.198 |
Fract | +0.197 |
Spiral | +0.191 |
ynes | +0.188 |
Neg logit contributions | |
TIT | -0.245 |
YY | -0.224 |
tz | -0.223 |
ieth | -0.219 |
ucha | -0.216 |
Token | parody |
Token ID | 29695 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
TIT | +0.126 |
YY | +0.115 |
tz | +0.114 |
ieth | +0.112 |
ucha | +0.110 |
Neg logit contributions | |
inver | -0.107 |
Fug | -0.104 |
Fract | -0.104 |
Spiral | -0.101 |
ynes | -0.099 |
Token | of |
Token ID | 286 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
inver | +0.037 |
Fug | +0.036 |
Fract | +0.036 |
Spiral | +0.035 |
ynes | +0.034 |
Neg logit contributions | |
TIT | -0.052 |
YY | -0.047 |
tz | -0.047 |
ieth | -0.046 |
ucha | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
inver | +0.492 |
Fug | +0.479 |
Fract | +0.476 |
Spiral | +0.460 |
ynes | +0.451 |
Neg logit contributions | |
TIT | -0.664 |
YY | -0.611 |
tz | -0.608 |
ieth | -0.597 |
ucha | -0.589 |
Token | Daredevil |
Token ID | 42390 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
inver | +0.468 |
Fug | +0.456 |
Fract | +0.454 |
Spiral | +0.439 |
ynes | +0.432 |
Neg logit contributions | |
TIT | -0.558 |
YY | -0.510 |
tz | -0.508 |
ieth | -0.498 |
ucha | -0.490 |
Token | comics |
Token ID | 12770 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
inver | +0.437 |
Fug | +0.425 |
Fract | +0.423 |
Spiral | +0.411 |
ynes | +0.407 |
Neg logit contributions | |
TIT | -0.481 |
YY | -0.438 |
tz | -0.436 |
ieth | -0.429 |
ucha | -0.421 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
inver | +0.769 |
Fug | +0.748 |
Fract | +0.745 |
Spiral | +0.721 |
ynes | +0.711 |
Neg logit contributions | |
TIT | -0.944 |
YY | -0.864 |
tz | -0.860 |
ieth | -0.844 |
ucha | -0.831 |
Token | ). |
Token ID | 737 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
TIT | +0.259 |
YY | +0.238 |
tz | +0.237 |
ieth | +0.232 |
ucha | +0.229 |
Neg logit contributions | |
inver | -0.204 |
Fug | -0.198 |
Fract | -0.197 |
Spiral | -0.191 |
ynes | -0.188 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
TIT | +0.257 |
YY | +0.236 |
tz | +0.234 |
ieth | +0.229 |
Judaism | +0.225 |
Neg logit contributions | |
inver | -0.209 |
Fug | -0.199 |
Fract | -0.199 |
ynes | -0.194 |
Spiral | -0.192 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
TIT | +0.026 |
YY | +0.024 |
tz | +0.024 |
ieth | +0.023 |
ucha | +0.023 |
Neg logit contributions | |
inver | -0.023 |
Fug | -0.022 |
Fract | -0.022 |
Spiral | -0.022 |
ynes | -0.021 |
Token | S |
Token ID | 50 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
TIT | +0.229 |
YY | +0.207 |
tz | +0.205 |
ieth | +0.200 |
ucha | +0.196 |
Neg logit contributions | |
inver | -0.250 |
Fug | -0.243 |
Fract | -0.243 |
Spiral | -0.236 |
ynes | -0.233 |
Token | omew |
Token ID | 28030 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
inver | +0.310 |
Fug | +0.301 |
Fract | +0.300 |
Spiral | +0.291 |
ynes | +0.286 |
Neg logit contributions | |
TIT | -0.369 |
YY | -0.337 |
tz | -0.336 |
ieth | -0.330 |
ucha | -0.325 |
Token | here |
Token ID | 1456 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
TIT | +0.140 |
YY | +0.126 |
tz | +0.125 |
ieth | +0.124 |
ucha | +0.120 |
Neg logit contributions | |
inver | -0.158 |
Fug | -0.154 |
Fract | -0.154 |
Spiral | -0.150 |
ynes | -0.148 |
Token | in |
Token ID | 287 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
inver | +0.645 |
Fract | +0.625 |
Fug | +0.621 |
Spiral | +0.596 |
ynes | +0.593 |
Neg logit contributions | |
TIT | -1.094 |
YY | -1.017 |
tz | -1.008 |
ieth | -0.993 |
ucha | -0.975 |
Token | between |
Token ID | 1022 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
inver | +0.133 |
Fug | +0.129 |
Fract | +0.128 |
Spiral | +0.124 |
ynes | +0.122 |
Neg logit contributions | |
TIT | -0.195 |
YY | -0.180 |
tz | -0.179 |
ieth | -0.176 |
ucha | -0.173 |
Token | op |
Token ID | 1034 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
TIT | +0.212 |
YY | +0.196 |
tz | +0.195 |
ieth | +0.192 |
ucha | +0.188 |
Neg logit contributions | |
inver | -0.150 |
Fract | -0.145 |
Fug | -0.145 |
Spiral | -0.140 |
ynes | -0.139 |
Token | ining |
Token ID | 3191 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
TIT | +0.067 |
YY | +0.061 |
tz | +0.061 |
ieth | +0.060 |
ucha | +0.059 |
Neg logit contributions | |
inver | -0.057 |
Fug | -0.056 |
Fract | -0.056 |
Spiral | -0.054 |
ynes | -0.053 |
Token | about |
Token ID | 546 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
inver | +0.080 |
Fug | +0.077 |
Fract | +0.077 |
Spiral | +0.074 |
ynes | +0.073 |
Neg logit contributions | |
TIT | -0.125 |
YY | -0.115 |
tz | -0.115 |
ieth | -0.113 |
ucha | -0.111 |
Token | NDP |
Token ID | 20392 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
TIT | +0.053 |
YY | +0.049 |
tz | +0.048 |
ieth | +0.048 |
ucha | +0.047 |
Neg logit contributions | |
inver | -0.045 |
Fug | -0.044 |
Fract | -0.044 |
Spiral | -0.042 |
ynes | -0.042 |
Token | � |
Token ID | 447 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
inver | +0.616 |
Fug | +0.596 |
Fract | +0.593 |
Spiral | +0.571 |
ynes | +0.560 |
Neg logit contributions | |
TIT | -0.958 |
YY | -0.884 |
tz | -0.880 |
ieth | -0.866 |
ucha | -0.855 |
Token | � |
Token ID | 247 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
inver | +0.276 |
Fug | +0.270 |
Fract | +0.269 |
Spiral | +0.263 |
ynes | +0.260 |
Neg logit contributions | |
TIT | -0.181 |
YY | -0.160 |
tz | -0.159 |
ieth | -0.154 |
ucha | -0.151 |
Token | s |
Token ID | 82 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
TIT | +0.240 |
YY | +0.219 |
tz | +0.217 |
ieth | +0.213 |
ucha | +0.210 |
Neg logit contributions | |
inver | -0.209 |
Fug | -0.204 |
Fract | -0.203 |
Spiral | -0.197 |
ynes | -0.194 |
Token | deputy |
Token ID | 10636 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
TIT | +0.101 |
YY | +0.093 |
tz | +0.093 |
ieth | +0.091 |
ucha | +0.090 |
Neg logit contributions | |
inver | -0.079 |
Fug | -0.077 |
Fract | -0.077 |
Spiral | -0.074 |
ynes | -0.073 |
Token | critic |
Token ID | 4014 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
inver | +0.701 |
Fug | +0.685 |
Fract | +0.682 |
Spiral | +0.662 |
ynes | +0.653 |
Neg logit contributions | |
TIT | -0.793 |
YY | -0.725 |
tz | -0.720 |
ieth | -0.707 |
ucha | -0.695 |
Token | for |
Token ID | 329 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
TIT | +0.137 |
YY | +0.125 |
tz | +0.124 |
ieth | +0.121 |
ucha | +0.119 |
Neg logit contributions | |
inver | -0.127 |
Fug | -0.124 |
Fract | -0.123 |
Spiral | -0.120 |
ynes | -0.118 |
Token | democratic |
Token ID | 10518 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
TIT | +0.374 |
YY | +0.345 |
tz | +0.343 |
ieth | +0.338 |
ucha | +0.331 |
Neg logit contributions | |
inver | -0.285 |
Fug | -0.278 |
Fract | -0.277 |
Spiral | -0.268 |
ynes | -0.266 |
Token | reform |
Token ID | 4975 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
inver | +0.345 |
Fug | +0.332 |
Fract | +0.331 |
Spiral | +0.318 |
ynes | +0.312 |
Neg logit contributions | |
TIT | -0.579 |
YY | -0.536 |
tz | -0.534 |
ieth | -0.525 |
ucha | -0.518 |
Token | , |
Token ID | 11 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
TIT | +1.271 |
YY | +1.163 |
tz | +1.157 |
ieth | +1.131 |
ucha | +1.114 |
Neg logit contributions | |
inver | -1.166 |
Fug | -1.140 |
Fract | -1.133 |
Spiral | -1.102 |
ynes | -1.087 |
Token | who |
Token ID | 508 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
TIT | +0.240 |
YY | +0.220 |
tz | +0.219 |
ieth | +0.215 |
ucha | +0.211 |
Neg logit contributions | |
inver | -0.191 |
Fug | -0.186 |
Fract | -0.185 |
Spiral | -0.179 |
ynes | -0.177 |
Token | prefer |
Token ID | 4702 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
TIT | +0.012 |
YY | +0.011 |
tz | +0.011 |
ieth | +0.011 |
ucha | +0.010 |
Neg logit contributions | |
inver | -0.011 |
Fug | -0.011 |
Fract | -0.011 |
Spiral | -0.010 |
ynes | -0.010 |
Token | touch |
Token ID | 3638 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
inver | +0.581 |
Fug | +0.564 |
Fract | +0.562 |
Spiral | +0.542 |
ynes | +0.534 |
Neg logit contributions | |
TIT | -0.826 |
YY | -0.760 |
tz | -0.758 |
ieth | -0.743 |
ucha | -0.734 |
Token | or |
Token ID | 393 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
TIT | +0.273 |
YY | +0.250 |
tz | +0.249 |
ieth | +0.244 |
ucha | +0.240 |
Neg logit contributions | |
inver | -0.255 |
Fug | -0.249 |
Fract | -0.248 |
Spiral | -0.241 |
ynes | -0.238 |
Token | not |
Token ID | 407 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
TIT | +0.287 |
YY | +0.265 |
tz | +0.264 |
ieth | +0.258 |
ucha | +0.255 |
Neg logit contributions | |
inver | -0.211 |
Fug | -0.206 |
Fract | -0.206 |
Spiral | -0.199 |
ynes | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
inver | +0.314 |
Fug | +0.306 |
Fract | +0.304 |
Spiral | +0.295 |
ynes | +0.291 |
Neg logit contributions | |
TIT | -0.360 |
YY | -0.329 |
tz | -0.327 |
ieth | -0.321 |
ucha | -0.316 |
Token | If |
Token ID | 1002 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
TIT | +0.335 |
YY | +0.307 |
tz | +0.305 |
ieth | +0.296 |
ucha | +0.292 |
Neg logit contributions | |
inver | -0.295 |
Fug | -0.282 |
Fract | -0.279 |
ynes | -0.275 |
Spiral | -0.272 |
Token | you |
Token ID | 345 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
TIT | +0.827 |
YY | +0.762 |
tz | +0.758 |
ieth | +0.739 |
ucha | +0.731 |
Neg logit contributions | |
inver | -0.628 |
Fug | -0.611 |
Fract | -0.609 |
Spiral | -0.588 |
ynes | -0.584 |
Token | don |
Token ID | 836 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
TIT | +0.156 |
YY | +0.144 |
tz | +0.144 |
ieth | +0.140 |
ucha | +0.139 |
Neg logit contributions | |
inver | -0.122 |
Fug | -0.119 |
Fract | -0.118 |
Spiral | -0.114 |
ynes | -0.112 |
Token | � |
Token ID | 447 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
TIT | +0.570 |
YY | +0.520 |
tz | +0.518 |
ieth | +0.504 |
ucha | +0.496 |
Neg logit contributions | |
inver | -0.541 |
Fug | -0.523 |
Fract | -0.521 |
Spiral | -0.506 |
ynes | -0.499 |
Token | � |
Token ID | 247 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
TIT | +0.312 |
YY | +0.273 |
tz | +0.271 |
ieth | +0.261 |
ucha | +0.258 |
Neg logit contributions | |
inver | -0.522 |
Fug | -0.513 |
Fract | -0.511 |
Spiral | -0.500 |
ynes | -0.492 |
Token | t |
Token ID | 83 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
inver | +0.223 |
Fug | +0.219 |
Fract | +0.218 |
Spiral | +0.213 |
ynes | +0.212 |
Neg logit contributions | |
TIT | -0.133 |
YY | -0.116 |
tz | -0.115 |
ieth | -0.112 |
ucha | -0.109 |
Token | it |
Token ID | 340 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
inver | +0.491 |
Fug | +0.475 |
Fract | +0.474 |
Spiral | +0.458 |
ynes | +0.453 |
Neg logit contributions | |
TIT | -0.678 |
YY | -0.625 |
tz | -0.622 |
ieth | -0.610 |
ucha | -0.600 |
Token | both |
Token ID | 1111 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
inver | +0.069 |
Fug | +0.068 |
Fract | +0.068 |
Spiral | +0.066 |
ynes | +0.065 |
Neg logit contributions | |
TIT | -0.059 |
YY | -0.053 |
tz | -0.053 |
ieth | -0.052 |
ucha | -0.051 |
Token | drives |
Token ID | 10182 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
TIT | +0.353 |
YY | +0.323 |
tz | +0.321 |
ieth | +0.317 |
ucha | +0.312 |
Neg logit contributions | |
inver | -0.298 |
Fug | -0.291 |
Fract | -0.289 |
Spiral | -0.282 |
ynes | -0.278 |
Token | home |
Token ID | 1363 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
TIT | +0.019 |
YY | +0.018 |
tz | +0.018 |
ieth | +0.017 |
ucha | +0.017 |
Neg logit contributions | |
inver | -0.012 |
Fug | -0.012 |
Fract | -0.012 |
Spiral | -0.011 |
ynes | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -7.02e-03 |
Pos logit contributions | |
TIT | +0.060 |
YY | +0.055 |
tz | +0.055 |
ieth | +0.054 |
ucha | +0.053 |
Neg logit contributions | |
inver | -0.040 |
Fug | -0.039 |
Fract | -0.039 |
Spiral | -0.038 |
ynes | -0.037 |
Token | pain |
Token ID | 2356 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
TIT | +0.006 |
YY | +0.006 |
tz | +0.006 |
ieth | +0.006 |
ucha | +0.006 |
Neg logit contributions | |
inver | -0.004 |
Fug | -0.004 |
Fract | -0.004 |
Spiral | -0.004 |
ynes | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
TIT | +0.875 |
YY | +0.809 |
tz | +0.799 |
ieth | +0.788 |
ucha | +0.772 |
Neg logit contributions | |
inver | -0.739 |
Fug | -0.718 |
Fract | -0.713 |
Spiral | -0.687 |
ynes | -0.678 |
Token | heart |
Token ID | 2612 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
TIT | +0.210 |
YY | +0.194 |
tz | +0.193 |
ieth | +0.189 |
ucha | +0.187 |
Neg logit contributions | |
inver | -0.151 |
Fug | -0.146 |
Fract | -0.146 |
Spiral | -0.141 |
ynes | -0.140 |
Token | break |
Token ID | 9032 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
inver | +0.508 |
Fug | +0.492 |
Fract | +0.490 |
Spiral | +0.472 |
ynes | +0.463 |
Neg logit contributions | |
TIT | -0.796 |
YY | -0.735 |
tz | -0.732 |
ieth | -0.719 |
ucha | -0.710 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
TIT | +0.680 |
YY | +0.624 |
tz | +0.618 |
ieth | +0.606 |
ucha | +0.597 |
Neg logit contributions | |
inver | -0.625 |
Fug | -0.609 |
Fract | -0.606 |
Spiral | -0.587 |
ynes | -0.581 |
Token | reminds |
Token ID | 17603 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
TIT | +0.138 |
YY | +0.126 |
tz | +0.126 |
ieth | +0.124 |
ucha | +0.122 |
Neg logit contributions | |
inver | -0.099 |
Fug | -0.096 |
Fract | -0.096 |
Spiral | -0.092 |
ynes | -0.091 |
Token | jump |
Token ID | 4391 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
inver | +0.818 |
Fug | +0.795 |
Fract | +0.791 |
Spiral | +0.764 |
ynes | +0.752 |
Neg logit contributions | |
TIT | -1.138 |
YY | -1.049 |
tz | -1.044 |
ieth | -1.025 |
ucha | -1.010 |
Token | through |
Token ID | 832 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
inver | +1.614 |
Fug | +1.563 |
Fract | +1.557 |
Spiral | +1.505 |
ynes | +1.489 |
Neg logit contributions | |
TIT | -2.187 |
YY | -2.004 |
tz | -1.996 |
ieth | -1.962 |
ucha | -1.936 |
Token | hoops |
Token ID | 46730 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
TIT | +0.503 |
YY | +0.464 |
tz | +0.462 |
ieth | +0.453 |
ucha | +0.447 |
Neg logit contributions | |
inver | -0.348 |
Fug | -0.339 |
Fract | -0.337 |
Spiral | -0.325 |
ynes | -0.320 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
TIT | +0.007 |
YY | +0.007 |
tz | +0.007 |
ieth | +0.007 |
ucha | +0.007 |
Neg logit contributions | |
inver | -0.006 |
Fug | -0.006 |
Fract | -0.006 |
Spiral | -0.006 |
ynes | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
inver | +0.847 |
Fug | +0.827 |
Fract | +0.825 |
Spiral | +0.798 |
ynes | +0.784 |
Neg logit contributions | |
TIT | -1.038 |
YY | -0.949 |
tz | -0.943 |
ieth | -0.932 |
ucha | -0.915 |
Token | and |
Token ID | 392 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
inver | +0.716 |
Fug | +0.699 |
Fract | +0.697 |
Spiral | +0.677 |
ynes | +0.670 |
Neg logit contributions | |
TIT | -0.643 |
YY | -0.580 |
tz | -0.576 |
ieth | -0.563 |
ucha | -0.553 |
Token | produce |
Token ID | 4439 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
TIT | +0.262 |
tz | +0.244 |
YY | +0.242 |
ieth | +0.237 |
ucha | +0.234 |
Neg logit contributions | |
inver | -0.169 |
Fug | -0.166 |
Fract | -0.165 |
Spiral | -0.158 |
ynes | -0.157 |
Token | useful |
Token ID | 4465 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
inver | +1.369 |
Fug | +1.328 |
Fract | +1.322 |
Spiral | +1.275 |
ynes | +1.255 |
Neg logit contributions | |
TIT | -1.978 |
YY | -1.823 |
tz | -1.814 |
ieth | -1.783 |
ucha | -1.758 |
Token | tricks |
Token ID | 15910 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
inver | +0.246 |
Fug | +0.240 |
Fract | +0.240 |
Spiral | +0.231 |
ynes | +0.227 |
Neg logit contributions | |
TIT | -0.367 |
YY | -0.340 |
tz | -0.340 |
ieth | -0.331 |
ucha | -0.327 |
Token | without |
Token ID | 1231 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
inver | +0.013 |
Fug | +0.013 |
Fract | +0.013 |
Spiral | +0.012 |
ynes | +0.012 |
Neg logit contributions | |
TIT | -0.017 |
YY | -0.016 |
tz | -0.016 |
ieth | -0.015 |
ucha | -0.015 |
Token | resort |
Token ID | 12600 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
inver | +0.005 |
Fug | +0.005 |
Fract | +0.005 |
Spiral | +0.005 |
ynes | +0.005 |
Neg logit contributions | |
TIT | -0.009 |
YY | -0.008 |
tz | -0.008 |
ieth | -0.008 |
ucha | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
TIT | +0.373 |
YY | +0.343 |
tz | +0.341 |
ieth | +0.334 |
ucha | +0.330 |
Neg logit contributions | |
inver | -0.275 |
Fug | -0.268 |
Fract | -0.267 |
Spiral | -0.257 |
ynes | -0.255 |
Token | bro |
Token ID | 1379 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
TIT | +0.014 |
YY | +0.012 |
tz | +0.012 |
ieth | +0.012 |
ucha | +0.012 |
Neg logit contributions | |
inver | -0.011 |
Fug | -0.010 |
Fract | -0.010 |
Spiral | -0.010 |
ynes | -0.010 |
Token | thel |
Token ID | 37274 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
inver | +0.406 |
Fug | +0.396 |
Fract | +0.394 |
Spiral | +0.382 |
ynes | +0.376 |
Neg logit contributions | |
TIT | -0.469 |
YY | -0.430 |
tz | -0.428 |
ieth | -0.418 |
ucha | -0.413 |
Token | , |
Token ID | 11 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
TIT | +1.231 |
YY | +1.134 |
tz | +1.127 |
ieth | +1.106 |
ucha | +1.092 |
Neg logit contributions | |
inver | -0.943 |
Fug | -0.920 |
Fract | -0.916 |
Spiral | -0.883 |
ynes | -0.877 |
Token | one |
Token ID | 530 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
inver | +0.169 |
Fug | +0.164 |
Fract | +0.163 |
Spiral | +0.157 |
ynes | +0.154 |
Neg logit contributions | |
TIT | -0.249 |
YY | -0.229 |
tz | -0.228 |
ieth | -0.224 |
ucha | -0.221 |
Token | would |
Token ID | 561 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
TIT | +0.174 |
YY | +0.160 |
tz | +0.159 |
ieth | +0.157 |
ucha | +0.154 |
Neg logit contributions | |
inver | -0.127 |
Fug | -0.124 |
Fract | -0.123 |
Spiral | -0.119 |
ynes | -0.118 |
Token | explain |
Token ID | 4727 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
TIT | +0.092 |
tz | +0.084 |
YY | +0.084 |
ieth | +0.083 |
ucha | +0.081 |
Neg logit contributions | |
inver | -0.079 |
Fug | -0.078 |
Fract | -0.077 |
Spiral | -0.075 |
ynes | -0.073 |
Token | it |
Token ID | 340 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
TIT | +0.575 |
YY | +0.529 |
tz | +0.526 |
ieth | +0.515 |
ucha | +0.508 |
Neg logit contributions | |
inver | -0.449 |
Fug | -0.435 |
Fract | -0.433 |
Spiral | -0.420 |
ynes | -0.415 |
Token | as |
Token ID | 355 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
inver | +0.061 |
Fug | +0.060 |
Fract | +0.060 |
Spiral | +0.058 |
ynes | +0.057 |
Neg logit contributions | |
TIT | -0.081 |
YY | -0.075 |
tz | -0.074 |
ieth | -0.073 |
ucha | -0.072 |
Token | follows |
Token ID | 5679 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
TIT | +0.239 |
YY | +0.220 |
tz | +0.219 |
ieth | +0.215 |
ucha | +0.213 |
Neg logit contributions | |
inver | -0.166 |
Fug | -0.161 |
Fract | -0.160 |
Spiral | -0.155 |
ynes | -0.153 |
Token | : |
Token ID | 25 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
TIT | +0.915 |
YY | +0.835 |
tz | +0.830 |
ieth | +0.812 |
ucha | +0.799 |
Neg logit contributions | |
inver | -0.834 |
Fug | -0.812 |
Fract | -0.808 |
Spiral | -0.785 |
ynes | -0.775 |
Token | sits |
Token ID | 10718 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
inver | +0.441 |
Fug | +0.427 |
Fract | +0.423 |
Spiral | +0.408 |
ynes | +0.400 |
Neg logit contributions | |
TIT | -0.676 |
YY | -0.623 |
tz | -0.620 |
ieth | -0.609 |
ucha | -0.601 |
Token | in |
Token ID | 287 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
TIT | +1.441 |
tz | +1.339 |
YY | +1.336 |
ieth | +1.310 |
ucha | +1.306 |
Neg logit contributions | |
inver | -1.044 |
Fract | -1.026 |
Fug | -1.015 |
Spiral | -0.989 |
ynes | -0.980 |
Token | front |
Token ID | 2166 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
TIT | +0.374 |
YY | +0.346 |
tz | +0.345 |
ieth | +0.339 |
ucha | +0.335 |
Neg logit contributions | |
inver | -0.226 |
Fug | -0.218 |
Fract | -0.217 |
Spiral | -0.209 |
ynes | -0.206 |
Token | of |
Token ID | 286 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
TIT | +0.824 |
YY | +0.759 |
tz | +0.757 |
ieth | +0.742 |
ucha | +0.735 |
Neg logit contributions | |
inver | -0.646 |
Fug | -0.626 |
Fract | -0.626 |
Spiral | -0.608 |
ynes | -0.600 |
Token | a |
Token ID | 257 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
TIT | +0.808 |
YY | +0.748 |
tz | +0.744 |
ieth | +0.729 |
ucha | +0.725 |
Neg logit contributions | |
inver | -0.534 |
Fug | -0.515 |
Fract | -0.514 |
Spiral | -0.497 |
ynes | -0.493 |
Token | store |
Token ID | 3650 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
TIT | +0.505 |
YY | +0.465 |
tz | +0.462 |
ieth | +0.454 |
ucha | +0.448 |
Neg logit contributions | |
inver | -0.370 |
Fug | -0.358 |
Fract | -0.357 |
Spiral | -0.345 |
ynes | -0.342 |
Token | that |
Token ID | 326 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
TIT | +2.132 |
YY | +1.983 |
tz | +1.965 |
ieth | +1.935 |
ucha | +1.894 |
Neg logit contributions | |
inver | -1.571 |
Fract | -1.529 |
Fug | -1.527 |
Spiral | -1.484 |
ynes | -1.464 |
Token | has |
Token ID | 468 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
TIT | +0.262 |
YY | +0.242 |
tz | +0.240 |
ieth | +0.236 |
ucha | +0.233 |
Neg logit contributions | |
inver | -0.190 |
Fug | -0.184 |
Fract | -0.184 |
Spiral | -0.178 |
ynes | -0.175 |
Token | been |
Token ID | 587 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
TIT | +0.278 |
YY | +0.255 |
tz | +0.253 |
ieth | +0.247 |
ucha | +0.244 |
Neg logit contributions | |
inver | -0.244 |
Fug | -0.238 |
Fract | -0.238 |
Spiral | -0.230 |
ynes | -0.228 |
Token | boarded |
Token ID | 35032 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
TIT | +0.783 |
YY | +0.723 |
tz | +0.721 |
ieth | +0.704 |
ucha | +0.699 |
Neg logit contributions | |
inver | -0.499 |
Fug | -0.487 |
Fract | -0.487 |
Spiral | -0.471 |
ynes | -0.467 |
Token | up |
Token ID | 510 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
inver | +0.431 |
Fug | +0.413 |
Fract | +0.411 |
Spiral | +0.391 |
ynes | +0.382 |
Neg logit contributions | |
TIT | -1.082 |
YY | -1.015 |
tz | -1.010 |
ieth | -0.997 |
ucha | -0.985 |
Token | in |
Token ID | 287 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
inver | +0.175 |
Fug | +0.170 |
Fract | +0.169 |
Spiral | +0.164 |
ynes | +0.161 |
Neg logit contributions | |
TIT | -0.241 |
YY | -0.222 |
tz | -0.221 |
ieth | -0.217 |
ucha | -0.214 |
Token | which |
Token ID | 543 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
inver | +0.027 |
Fug | +0.027 |
Fract | +0.026 |
Spiral | +0.026 |
ynes | +0.025 |
Neg logit contributions | |
TIT | -0.040 |
YY | -0.037 |
tz | -0.037 |
ieth | -0.036 |
ucha | -0.036 |
Token | they |
Token ID | 484 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
TIT | +0.305 |
YY | +0.282 |
tz | +0.280 |
ieth | +0.276 |
ucha | +0.272 |
Neg logit contributions | |
inver | -0.201 |
Fug | -0.195 |
Fract | -0.194 |
Spiral | -0.187 |
ynes | -0.184 |
Token | are |
Token ID | 389 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
TIT | +0.283 |
tz | +0.263 |
YY | +0.263 |
ieth | +0.258 |
ucha | +0.255 |
Neg logit contributions | |
inver | -0.181 |
Fug | -0.177 |
Fract | -0.176 |
Spiral | -0.169 |
ynes | -0.166 |
Token | en |
Token ID | 551 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
TIT | +0.444 |
YY | +0.409 |
tz | +0.408 |
ieth | +0.399 |
ucha | +0.395 |
Neg logit contributions | |
inver | -0.313 |
Fug | -0.307 |
Fract | -0.306 |
Spiral | -0.296 |
ynes | -0.293 |
Token | mes |
Token ID | 6880 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
inver | +0.228 |
Fug | +0.222 |
Fract | +0.222 |
Spiral | +0.215 |
ynes | +0.212 |
Neg logit contributions | |
TIT | -0.248 |
YY | -0.226 |
tz | -0.225 |
ieth | -0.221 |
ucha | -0.217 |
Token | hed |
Token ID | 704 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
TIT | +1.838 |
tz | +1.689 |
ieth | +1.651 |
YY | +1.640 |
ucha | +1.590 |
Neg logit contributions | |
inver | -2.607 |
Fug | -2.534 |
Fract | -2.520 |
Spiral | -2.449 |
ynes | -2.444 |
Token | . |
Token ID | 13 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
inver | +0.273 |
Fug | +0.266 |
Fract | +0.264 |
Spiral | +0.256 |
ynes | +0.253 |
Neg logit contributions | |
TIT | -0.309 |
YY | -0.283 |
tz | -0.281 |
ieth | -0.275 |
ucha | -0.271 |
Token | Thus |
Token ID | 6660 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
TIT | +0.202 |
YY | +0.184 |
tz | +0.184 |
ieth | +0.180 |
ucha | +0.177 |
Neg logit contributions | |
inver | -0.171 |
Fug | -0.165 |
Fract | -0.163 |
Spiral | -0.159 |
ynes | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
TIT | +0.525 |
YY | +0.485 |
tz | +0.483 |
ieth | +0.474 |
ucha | +0.467 |
Neg logit contributions | |
inver | -0.368 |
Fug | -0.357 |
Fract | -0.355 |
Spiral | -0.343 |
ynes | -0.340 |
Token | power |
Token ID | 1176 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
inver | +0.098 |
Fug | +0.096 |
Fract | +0.095 |
Spiral | +0.092 |
ynes | +0.091 |
Neg logit contributions | |
TIT | -0.138 |
YY | -0.127 |
tz | -0.127 |
ieth | -0.124 |
ucha | -0.122 |
Token | in |
Token ID | 287 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
TIT | +0.283 |
YY | +0.261 |
tz | +0.259 |
ieth | +0.256 |
ucha | +0.252 |
Neg logit contributions | |
inver | -0.211 |
Fract | -0.205 |
Fug | -0.205 |
Spiral | -0.199 |
ynes | -0.195 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
TIT | +0.097 |
tz | +0.089 |
YY | +0.089 |
ieth | +0.087 |
ucha | +0.086 |
Neg logit contributions | |
inver | -0.072 |
Fract | -0.070 |
Fug | -0.070 |
Spiral | -0.067 |
ynes | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
TIT | +0.736 |
YY | +0.679 |
tz | +0.676 |
ieth | +0.664 |
ucha | +0.655 |
Neg logit contributions | |
inver | -0.503 |
Fug | -0.488 |
Fract | -0.486 |
Spiral | -0.468 |
ynes | -0.461 |
Token | California |
Token ID | 3442 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
TIT | +0.741 |
YY | +0.688 |
tz | +0.681 |
ieth | +0.671 |
Judaism | +0.665 |
Neg logit contributions | |
inver | -0.505 |
Fract | -0.496 |
Fug | -0.493 |
Spiral | -0.473 |
ynes | -0.472 |
Token | . |
Token ID | 13 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
TIT | +0.706 |
YY | +0.642 |
tz | +0.637 |
ieth | +0.626 |
ucha | +0.615 |
Neg logit contributions | |
inver | -0.594 |
Fug | -0.583 |
Fract | -0.578 |
Spiral | -0.560 |
ynes | -0.556 |
Token | Hide |
Token ID | 10415 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
TIT | +0.706 |
YY | +0.651 |
tz | +0.642 |
ieth | +0.628 |
ucha | +0.620 |
Neg logit contributions | |
inver | -0.600 |
Fract | -0.567 |
Fug | -0.565 |
ynes | -0.551 |
Spiral | -0.550 |
Token | Caption |
Token ID | 11260 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
TIT | +0.541 |
YY | +0.333 |
tz | +0.298 |
Judaism | +0.232 |
ieth | +0.223 |
Neg logit contributions | |
inver | -3.946 |
Fug | -3.829 |
Fract | -3.809 |
ynes | -3.790 |
Spiral | -3.746 |
Token | 9 |
Token ID | 860 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
TIT | +2.087 |
YY | +1.858 |
tz | +1.849 |
ieth | +1.826 |
Judaism | +1.794 |
Neg logit contributions | |
inver | -2.370 |
Fug | -2.248 |
ynes | -2.243 |
awa | -2.236 |
Fract | -2.200 |
Token | of |
Token ID | 286 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
TIT | +0.350 |
YY | +0.322 |
tz | +0.320 |
ieth | +0.314 |
ucha | +0.310 |
Neg logit contributions | |
inver | -0.263 |
Fug | -0.254 |
Fract | -0.253 |
Spiral | -0.245 |
ynes | -0.241 |
Token | 15 |
Token ID | 1315 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
TIT | +0.299 |
YY | +0.268 |
tz | +0.266 |
ieth | +0.261 |
ucha | +0.257 |
Neg logit contributions | |
inver | -0.341 |
Fug | -0.330 |
Fract | -0.328 |
Spiral | -0.320 |
ynes | -0.320 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
TIT | +0.269 |
YY | +0.232 |
tz | +0.230 |
ieth | +0.223 |
ucha | +0.217 |
Neg logit contributions | |
inver | -0.529 |
Fug | -0.520 |
Fract | -0.518 |
Spiral | -0.507 |
ynes | -0.502 |
Token | Share |
Token ID | 8734 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
TIT | +2.122 |
YY | +1.900 |
tz | +1.893 |
ieth | +1.859 |
ucha | +1.813 |
Neg logit contributions | |
inver | -2.591 |
Fract | -2.484 |
Fug | -2.481 |
Spiral | -2.430 |
ynes | -2.421 |
Token | this |
Token ID | 428 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
TIT | +2.780 |
YY | +2.584 |
tz | +2.584 |
ieth | +2.516 |
ucha | +2.493 |
Neg logit contributions | |
inver | -2.000 |
Fract | -1.944 |
Fug | -1.940 |
ynes | -1.892 |
Spiral | -1.878 |
Token | comment |
Token ID | 2912 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
inver | +0.554 |
Fug | +0.538 |
Fract | +0.537 |
Spiral | +0.518 |
ynes | +0.512 |
Neg logit contributions | |
TIT | -0.654 |
YY | -0.597 |
tz | -0.590 |
ieth | -0.585 |
ucha | -0.574 |
Token | on |
Token ID | 319 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
inver | +0.510 |
Fug | +0.493 |
Fract | +0.490 |
Spiral | +0.471 |
ynes | +0.462 |
Neg logit contributions | |
TIT | -0.880 |
YY | -0.816 |
tz | -0.812 |
ieth | -0.799 |
ucha | -0.789 |
Token | Facebook |
Token ID | 3203 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
inver | +0.208 |
Fug | +0.202 |
Fract | +0.202 |
Spiral | +0.196 |
ynes | +0.194 |
Neg logit contributions | |
TIT | -0.198 |
YY | -0.180 |
tz | -0.179 |
ieth | -0.174 |
ucha | -0.172 |
Token | Share |
Token ID | 8734 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
inver | +0.866 |
Fug | +0.855 |
Fract | +0.854 |
Spiral | +0.824 |
ynes | +0.804 |
Neg logit contributions | |
TIT | -0.899 |
YY | -0.816 |
tz | -0.810 |
ieth | -0.797 |
ucha | -0.783 |
Token | this |
Token ID | 428 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
TIT | +2.692 |
tz | +2.505 |
YY | +2.496 |
ieth | +2.435 |
ucha | +2.417 |
Neg logit contributions | |
inver | -1.928 |
Fug | -1.888 |
Fract | -1.883 |
Spiral | -1.815 |
ynes | -1.813 |
Token | comment |
Token ID | 2912 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
inver | +0.541 |
Fug | +0.525 |
Fract | +0.524 |
Spiral | +0.507 |
ynes | +0.500 |
Neg logit contributions | |
TIT | -0.625 |
YY | -0.570 |
tz | -0.565 |
ieth | -0.557 |
ucha | -0.548 |
Token | on |
Token ID | 319 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
inver | +0.433 |
Fug | +0.419 |
Fract | +0.416 |
Spiral | +0.401 |
ynes | +0.394 |
Neg logit contributions | |
TIT | -0.735 |
YY | -0.681 |
tz | -0.678 |
ieth | -0.666 |
ucha | -0.658 |
Token | Twitter |
Token ID | 3009 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
inver | +0.341 |
Fug | +0.334 |
Fract | +0.333 |
Spiral | +0.325 |
ynes | +0.319 |
Neg logit contributions | |
TIT | -0.287 |
YY | -0.258 |
tz | -0.255 |
ieth | -0.251 |
ucha | -0.246 |
Token |
|
Token ID | 198 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
inver | +0.736 |
Fug | +0.718 |
Fract | +0.716 |
Spiral | +0.689 |
ynes | +0.678 |
Neg logit contributions | |
TIT | -0.912 |
YY | -0.838 |
tz | -0.832 |
ieth | -0.822 |
ucha | -0.803 |
Token | ua |
Token ID | 6413 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
inver | +0.340 |
Fug | +0.331 |
Fract | +0.329 |
Spiral | +0.319 |
ynes | +0.314 |
Neg logit contributions | |
TIT | -0.425 |
YY | -0.389 |
tz | -0.387 |
ieth | -0.380 |
ucha | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
TIT | +0.197 |
YY | +0.182 |
tz | +0.181 |
ieth | +0.178 |
ucha | +0.176 |
Neg logit contributions | |
inver | -0.131 |
Fug | -0.127 |
Fract | -0.126 |
Spiral | -0.122 |
ynes | -0.120 |
Token | New |
Token ID | 968 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
TIT | +0.675 |
YY | +0.611 |
tz | +0.605 |
ieth | +0.594 |
ucha | +0.582 |
Neg logit contributions | |
inver | -0.698 |
Fug | -0.679 |
Fract | -0.678 |
Spiral | -0.659 |
ynes | -0.655 |
Token | Hampshire |
Token ID | 13910 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
TIT | +0.571 |
YY | +0.524 |
tz | +0.521 |
ieth | +0.512 |
ucha | +0.504 |
Neg logit contributions | |
inver | -0.446 |
Fug | -0.433 |
Fract | -0.431 |
Spiral | -0.417 |
ynes | -0.411 |
Token | . |
Token ID | 13 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
inver | +0.409 |
Fug | +0.405 |
Fract | +0.398 |
Spiral | +0.386 |
ynes | +0.382 |
Neg logit contributions | |
TIT | -0.510 |
YY | -0.463 |
tz | -0.460 |
ieth | -0.451 |
ucha | -0.446 |
Token | Hide |
Token ID | 10415 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
TIT | +0.743 |
YY | +0.683 |
tz | +0.677 |
ieth | +0.661 |
ucha | +0.654 |
Neg logit contributions | |
inver | -0.596 |
Fract | -0.564 |
Fug | -0.561 |
ynes | -0.545 |
Spiral | -0.544 |
Token | Caption |
Token ID | 11260 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
TIT | +0.553 |
YY | +0.331 |
tz | +0.291 |
Judaism | +0.226 |
ucha | +0.215 |
Neg logit contributions | |
inver | -4.183 |
Fug | -4.056 |
Fract | -4.034 |
ynes | -4.022 |
Spiral | -3.966 |
Token | 6 |
Token ID | 718 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
TIT | +2.323 |
YY | +2.162 |
tz | +2.131 |
ucha | +2.082 |
Judaism | +2.056 |
Neg logit contributions | |
inver | -2.178 |
Fract | -2.120 |
Fug | -2.104 |
ynes | -2.054 |
awa | -2.030 |
Token | of |
Token ID | 286 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
TIT | +0.266 |
YY | +0.245 |
tz | +0.244 |
ieth | +0.239 |
ucha | +0.236 |
Neg logit contributions | |
inver | -0.197 |
Fug | -0.191 |
Fract | -0.190 |
Spiral | -0.183 |
ynes | -0.181 |
Token | 15 |
Token ID | 1315 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
TIT | +0.266 |
YY | +0.238 |
tz | +0.236 |
ieth | +0.232 |
ucha | +0.228 |
Neg logit contributions | |
inver | -0.307 |
Fug | -0.297 |
Fract | -0.295 |
ynes | -0.288 |
Spiral | -0.288 |
Token | Photos |
Token ID | 9434 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
TIT | +0.309 |
YY | +0.266 |
tz | +0.264 |
ieth | +0.256 |
ucha | +0.249 |
Neg logit contributions | |
inver | -0.603 |
Fug | -0.594 |
Fract | -0.592 |
Spiral | -0.579 |
ynes | -0.573 |