Token | city |
Token ID | 1748 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
\": | +0.021 |
aints | +0.021 |
confir | +0.021 |
wcs | +0.020 |
rid | +0.020 |
Neg logit contributions | |
collateral | -0.020 |
atari | -0.019 |
リ | -0.016 |
hers | -0.016 |
inert | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
collateral | +0.557 |
atari | +0.523 |
hers | +0.449 |
リ | +0.445 |
Admiral | +0.441 |
Neg logit contributions | |
\": | -0.538 |
aints | -0.531 |
confir | -0.517 |
wcs | -0.491 |
rid | -0.487 |
Token | buzzing |
Token ID | 41719 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
\": | +0.343 |
aints | +0.339 |
confir | +0.332 |
wcs | +0.313 |
rid | +0.312 |
Neg logit contributions | |
collateral | -0.316 |
atari | -0.296 |
hers | -0.254 |
リ | -0.254 |
Admiral | -0.247 |
Token | with |
Token ID | 351 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
collateral | +0.410 |
atari | +0.385 |
hers | +0.325 |
リ | +0.322 |
inert | +0.317 |
Neg logit contributions | |
\": | -0.479 |
aints | -0.474 |
confir | -0.468 |
wcs | -0.439 |
rid | -0.438 |
Token | r |
Token ID | 374 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
\": | +0.017 |
aints | +0.017 |
confir | +0.017 |
wcs | +0.016 |
rid | +0.016 |
Neg logit contributions | |
collateral | -0.017 |
atari | -0.016 |
hers | -0.013 |
リ | -0.013 |
inert | -0.013 |
Token | icks |
Token ID | 3378 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
collateral | +0.173 |
atari | +0.168 |
リ | +0.150 |
hers | +0.148 |
inert | +0.145 |
Neg logit contributions | |
\": | -0.080 |
confir | -0.078 |
aints | -0.077 |
wcs | -0.070 |
Sod | -0.069 |
Token | h |
Token ID | 71 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
collateral | +2.519 |
atari | +2.332 |
hers | +1.968 |
リ | +1.953 |
inert | +1.886 |
Neg logit contributions | |
\": | -3.185 |
confir | -3.172 |
aints | -3.108 |
wcs | -2.976 |
Sod | -2.957 |
Token | aws |
Token ID | 8356 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
collateral | +1.170 |
atari | +1.126 |
リ | +1.001 |
hers | +0.999 |
Admiral | +0.993 |
Neg logit contributions | |
confir | -0.443 |
\": | -0.442 |
aints | -0.402 |
wcs | -0.387 |
Sod | -0.367 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
collateral | +0.930 |
atari | +0.865 |
hers | +0.736 |
リ | +0.730 |
inert | +0.719 |
Neg logit contributions | |
\": | -1.069 |
aints | -1.060 |
confir | -1.050 |
rid | -0.982 |
Sod | -0.980 |
Token | workers |
Token ID | 3259 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
\": | +0.142 |
aints | +0.140 |
confir | +0.137 |
wcs | +0.129 |
Sod | +0.128 |
Neg logit contributions | |
collateral | -0.145 |
atari | -0.137 |
hers | -0.117 |
リ | -0.117 |
inert | -0.115 |
Token | to |
Token ID | 284 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
collateral | +0.316 |
atari | +0.294 |
hers | +0.252 |
リ | +0.249 |
inert | +0.248 |
Neg logit contributions | |
\": | -0.336 |
aints | -0.332 |
confir | -0.327 |
Sod | -0.308 |
rid | -0.307 |
Token | willingness |
Token ID | 16826 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
collateral | +0.081 |
atari | +0.077 |
リ | +0.066 |
hers | +0.065 |
inert | +0.063 |
Neg logit contributions | |
\": | -0.084 |
aints | -0.083 |
confir | -0.082 |
Sod | -0.077 |
rid | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
\": | +0.419 |
aints | +0.415 |
confir | +0.408 |
Sod | +0.388 |
rid | +0.387 |
Neg logit contributions | |
collateral | -0.292 |
atari | -0.275 |
リ | -0.227 |
hers | -0.223 |
inert | -0.216 |
Token | take |
Token ID | 1011 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
\": | +0.102 |
aints | +0.101 |
confir | +0.098 |
wcs | +0.093 |
Sod | +0.093 |
Neg logit contributions | |
collateral | -0.088 |
atari | -0.083 |
hers | -0.070 |
リ | -0.070 |
inert | -0.068 |
Token | on |
Token ID | 319 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
collateral | +0.306 |
atari | +0.285 |
リ | +0.241 |
hers | +0.240 |
inert | +0.233 |
Neg logit contributions | |
\": | -0.369 |
aints | -0.365 |
confir | -0.359 |
wcs | -0.338 |
Sod | -0.337 |
Token | Wall |
Token ID | 5007 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
collateral | +0.132 |
atari | +0.124 |
リ | +0.104 |
hers | +0.104 |
Admiral | +0.101 |
Neg logit contributions | |
\": | -0.156 |
aints | -0.154 |
confir | -0.151 |
wcs | -0.143 |
Sod | -0.142 |
Token | Street |
Token ID | 3530 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
collateral | +0.542 |
atari | +0.514 |
リ | +0.437 |
hers | +0.434 |
intern | +0.423 |
Neg logit contributions | |
\": | -0.562 |
confir | -0.556 |
aints | -0.553 |
wcs | -0.519 |
Sod | -0.518 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
collateral | +2.507 |
atari | +2.297 |
hers | +1.951 |
intern | +1.923 |
リ | +1.923 |
Neg logit contributions | |
\": | -2.858 |
aints | -2.809 |
confir | -2.793 |
wcs | -2.629 |
rid | -2.598 |
Token | the |
Token ID | 262 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
\": | +0.090 |
aints | +0.089 |
confir | +0.087 |
Sod | +0.082 |
rid | +0.082 |
Neg logit contributions | |
collateral | -0.074 |
atari | -0.070 |
リ | -0.059 |
hers | -0.058 |
inert | -0.056 |
Token | billionaire |
Token ID | 18828 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
collateral | +0.023 |
atari | +0.022 |
リ | +0.018 |
hers | +0.018 |
inert | +0.017 |
Neg logit contributions | |
\": | -0.027 |
aints | -0.027 |
confir | -0.026 |
wcs | -0.025 |
rid | -0.025 |
Token | class |
Token ID | 1398 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
collateral | +0.299 |
atari | +0.277 |
hers | +0.230 |
リ | +0.228 |
inert | +0.226 |
Neg logit contributions | |
\": | -0.372 |
aints | -0.367 |
confir | -0.364 |
wcs | -0.344 |
rid | -0.341 |
Token | , |
Token ID | 11 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
collateral | +0.845 |
atari | +0.786 |
hers | +0.668 |
リ | +0.664 |
inert | +0.650 |
Neg logit contributions | |
\": | -0.955 |
aints | -0.940 |
confir | -0.938 |
wcs | -0.876 |
Sod | -0.871 |
Token | v |
Token ID | 410 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
collateral | +0.502 |
atari | +0.472 |
リ | +0.399 |
hers | +0.393 |
Admiral | +0.387 |
Neg logit contributions | |
\": | -0.572 |
aints | -0.565 |
confir | -0.556 |
wcs | -0.526 |
rid | -0.525 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
collateral | +0.564 |
atari | +0.536 |
リ | +0.456 |
hers | +0.449 |
inert | +0.438 |
Neg logit contributions | |
\": | -0.623 |
aints | -0.619 |
confir | -0.605 |
Sod | -0.574 |
rid | -0.571 |
Token | NFL |
Token ID | 5134 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
collateral | +0.029 |
atari | +0.027 |
リ | +0.023 |
hers | +0.022 |
Admiral | +0.022 |
Neg logit contributions | |
\": | -0.040 |
aints | -0.040 |
confir | -0.039 |
wcs | -0.037 |
rid | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
collateral | +0.776 |
atari | +0.734 |
リ | +0.629 |
hers | +0.616 |
Admiral | +0.612 |
Neg logit contributions | |
\": | -0.784 |
aints | -0.768 |
confir | -0.759 |
wcs | -0.713 |
Sod | -0.710 |
Token |
|
Token ID | 198 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
collateral | +0.091 |
atari | +0.087 |
リ | +0.075 |
hers | +0.074 |
Admiral | +0.072 |
Neg logit contributions | |
confir | -0.094 |
aints | -0.092 |
\": | -0.091 |
wcs | -0.085 |
jriwal | -0.084 |
Token | Common |
Token ID | 17227 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
collateral | +0.127 |
atari | +0.122 |
リ | +0.105 |
hers | +0.102 |
Admiral | +0.100 |
Neg logit contributions | |
\": | -0.123 |
aints | -0.122 |
confir | -0.122 |
Sod | -0.113 |
wcs | -0.112 |
Token | Bounty |
Token ID | 38166 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
collateral | +2.469 |
atari | +2.307 |
リ | +1.998 |
Admiral | +1.944 |
hers | +1.917 |
Neg logit contributions | |
\": | -2.625 |
confir | -2.557 |
aints | -2.557 |
jriwal | -2.403 |
wcs | -2.397 |
Token | gate |
Token ID | 10494 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
collateral | +0.806 |
atari | +0.760 |
リ | +0.642 |
hers | +0.632 |
Admiral | +0.629 |
Neg logit contributions | |
\": | -0.868 |
confir | -0.855 |
aints | -0.854 |
wcs | -0.797 |
rid | -0.791 |
Token | Lit |
Token ID | 25659 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
collateral | +0.310 |
atari | +0.291 |
リ | +0.247 |
hers | +0.244 |
Admiral | +0.242 |
Neg logit contributions | |
\": | -0.329 |
aints | -0.325 |
confir | -0.322 |
wcs | -0.302 |
rid | -0.302 |
Token | igation |
Token ID | 7065 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
collateral | +0.946 |
atari | +0.902 |
リ | +0.755 |
hers | +0.753 |
Admiral | +0.740 |
Neg logit contributions | |
\": | -0.941 |
confir | -0.926 |
aints | -0.910 |
wcs | -0.857 |
Sod | -0.849 |
Token | Q |
Token ID | 1195 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
collateral | +0.045 |
atari | +0.042 |
リ | +0.036 |
hers | +0.035 |
Admiral | +0.035 |
Neg logit contributions | |
\": | -0.048 |
aints | -0.047 |
confir | -0.047 |
wcs | -0.044 |
rid | -0.044 |
Token | but |
Token ID | 475 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
collateral | +0.204 |
atari | +0.192 |
リ | +0.163 |
hers | +0.161 |
inert | +0.156 |
Neg logit contributions | |
\": | -0.243 |
aints | -0.240 |
confir | -0.235 |
Sod | -0.223 |
rid | -0.222 |
Token | I |
Token ID | 314 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
collateral | +0.061 |
atari | +0.057 |
リ | +0.048 |
hers | +0.047 |
Admiral | +0.046 |
Neg logit contributions | |
\": | -0.084 |
aints | -0.083 |
confir | -0.081 |
wcs | -0.077 |
Sod | -0.077 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
collateral | +0.437 |
atari | +0.412 |
リ | +0.344 |
hers | +0.341 |
intern | +0.332 |
Neg logit contributions | |
aints | -0.551 |
\": | -0.551 |
confir | -0.535 |
wcs | -0.509 |
Sod | -0.508 |
Token | like |
Token ID | 588 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
collateral | +1.002 |
atari | +0.922 |
hers | +0.792 |
リ | +0.784 |
inert | +0.778 |
Neg logit contributions | |
\": | -1.156 |
aints | -1.141 |
confir | -1.113 |
wcs | -1.054 |
Sod | -1.050 |
Token | Harry |
Token ID | 5850 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
collateral | +0.195 |
atari | +0.181 |
リ | +0.150 |
hers | +0.148 |
Admiral | +0.144 |
Neg logit contributions | |
\": | -0.279 |
aints | -0.276 |
confir | -0.271 |
wcs | -0.257 |
rid | -0.256 |
Token | Potter |
Token ID | 14179 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
collateral | +0.383 |
atari | +0.355 |
リ | +0.299 |
hers | +0.292 |
inert | +0.282 |
Neg logit contributions | |
\": | -0.537 |
aints | -0.534 |
confir | -0.523 |
wcs | -0.493 |
rid | -0.490 |
Token | sitting |
Token ID | 5586 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
collateral | +2.398 |
atari | +2.252 |
リ | +1.914 |
hers | +1.884 |
intern | +1.848 |
Neg logit contributions | |
\": | -2.670 |
aints | -2.649 |
confir | -2.584 |
wcs | -2.443 |
jriwal | -2.413 |
Token | under |
Token ID | 739 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
\": | +0.473 |
aints | +0.468 |
confir | +0.460 |
Sod | +0.433 |
wcs | +0.432 |
Neg logit contributions | |
collateral | -0.415 |
atari | -0.391 |
リ | -0.331 |
hers | -0.330 |
inert | -0.322 |
Token | the |
Token ID | 262 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
collateral | +0.116 |
atari | +0.108 |
hers | +0.091 |
リ | +0.091 |
inert | +0.088 |
Neg logit contributions | |
\": | -0.148 |
aints | -0.145 |
confir | -0.143 |
wcs | -0.136 |
jriwal | -0.134 |
Token | sorting |
Token ID | 29407 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
collateral | +0.643 |
atari | +0.606 |
リ | +0.520 |
hers | +0.519 |
Admiral | +0.512 |
Neg logit contributions | |
\": | -0.611 |
aints | -0.598 |
confir | -0.591 |
wcs | -0.561 |
jriwal | -0.548 |
Token | hat |
Token ID | 6877 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
collateral | +0.378 |
atari | +0.359 |
リ | +0.300 |
hers | +0.300 |
inert | +0.293 |
Neg logit contributions | |
\": | -0.442 |
aints | -0.437 |
confir | -0.432 |
wcs | -0.405 |
Sod | -0.404 |
Token | lex |
Token ID | 2588 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
\": | +0.244 |
aints | +0.241 |
confir | +0.239 |
Sod | +0.226 |
wcs | +0.225 |
Neg logit contributions | |
collateral | -0.191 |
atari | -0.182 |
リ | -0.151 |
hers | -0.148 |
inert | -0.145 |
Token | ible |
Token ID | 856 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
\": | +0.223 |
aints | +0.220 |
confir | +0.216 |
Sod | +0.201 |
wcs | +0.200 |
Neg logit contributions | |
collateral | -0.283 |
atari | -0.271 |
リ | -0.238 |
hers | -0.233 |
inert | -0.230 |
Token | deadlines |
Token ID | 36773 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
\": | +0.051 |
aints | +0.050 |
confir | +0.050 |
Sod | +0.047 |
rid | +0.047 |
Neg logit contributions | |
collateral | -0.040 |
atari | -0.038 |
リ | -0.032 |
hers | -0.031 |
inert | -0.031 |
Token | is |
Token ID | 318 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
\": | +0.086 |
aints | +0.085 |
confir | +0.084 |
Sod | +0.079 |
rid | +0.079 |
Neg logit contributions | |
collateral | -0.083 |
atari | -0.078 |
リ | -0.066 |
hers | -0.066 |
intern | -0.064 |
Token | imp |
Token ID | 848 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
collateral | +0.280 |
atari | +0.261 |
リ | +0.225 |
hers | +0.224 |
inert | +0.219 |
Neg logit contributions | |
\": | -0.284 |
aints | -0.282 |
confir | -0.278 |
Sod | -0.260 |
wcs | -0.258 |
Token | ract |
Token ID | 974 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
collateral | +0.673 |
atari | +0.640 |
リ | +0.559 |
hers | +0.553 |
Admiral | +0.545 |
Neg logit contributions | |
\": | -0.545 |
aints | -0.538 |
confir | -0.536 |
Sod | -0.500 |
wcs | -0.489 |
Token | icable |
Token ID | 18424 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
collateral | +1.493 |
atari | +1.269 |
リ | +1.026 |
hers | +0.991 |
inert | +0.945 |
Neg logit contributions | |
\": | -3.445 |
confir | -3.416 |
aints | -3.388 |
Sod | -3.175 |
jriwal | -3.167 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
collateral | +0.191 |
atari | +0.180 |
リ | +0.152 |
hers | +0.150 |
inert | +0.146 |
Neg logit contributions | |
\": | -0.218 |
aints | -0.216 |
confir | -0.213 |
Sod | -0.201 |
rid | -0.199 |
Token | � |
Token ID | 447 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
collateral | +0.171 |
atari | +0.163 |
リ | +0.143 |
Admiral | +0.139 |
hers | +0.139 |
Neg logit contributions | |
confir | -0.150 |
\": | -0.149 |
aints | -0.148 |
wcs | -0.138 |
rid | -0.136 |
Token | � |
Token ID | 251 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
collateral | +0.045 |
atari | +0.043 |
リ | +0.037 |
hers | +0.036 |
inert | +0.036 |
Neg logit contributions | |
\": | -0.040 |
aints | -0.040 |
confir | -0.039 |
Sod | -0.037 |
rid | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
collateral | +0.308 |
atari | +0.293 |
リ | +0.257 |
Admiral | +0.251 |
hers | +0.250 |
Neg logit contributions | |
\": | -0.263 |
confir | -0.263 |
aints | -0.262 |
wcs | -0.244 |
rid | -0.240 |
Token | Among |
Token ID | 9754 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
collateral | +1.247 |
atari | +1.198 |
hers | +1.071 |
Admiral | +1.065 |
リ | +1.054 |
Neg logit contributions | |
\": | -0.590 |
aints | -0.590 |
confir | -0.577 |
wcs | -0.547 |
rid | -0.519 |
Token | Thieves |
Token ID | 40392 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
collateral | +0.011 |
atari | +0.010 |
リ | +0.009 |
hers | +0.009 |
Admiral | +0.009 |
Neg logit contributions | |
confir | -0.007 |
\": | -0.007 |
aints | -0.007 |
wcs | -0.007 |
jriwal | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
\": | +0.207 |
aints | +0.205 |
confir | +0.201 |
rid | +0.188 |
wcs | +0.188 |
Neg logit contributions | |
collateral | -0.254 |
atari | -0.242 |
リ | -0.210 |
hers | -0.208 |
intern | -0.204 |
Token | a |
Token ID | 257 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
\": | +0.184 |
aints | +0.184 |
confir | +0.179 |
wcs | +0.169 |
Sod | +0.168 |
Neg logit contributions | |
collateral | -0.174 |
atari | -0.163 |
リ | -0.140 |
hers | -0.139 |
inert | -0.136 |
Token | h |
Token ID | 289 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
collateral | +0.059 |
atari | +0.055 |
リ | +0.047 |
hers | +0.047 |
inert | +0.046 |
Neg logit contributions | |
\": | -0.060 |
aints | -0.060 |
confir | -0.058 |
wcs | -0.055 |
rid | -0.055 |
Token | oot |
Token ID | 1025 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
collateral | +0.734 |
atari | +0.722 |
リ | +0.626 |
hers | +0.617 |
Admiral | +0.607 |
Neg logit contributions | |
\": | -0.501 |
confir | -0.496 |
aints | -0.485 |
wcs | -0.449 |
Sod | -0.447 |
Token | from |
Token ID | 422 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
collateral | +2.229 |
atari | +2.126 |
リ | +1.756 |
hers | +1.753 |
intern | +1.715 |
Neg logit contributions | |
\": | -2.612 |
aints | -2.567 |
confir | -2.547 |
Sod | -2.406 |
wcs | -2.400 |
Token | bold |
Token ID | 10758 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
\": | +0.074 |
aints | +0.074 |
confir | +0.073 |
wcs | +0.069 |
rid | +0.068 |
Neg logit contributions | |
collateral | -0.058 |
atari | -0.054 |
リ | -0.046 |
hers | -0.045 |
inert | -0.044 |
Token | beginning |
Token ID | 3726 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
collateral | +1.767 |
atari | +1.695 |
リ | +1.438 |
hers | +1.417 |
Admiral | +1.406 |
Neg logit contributions | |
\": | -1.795 |
aints | -1.783 |
confir | -1.769 |
wcs | -1.653 |
rid | -1.641 |
Token | right |
Token ID | 826 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
\": | +0.775 |
aints | +0.766 |
confir | +0.756 |
Sod | +0.714 |
wcs | +0.712 |
Neg logit contributions | |
collateral | -0.643 |
atari | -0.611 |
リ | -0.516 |
hers | -0.505 |
inert | -0.492 |
Token | through |
Token ID | 832 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
\": | +0.191 |
aints | +0.190 |
confir | +0.188 |
Sod | +0.175 |
wcs | +0.174 |
Neg logit contributions | |
collateral | -0.208 |
atari | -0.197 |
リ | -0.170 |
hers | -0.169 |
inert | -0.166 |
Token | someone |
Token ID | 2130 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
collateral | +0.001 |
atari | +0.001 |
リ | +0.001 |
hers | +0.001 |
Admiral | +0.001 |
Neg logit contributions | |
\": | -0.001 |
aints | -0.001 |
confir | -0.001 |
Sod | -0.001 |
rid | -0.001 |
Token | who |
Token ID | 508 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
\": | +1.054 |
aints | +1.041 |
confir | +1.026 |
Sod | +0.965 |
rid | +0.963 |
Neg logit contributions | |
collateral | -0.911 |
atari | -0.856 |
リ | -0.722 |
hers | -0.720 |
inert | -0.701 |
Token | had |
Token ID | 550 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
\": | +0.104 |
aints | +0.102 |
confir | +0.101 |
wcs | +0.094 |
rid | +0.093 |
Neg logit contributions | |
collateral | -0.122 |
atari | -0.116 |
hers | -0.100 |
リ | -0.100 |
intern | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
collateral | +0.010 |
atari | +0.009 |
リ | +0.008 |
hers | +0.008 |
inert | +0.008 |
Neg logit contributions | |
\": | -0.012 |
aints | -0.012 |
confir | -0.011 |
Sod | -0.011 |
rid | -0.011 |
Token | r |
Token ID | 374 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
collateral | +0.077 |
atari | +0.073 |
hers | +0.061 |
リ | +0.061 |
inert | +0.059 |
Neg logit contributions | |
\": | -0.090 |
aints | -0.089 |
confir | -0.087 |
Sod | -0.083 |
rid | -0.082 |
Token | ouse |
Token ID | 1076 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
\": | +0.226 |
aints | +0.222 |
confir | +0.220 |
Sod | +0.208 |
wcs | +0.207 |
Neg logit contributions | |
collateral | -0.197 |
atari | -0.189 |
リ | -0.158 |
hers | -0.155 |
inert | -0.152 |
Token | a |
Token ID | 257 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
collateral | +2.069 |
atari | +1.921 |
hers | +1.663 |
Admiral | +1.580 |
リ | +1.564 |
Neg logit contributions | |
\": | -2.714 |
aints | -2.650 |
confir | -2.649 |
wcs | -2.467 |
jriwal | -2.449 |
Token | ble |
Token ID | 7245 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
collateral | +0.054 |
atari | +0.051 |
リ | +0.042 |
hers | +0.042 |
inert | +0.041 |
Neg logit contributions | |
\": | -0.070 |
aints | -0.069 |
confir | -0.068 |
wcs | -0.064 |
rid | -0.064 |
Token | ary |
Token ID | 560 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
collateral | +0.450 |
atari | +0.428 |
リ | +0.362 |
hers | +0.357 |
inert | +0.347 |
Neg logit contributions | |
\": | -0.512 |
aints | -0.507 |
confir | -0.500 |
Sod | -0.470 |
rid | -0.468 |
Token | - |
Token ID | 12 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
collateral | +1.552 |
atari | +1.468 |
hers | +1.250 |
inert | +1.242 |
intern | +1.240 |
Neg logit contributions | |
\": | -1.581 |
aints | -1.577 |
confir | -1.554 |
wcs | -1.460 |
rid | -1.419 |
Token | eyed |
Token ID | 18834 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
collateral | +0.320 |
atari | +0.306 |
リ | +0.248 |
hers | +0.247 |
Admiral | +0.240 |
Neg logit contributions | |
\": | -0.438 |
confir | -0.435 |
aints | -0.432 |
Sod | -0.404 |
wcs | -0.403 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
collateral | +0.193 |
atari | +0.181 |
hers | +0.154 |
リ | +0.154 |
inert | +0.150 |
Neg logit contributions | |
\": | -0.214 |
aints | -0.212 |
confir | -0.209 |
wcs | -0.197 |
rid | -0.196 |
Token | If |
Token ID | 1002 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
\": | +0.030 |
confir | +0.030 |
aints | +0.030 |
wcs | +0.028 |
rid | +0.028 |
Neg logit contributions | |
collateral | -0.031 |
atari | -0.030 |
リ | -0.026 |
hers | -0.025 |
Admiral | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
\": | +0.607 |
aints | +0.601 |
confir | +0.590 |
rid | +0.557 |
Sod | +0.557 |
Neg logit contributions | |
collateral | -0.441 |
atari | -0.413 |
リ | -0.343 |
hers | -0.341 |
Admiral | -0.329 |
Token | body |
Token ID | 1767 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
collateral | +0.736 |
atari | +0.691 |
リ | +0.587 |
hers | +0.584 |
inert | +0.577 |
Neg logit contributions | |
\": | -0.789 |
aints | -0.779 |
confir | -0.763 |
rid | -0.719 |
wcs | -0.719 |
Token | got |
Token ID | 1392 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
collateral | +1.446 |
atari | +1.377 |
hers | +1.182 |
リ | +1.175 |
inert | +1.158 |
Neg logit contributions | |
\": | -1.321 |
aints | -1.296 |
confir | -1.278 |
Sod | -1.195 |
rid | -1.193 |
Token | cold |
Token ID | 4692 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
collateral | +0.328 |
atari | +0.306 |
hers | +0.270 |
リ | +0.264 |
inert | +0.262 |
Neg logit contributions | |
\": | -0.312 |
aints | -0.308 |
confir | -0.301 |
wcs | -0.281 |
Sod | -0.280 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
collateral | +2.124 |
atari | +1.974 |
hers | +1.701 |
リ | +1.660 |
inert | +1.627 |
Neg logit contributions | |
\": | -2.549 |
aints | -2.515 |
confir | -2.499 |
Sod | -2.308 |
jriwal | -2.307 |
Token | her |
Token ID | 607 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
collateral | +0.100 |
atari | +0.093 |
リ | +0.076 |
hers | +0.075 |
inert | +0.072 |
Neg logit contributions | |
\": | -0.159 |
aints | -0.158 |
confir | -0.156 |
wcs | -0.147 |
Sod | -0.147 |
Token | immunity |
Token ID | 16989 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
collateral | +0.818 |
atari | +0.765 |
hers | +0.658 |
リ | +0.656 |
inert | +0.648 |
Neg logit contributions | |
\": | -0.814 |
aints | -0.801 |
confir | -0.790 |
wcs | -0.742 |
rid | -0.739 |
Token | would |
Token ID | 561 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
collateral | +0.284 |
atari | +0.266 |
hers | +0.226 |
リ | +0.225 |
inert | +0.219 |
Neg logit contributions | |
\": | -0.325 |
aints | -0.324 |
confir | -0.317 |
rid | -0.300 |
Sod | -0.299 |
Token | drop |
Token ID | 4268 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
collateral | +0.423 |
atari | +0.395 |
hers | +0.343 |
リ | +0.337 |
inert | +0.332 |
Neg logit contributions | |
\": | -0.444 |
aints | -0.438 |
confir | -0.427 |
wcs | -0.404 |
Sod | -0.404 |
Token | in |
Token ID | 287 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
\": | +0.022 |
aints | +0.021 |
confir | +0.021 |
wcs | +0.020 |
Sod | +0.020 |
Neg logit contributions | |
collateral | -0.019 |
atari | -0.018 |
hers | -0.015 |
リ | -0.015 |
inert | -0.015 |
Token | today |
Token ID | 1909 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
collateral | +0.095 |
atari | +0.089 |
hers | +0.075 |
リ | +0.075 |
intern | +0.073 |
Neg logit contributions | |
\": | -0.108 |
aints | -0.107 |
confir | -0.105 |
wcs | -0.099 |
rid | -0.098 |
Token | 's |
Token ID | 338 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
collateral | +0.281 |
atari | +0.266 |
リ | +0.227 |
hers | +0.223 |
inert | +0.218 |
Neg logit contributions | |
\": | -0.308 |
aints | -0.305 |
confir | -0.299 |
wcs | -0.282 |
Sod | -0.280 |
Token | Counter |
Token ID | 15034 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
collateral | +0.474 |
atari | +0.445 |
リ | +0.379 |
hers | +0.377 |
intern | +0.375 |
Neg logit contributions | |
\": | -0.468 |
aints | -0.466 |
confir | -0.451 |
wcs | -0.425 |
rid | -0.425 |
Token | - |
Token ID | 12 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
collateral | +0.122 |
atari | +0.115 |
リ | +0.101 |
hers | +0.099 |
Admiral | +0.099 |
Neg logit contributions | |
aints | -0.111 |
\": | -0.111 |
confir | -0.110 |
rid | -0.101 |
jriwal | -0.100 |
Token | Strike |
Token ID | 31584 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
collateral | +0.116 |
atari | +0.109 |
リ | +0.091 |
hers | +0.088 |
Admiral | +0.086 |
Neg logit contributions | |
\": | -0.174 |
aints | -0.173 |
confir | -0.171 |
Sod | -0.161 |
rid | -0.160 |
Token | are |
Token ID | 389 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
collateral | +2.219 |
atari | +2.066 |
リ | +1.743 |
hers | +1.741 |
intern | +1.732 |
Neg logit contributions | |
\": | -2.406 |
aints | -2.395 |
confir | -2.329 |
wcs | -2.222 |
jriwal | -2.203 |
Token | caused |
Token ID | 4073 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
collateral | +0.293 |
atari | +0.275 |
hers | +0.238 |
リ | +0.236 |
inert | +0.231 |
Neg logit contributions | |
\": | -0.280 |
aints | -0.276 |
confir | -0.269 |
wcs | -0.255 |
Sod | -0.253 |
Token | by |
Token ID | 416 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
collateral | +0.601 |
atari | +0.570 |
リ | +0.491 |
hers | +0.485 |
inert | +0.474 |
Neg logit contributions | |
\": | -0.577 |
aints | -0.570 |
confir | -0.558 |
Sod | -0.525 |
rid | -0.522 |
Token | two |
Token ID | 734 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
\": | +0.064 |
aints | +0.063 |
confir | +0.062 |
wcs | +0.058 |
Sod | +0.058 |
Neg logit contributions | |
collateral | -0.055 |
atari | -0.052 |
hers | -0.043 |
リ | -0.043 |
inert | -0.043 |
Token | magical |
Token ID | 10883 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
collateral | +0.444 |
atari | +0.416 |
リ | +0.357 |
hers | +0.356 |
inert | +0.353 |
Neg logit contributions | |
\": | -0.399 |
aints | -0.393 |
confir | -0.387 |
Sod | -0.363 |
wcs | -0.362 |
Token | king |
Token ID | 3364 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
collateral | +1.700 |
atari | +1.640 |
リ | +1.444 |
hers | +1.395 |
inert | +1.387 |
Neg logit contributions | |
\": | -1.147 |
aints | -1.138 |
confir | -1.124 |
wcs | -1.034 |
Sod | -1.027 |
Token | postwar |
Token ID | 44060 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
\": | +0.067 |
aints | +0.067 |
confir | +0.065 |
wcs | +0.062 |
rid | +0.061 |
Neg logit contributions | |
collateral | -0.062 |
atari | -0.059 |
リ | -0.050 |
hers | -0.049 |
inert | -0.048 |
Token | structure |
Token ID | 4645 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
collateral | +0.386 |
atari | +0.366 |
リ | +0.307 |
hers | +0.305 |
Admiral | +0.298 |
Neg logit contributions | |
\": | -0.441 |
aints | -0.440 |
confir | -0.432 |
wcs | -0.409 |
rid | -0.407 |
Token | that |
Token ID | 326 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
collateral | +0.188 |
atari | +0.177 |
リ | +0.151 |
hers | +0.150 |
inert | +0.146 |
Neg logit contributions | |
\": | -0.201 |
aints | -0.199 |
confir | -0.195 |
Sod | -0.183 |
rid | -0.183 |
Token | j |
Token ID | 474 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
collateral | +0.257 |
atari | +0.245 |
リ | +0.212 |
hers | +0.210 |
Admiral | +0.206 |
Neg logit contributions | |
\": | -0.222 |
aints | -0.221 |
confir | -0.215 |
wcs | -0.200 |
Sod | -0.200 |
Token | uts |
Token ID | 5500 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
collateral | +0.642 |
atari | +0.626 |
リ | +0.553 |
hers | +0.546 |
intern | +0.537 |
Neg logit contributions | |
\": | -0.362 |
confir | -0.352 |
aints | -0.350 |
Sod | -0.320 |
wcs | -0.317 |
Token | into |
Token ID | 656 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
collateral | +2.247 |
atari | +2.100 |
hers | +1.812 |
リ | +1.780 |
inert | +1.770 |
Neg logit contributions | |
\": | -2.393 |
aints | -2.348 |
confir | -2.318 |
wcs | -2.173 |
jriwal | -2.148 |
Token | the |
Token ID | 262 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
\": | +0.189 |
aints | +0.187 |
confir | +0.184 |
Sod | +0.174 |
rid | +0.174 |
Neg logit contributions | |
collateral | -0.154 |
atari | -0.146 |
リ | -0.123 |
hers | -0.121 |
inert | -0.118 |
Token | Hudson |
Token ID | 19995 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
collateral | +0.033 |
atari | +0.031 |
リ | +0.026 |
hers | +0.026 |
Admiral | +0.026 |
Neg logit contributions | |
\": | -0.038 |
aints | -0.038 |
confir | -0.037 |
wcs | -0.035 |
rid | -0.035 |
Token | River |
Token ID | 5866 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
\": | +1.169 |
aints | +1.156 |
confir | +1.136 |
Sod | +1.073 |
rid | +1.069 |
Neg logit contributions | |
collateral | -1.060 |
atari | -1.008 |
リ | -0.858 |
hers | -0.845 |
inert | -0.824 |
Token | at |
Token ID | 379 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
collateral | +0.485 |
atari | +0.461 |
リ | +0.389 |
hers | +0.385 |
inert | +0.375 |
Neg logit contributions | |
\": | -0.536 |
aints | -0.533 |
confir | -0.523 |
Sod | -0.492 |
rid | -0.491 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
collateral | +0.176 |
atari | +0.168 |
リ | +0.145 |
hers | +0.143 |
Admiral | +0.139 |
Neg logit contributions | |
confir | -0.195 |
aints | -0.186 |
\": | -0.184 |
wcs | -0.173 |
jriwal | -0.173 |
Token | The |
Token ID | 464 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
collateral | +0.197 |
atari | +0.191 |
リ | +0.167 |
hers | +0.161 |
Admiral | +0.158 |
Neg logit contributions | |
confir | -0.168 |
\": | -0.166 |
aints | -0.166 |
Sod | -0.153 |
jriwal | -0.152 |
Token | Brazil |
Token ID | 7595 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
collateral | +0.160 |
atari | +0.151 |
リ | +0.128 |
hers | +0.127 |
Admiral | +0.126 |
Neg logit contributions | |
\": | -0.169 |
aints | -0.169 |
confir | -0.165 |
wcs | -0.154 |
rid | -0.154 |
Token | ians |
Token ID | 1547 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
\": | +0.561 |
aints | +0.551 |
confir | +0.548 |
Sod | +0.513 |
jriwal | +0.510 |
Neg logit contributions | |
collateral | -0.543 |
atari | -0.515 |
リ | -0.442 |
hers | -0.434 |
Admiral | -0.428 |
Token | were |
Token ID | 547 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
\": | +0.314 |
aints | +0.312 |
confir | +0.306 |
Sod | +0.290 |
wcs | +0.289 |
Neg logit contributions | |
collateral | -0.292 |
atari | -0.276 |
リ | -0.232 |
hers | -0.231 |
Admiral | -0.226 |
Token | lucky |
Token ID | 9670 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
collateral | +0.182 |
atari | +0.170 |
hers | +0.145 |
リ | +0.144 |
inert | +0.142 |
Neg logit contributions | |
aints | -0.186 |
\": | -0.186 |
confir | -0.180 |
wcs | -0.170 |
jriwal | -0.169 |
Token | to |
Token ID | 284 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
collateral | +1.802 |
atari | +1.665 |
リ | +1.387 |
hers | +1.356 |
Admiral | +1.337 |
Neg logit contributions | |
aints | -2.704 |
\": | -2.670 |
confir | -2.639 |
jriwal | -2.504 |
Sod | -2.487 |
Token | be |
Token ID | 307 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
collateral | +0.245 |
atari | +0.228 |
hers | +0.192 |
リ | +0.190 |
intern | +0.188 |
Neg logit contributions | |
\": | -0.285 |
aints | -0.282 |
confir | -0.275 |
Sod | -0.262 |
wcs | -0.260 |
Token | put |
Token ID | 1234 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
collateral | +0.056 |
atari | +0.052 |
hers | +0.044 |
リ | +0.044 |
inert | +0.043 |
Neg logit contributions | |
\": | -0.061 |
aints | -0.060 |
confir | -0.059 |
Sod | -0.055 |
jriwal | -0.055 |
Token | into |
Token ID | 656 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
\": | +0.351 |
aints | +0.345 |
confir | +0.343 |
Sod | +0.319 |
jriwal | +0.317 |
Neg logit contributions | |
collateral | -0.332 |
atari | -0.315 |
リ | -0.269 |
hers | -0.267 |
inert | -0.260 |
Token | group |
Token ID | 1448 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
collateral | +0.018 |
atari | +0.017 |
リ | +0.014 |
hers | +0.014 |
Admiral | +0.014 |
Neg logit contributions | |
\": | -0.022 |
aints | -0.022 |
confir | -0.021 |
rid | -0.020 |
jriwal | -0.020 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
collateral | +0.135 |
atari | +0.126 |
hers | +0.108 |
リ | +0.108 |
inert | +0.106 |
Neg logit contributions | |
\": | -0.137 |
aints | -0.135 |
confir | -0.133 |
wcs | -0.125 |
rid | -0.124 |
Token | s |
Token ID | 82 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
\": | +0.619 |
aints | +0.610 |
confir | +0.600 |
wcs | +0.556 |
Sod | +0.555 |
Neg logit contributions | |
collateral | -0.776 |
atari | -0.737 |
リ | -0.644 |
hers | -0.640 |
inert | -0.626 |
Token | would |
Token ID | 561 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
\": | +0.097 |
aints | +0.096 |
confir | +0.095 |
Sod | +0.090 |
wcs | +0.090 |
Neg logit contributions | |
collateral | -0.081 |
atari | -0.077 |
hers | -0.064 |
リ | -0.064 |
inert | -0.063 |
Token | gen |
Token ID | 2429 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
collateral | +0.388 |
atari | +0.364 |
hers | +0.311 |
リ | +0.306 |
inert | +0.302 |
Neg logit contributions | |
\": | -0.425 |
aints | -0.417 |
confir | -0.413 |
wcs | -0.390 |
Sod | -0.390 |
Token | uf |
Token ID | 3046 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
collateral | +0.055 |
atari | +0.051 |
リ | +0.043 |
hers | +0.042 |
intern | +0.041 |
Neg logit contributions | |
\": | -0.071 |
aints | -0.070 |
confir | -0.070 |
Sod | -0.066 |
wcs | -0.066 |
Token | lect |
Token ID | 801 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
\": | +0.110 |
confir | +0.108 |
aints | +0.107 |
Sod | +0.101 |
jriwal | +0.098 |
Neg logit contributions | |
collateral | -0.127 |
atari | -0.122 |
hers | -0.106 |
リ | -0.106 |
Admiral | -0.103 |
Token | before |
Token ID | 878 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
collateral | +2.078 |
atari | +1.892 |
hers | +1.675 |
inert | +1.619 |
リ | +1.604 |
Neg logit contributions | |
\": | -2.420 |
confir | -2.388 |
aints | -2.385 |
wcs | -2.227 |
jriwal | -2.212 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
collateral | +0.206 |
atari | +0.192 |
hers | +0.165 |
リ | +0.162 |
inert | +0.160 |
Neg logit contributions | |
\": | -0.233 |
aints | -0.231 |
confir | -0.226 |
wcs | -0.213 |
rid | -0.212 |
Token | nut |
Token ID | 6701 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
collateral | +0.122 |
atari | +0.115 |
リ | +0.099 |
hers | +0.099 |
inert | +0.097 |
Neg logit contributions | |
\": | -0.119 |
aints | -0.119 |
confir | -0.116 |
wcs | -0.109 |
rid | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
collateral | +1.142 |
atari | +1.075 |
リ | +0.935 |
hers | +0.926 |
inert | +0.906 |
Neg logit contributions | |
\": | -1.027 |
aints | -1.007 |
confir | -0.991 |
Sod | -0.922 |
wcs | -0.920 |
Token | she |
Token ID | 673 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
collateral | +0.014 |
atari | +0.013 |
hers | +0.010 |
リ | +0.010 |
Admiral | +0.009 |
Neg logit contributions | |
\": | -0.026 |
aints | -0.026 |
confir | -0.026 |
wcs | -0.024 |
Sod | -0.024 |
Token | corporate |
Token ID | 6355 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
\": | +0.210 |
aints | +0.209 |
confir | +0.205 |
wcs | +0.194 |
rid | +0.194 |
Neg logit contributions | |
collateral | -0.158 |
atari | -0.148 |
リ | -0.123 |
hers | -0.122 |
Admiral | -0.119 |
Token | America |
Token ID | 2253 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
collateral | +1.093 |
atari | +1.012 |
リ | +0.847 |
hers | +0.839 |
Admiral | +0.832 |
Neg logit contributions | |
\": | -1.260 |
aints | -1.251 |
confir | -1.243 |
wcs | -1.165 |
rid | -1.160 |
Token | and |
Token ID | 290 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
collateral | +0.757 |
atari | +0.715 |
リ | +0.612 |
hers | +0.607 |
inert | +0.595 |
Neg logit contributions | |
\": | -0.727 |
aints | -0.719 |
confir | -0.716 |
Sod | -0.664 |
wcs | -0.663 |
Token | the |
Token ID | 262 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
\": | +0.058 |
aints | +0.057 |
confir | +0.056 |
wcs | +0.053 |
rid | +0.053 |
Neg logit contributions | |
collateral | -0.044 |
atari | -0.041 |
リ | -0.034 |
hers | -0.034 |
Admiral | -0.033 |
Token | Wall |
Token ID | 5007 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
collateral | +0.051 |
atari | +0.048 |
リ | +0.040 |
hers | +0.040 |
inert | +0.039 |
Neg logit contributions | |
\": | -0.059 |
aints | -0.058 |
confir | -0.057 |
wcs | -0.054 |
rid | -0.054 |
Token | Street |
Token ID | 3530 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
collateral | +1.141 |
atari | +1.084 |
リ | +0.907 |
hers | +0.898 |
Admiral | +0.889 |
Neg logit contributions | |
confir | -1.343 |
\": | -1.305 |
aints | -1.282 |
wcs | -1.220 |
rid | -1.194 |
Token | cabal |
Token ID | 47548 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
collateral | +2.057 |
atari | +1.895 |
リ | +1.585 |
inert | +1.568 |
hers | +1.566 |
Neg logit contributions | |
\": | -2.424 |
confir | -2.401 |
aints | -2.398 |
wcs | -2.258 |
rid | -2.231 |
Token | is |
Token ID | 318 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
collateral | +0.585 |
atari | +0.549 |
リ | +0.471 |
hers | +0.468 |
inert | +0.460 |
Neg logit contributions | |
\": | -0.567 |
confir | -0.557 |
aints | -0.557 |
wcs | -0.515 |
Sod | -0.513 |
Token | their |
Token ID | 511 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
collateral | +0.010 |
atari | +0.009 |
リ | +0.008 |
hers | +0.008 |
Admiral | +0.008 |
Neg logit contributions | |
\": | -0.011 |
aints | -0.011 |
confir | -0.011 |
wcs | -0.010 |
rid | -0.010 |
Token | complete |
Token ID | 1844 |
Feature activation | -7.87e-02 |
Pos logit contributions | |
collateral | +0.587 |
atari | +0.548 |
hers | +0.465 |
リ | +0.464 |
inert | +0.461 |
Neg logit contributions | |
\": | -0.588 |
aints | -0.584 |
confir | -0.574 |
wcs | -0.536 |
rid | -0.533 |
Token | lack |
Token ID | 3092 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
\": | +0.058 |
aints | +0.057 |
confir | +0.056 |
wcs | +0.052 |
Sod | +0.052 |
Neg logit contributions | |
collateral | -0.067 |
atari | -0.064 |
リ | -0.055 |
hers | -0.055 |
inert | -0.054 |
Token | you |
Token ID | 345 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
collateral | +0.437 |
atari | +0.410 |
リ | +0.334 |
hers | +0.326 |
Admiral | +0.317 |
Neg logit contributions | |
\": | -0.700 |
aints | -0.695 |
confir | -0.685 |
wcs | -0.650 |
Sod | -0.649 |
Token | ! |
Token ID | 0 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
collateral | +0.263 |
atari | +0.248 |
リ | +0.212 |
hers | +0.209 |
Admiral | +0.206 |
Neg logit contributions | |
\": | -0.279 |
aints | -0.276 |
confir | -0.271 |
wcs | -0.255 |
Sod | -0.253 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
\": | +0.304 |
aints | +0.301 |
confir | +0.296 |
rid | +0.275 |
wcs | +0.275 |
Neg logit contributions | |
collateral | -0.345 |
atari | -0.330 |
リ | -0.286 |
hers | -0.282 |
Admiral | -0.276 |
Token | What |
Token ID | 2061 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
collateral | +0.179 |
atari | +0.174 |
リ | +0.151 |
hers | +0.146 |
Admiral | +0.143 |
Neg logit contributions | |
\": | -0.159 |
confir | -0.159 |
aints | -0.158 |
Sod | -0.146 |
wcs | -0.144 |
Token | Wall |
Token ID | 5007 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
collateral | +0.444 |
atari | +0.419 |
リ | +0.361 |
hers | +0.355 |
Admiral | +0.350 |
Neg logit contributions | |
\": | -0.438 |
aints | -0.437 |
confir | -0.425 |
wcs | -0.405 |
rid | -0.398 |
Token | Street |
Token ID | 3530 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
collateral | +0.147 |
atari | +0.140 |
リ | +0.120 |
hers | +0.118 |
Admiral | +0.115 |
Neg logit contributions | |
\": | -0.146 |
aints | -0.145 |
confir | -0.144 |
Sod | -0.134 |
wcs | -0.134 |
Token | doesn |
Token ID | 1595 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
collateral | +2.337 |
atari | +2.188 |
Admiral | +1.870 |
リ | +1.867 |
hers | +1.853 |
Neg logit contributions | |
aints | -2.104 |
\": | -2.090 |
confir | -2.065 |
wcs | -1.969 |
rid | -1.918 |
Token | � |
Token ID | 447 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
collateral | +0.222 |
atari | +0.215 |
リ | +0.188 |
hers | +0.182 |
Admiral | +0.179 |
Neg logit contributions | |
confir | -0.213 |
aints | -0.203 |
\": | -0.200 |
wcs | -0.189 |
jriwal | -0.188 |
Token | � |
Token ID | 247 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
collateral | +0.874 |
atari | +0.824 |
リ | +0.722 |
hers | +0.704 |
Admiral | +0.689 |
Neg logit contributions | |
aints | -0.775 |
\": | -0.772 |
confir | -0.760 |
Sod | -0.717 |
wcs | -0.713 |
Token | t |
Token ID | 83 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
collateral | +0.333 |
atari | +0.317 |
リ | +0.278 |
hers | +0.272 |
Admiral | +0.266 |
Neg logit contributions | |
\": | -0.286 |
aints | -0.285 |
confir | -0.280 |
Sod | -0.263 |
wcs | -0.262 |
Token | want |
Token ID | 765 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
\": | +0.351 |
aints | +0.350 |
confir | +0.344 |
Sod | +0.328 |
wcs | +0.327 |
Neg logit contributions | |
collateral | -0.223 |
atari | -0.209 |
リ | -0.170 |
hers | -0.167 |
Admiral | -0.161 |
Token | 1 |
Token ID | 16 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
collateral | +0.631 |
atari | +0.610 |
リ | +0.526 |
hers | +0.514 |
Admiral | +0.500 |
Neg logit contributions | |
confir | -0.597 |
\": | -0.593 |
aints | -0.592 |
wcs | -0.546 |
Sod | -0.545 |
Token | billion |
Token ID | 2997 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
collateral | +0.065 |
atari | +0.061 |
リ | +0.050 |
hers | +0.050 |
inert | +0.048 |
Neg logit contributions | |
\": | -0.089 |
aints | -0.089 |
confir | -0.087 |
Sod | -0.082 |
rid | -0.082 |
Token | in |
Token ID | 287 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
collateral | +0.622 |
atari | +0.576 |
hers | +0.491 |
リ | +0.484 |
Admiral | +0.477 |
Neg logit contributions | |
\": | -0.660 |
aints | -0.658 |
confir | -0.643 |
wcs | -0.606 |
rid | -0.602 |
Token | Kh |
Token ID | 5311 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
\": | +0.344 |
aints | +0.340 |
confir | +0.334 |
wcs | +0.316 |
rid | +0.316 |
Neg logit contributions | |
collateral | -0.268 |
atari | -0.250 |
リ | -0.208 |
hers | -0.207 |
inert | -0.201 |
Token | ark |
Token ID | 668 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
\": | +0.647 |
aints | +0.638 |
confir | +0.633 |
Sod | +0.586 |
wcs | +0.584 |
Neg logit contributions | |
collateral | -0.731 |
atari | -0.707 |
リ | -0.604 |
hers | -0.595 |
Admiral | -0.581 |
Token | iv |
Token ID | 452 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
collateral | +0.609 |
atari | +0.583 |
リ | +0.487 |
hers | +0.474 |
Admiral | +0.470 |
Neg logit contributions | |
\": | -0.692 |
aints | -0.680 |
confir | -0.679 |
wcs | -0.637 |
Sod | -0.627 |
Token | loans |
Token ID | 10021 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
collateral | +2.126 |
atari | +1.971 |
hers | +1.644 |
リ | +1.643 |
intern | +1.620 |
Neg logit contributions | |
\": | -2.352 |
aints | -2.329 |
confir | -2.253 |
wcs | -2.165 |
rid | -2.148 |
Token | likely |
Token ID | 1884 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
collateral | +0.946 |
atari | +0.880 |
hers | +0.742 |
リ | +0.736 |
Admiral | +0.722 |
Neg logit contributions | |
\": | -1.055 |
aints | -1.045 |
confir | -1.020 |
wcs | -0.966 |
rid | -0.964 |
Token | also |
Token ID | 635 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
\": | +0.309 |
aints | +0.305 |
confir | +0.299 |
Sod | +0.281 |
wcs | +0.280 |
Neg logit contributions | |
collateral | -0.333 |
atari | -0.314 |
hers | -0.269 |
リ | -0.268 |
inert | -0.261 |
Token | lacked |
Token ID | 19989 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
\": | +0.198 |
aints | +0.195 |
confir | +0.191 |
Sod | +0.180 |
wcs | +0.179 |
Neg logit contributions | |
collateral | -0.218 |
atari | -0.206 |
hers | -0.177 |
リ | -0.176 |
intern | -0.172 |
Token | collateral |
Token ID | 27907 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
\": | +0.551 |
aints | +0.547 |
confir | +0.536 |
Sod | +0.509 |
rid | +0.508 |
Neg logit contributions | |
collateral | -0.411 |
atari | -0.384 |
リ | -0.318 |
hers | -0.315 |
inert | -0.306 |
Token | � |
Token ID | 251 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
collateral | +0.491 |
atari | +0.471 |
リ | +0.410 |
hers | +0.405 |
inert | +0.396 |
Neg logit contributions | |
\": | -0.392 |
aints | -0.389 |
confir | -0.380 |
Sod | -0.355 |
rid | -0.353 |
Token | http |
Token ID | 2638 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
collateral | +0.107 |
atari | +0.102 |
リ | +0.085 |
hers | +0.084 |
Admiral | +0.082 |
Neg logit contributions | |
\": | -0.130 |
aints | -0.129 |
confir | -0.127 |
Sod | -0.120 |
rid | -0.119 |
Token | :// |
Token ID | 1378 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
confir | +0.572 |
\": | +0.566 |
aints | +0.566 |
wcs | +0.520 |
Sod | +0.520 |
Neg logit contributions | |
collateral | -0.600 |
atari | -0.576 |
リ | -0.500 |
hers | -0.490 |
Admiral | -0.477 |
Token | www |
Token ID | 2503 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
\": | +0.379 |
aints | +0.374 |
confir | +0.369 |
Sod | +0.344 |
rid | +0.340 |
Neg logit contributions | |
collateral | -0.445 |
atari | -0.429 |
リ | -0.372 |
hers | -0.366 |
inert | -0.357 |
Token | . |
Token ID | 13 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
\": | +0.929 |
aints | +0.922 |
confir | +0.918 |
Sod | +0.855 |
rid | +0.853 |
Neg logit contributions | |
collateral | -0.790 |
atari | -0.753 |
リ | -0.636 |
hers | -0.626 |
Admiral | -0.607 |
Token | members |
Token ID | 30814 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
collateral | +0.253 |
atari | +0.245 |
リ | +0.208 |
hers | +0.205 |
inert | +0.198 |
Neg logit contributions | |
\": | -0.259 |
aints | -0.254 |
confir | -0.254 |
Sod | -0.238 |
rid | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
collateral | +2.036 |
atari | +1.955 |
リ | +1.623 |
hers | +1.598 |
Admiral | +1.573 |
Neg logit contributions | |
\": | -2.321 |
confir | -2.273 |
aints | -2.270 |
Sod | -2.167 |
rid | -2.115 |
Token | trip |
Token ID | 39813 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
collateral | +0.309 |
atari | +0.300 |
リ | +0.258 |
hers | +0.253 |
Admiral | +0.247 |
Neg logit contributions | |
\": | -0.280 |
confir | -0.275 |
aints | -0.275 |
Sod | -0.255 |
rid | -0.250 |
Token | od |
Token ID | 375 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
collateral | +0.678 |
atari | +0.661 |
リ | +0.587 |
hers | +0.580 |
Admiral | +0.574 |
Neg logit contributions | |
\": | -0.337 |
confir | -0.325 |
aints | -0.322 |
Sod | -0.295 |
rid | -0.285 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
collateral | +0.115 |
atari | +0.110 |
リ | +0.094 |
hers | +0.092 |
inert | +0.090 |
Neg logit contributions | |
\": | -0.122 |
aints | -0.121 |
confir | -0.119 |
Sod | -0.112 |
rid | -0.111 |
Token | com |
Token ID | 785 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
collateral | +0.201 |
atari | +0.194 |
リ | +0.167 |
hers | +0.164 |
Admiral | +0.161 |
Neg logit contributions | |
\": | -0.177 |
aints | -0.174 |
confir | -0.173 |
Sod | -0.160 |
rid | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
collateral | +0.466 |
atari | +0.436 |
リ | +0.368 |
hers | +0.359 |
Admiral | +0.350 |
Neg logit contributions | |
\": | -0.643 |
aints | -0.642 |
confir | -0.630 |
wcs | -0.599 |
rid | -0.594 |
Token | G |
Token ID | 402 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
collateral | +0.320 |
atari | +0.306 |
リ | +0.268 |
hers | +0.261 |
Admiral | +0.259 |
Neg logit contributions | |
aints | -0.295 |
\": | -0.295 |
confir | -0.292 |
wcs | -0.271 |
rid | -0.270 |
Token | Wolf |
Token ID | 8662 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
collateral | +0.672 |
atari | +0.650 |
リ | +0.578 |
hers | +0.571 |
inert | +0.563 |
Neg logit contributions | |
\": | -0.359 |
aints | -0.352 |
confir | -0.344 |
Sod | -0.314 |
wcs | -0.313 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
\": | +0.036 |
aints | +0.036 |
confir | +0.035 |
wcs | +0.033 |
Sod | +0.033 |
Neg logit contributions | |
collateral | -0.038 |
atari | -0.036 |
リ | -0.031 |
hers | -0.030 |
Admiral | -0.030 |
Token | H |
Token ID | 39 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
collateral | +0.145 |
atari | +0.141 |
リ | +0.122 |
hers | +0.119 |
Admiral | +0.116 |
Neg logit contributions | |
\": | -0.129 |
confir | -0.128 |
aints | -0.128 |
Sod | -0.118 |
wcs | -0.116 |
Token | ollywood |
Token ID | 31777 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
collateral | +0.295 |
atari | +0.285 |
リ | +0.245 |
hers | +0.241 |
Admiral | +0.237 |
Neg logit contributions | |
\": | -0.256 |
aints | -0.250 |
confir | -0.249 |
Sod | -0.232 |
wcs | -0.232 |
Token | , |
Token ID | 11 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
collateral | +2.175 |
atari | +2.060 |
リ | +1.761 |
hers | +1.724 |
Admiral | +1.715 |
Neg logit contributions | |
\": | -2.140 |
aints | -2.131 |
confir | -2.100 |
wcs | -1.984 |
Sod | -1.946 |
Token | it |
Token ID | 340 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
\": | +0.470 |
aints | +0.465 |
confir | +0.457 |
wcs | +0.430 |
rid | +0.429 |
Neg logit contributions | |
collateral | -0.428 |
atari | -0.402 |
リ | -0.344 |
hers | -0.340 |
inert | -0.331 |
Token | seems |
Token ID | 2331 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
\": | +0.168 |
aints | +0.166 |
confir | +0.163 |
Sod | +0.152 |
wcs | +0.152 |
Neg logit contributions | |
collateral | -0.190 |
atari | -0.181 |
リ | -0.158 |
hers | -0.155 |
inert | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
\": | +1.208 |
aints | +1.192 |
confir | +1.170 |
Sod | +1.111 |
rid | +1.108 |
Neg logit contributions | |
collateral | -1.217 |
atari | -1.171 |
リ | -0.996 |
hers | -0.982 |
inert | -0.959 |
Token | is |
Token ID | 318 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
\": | +0.346 |
aints | +0.342 |
confir | +0.335 |
wcs | +0.312 |
rid | +0.312 |
Neg logit contributions | |
collateral | -0.405 |
atari | -0.386 |
リ | -0.335 |
hers | -0.332 |
inert | -0.325 |
Token | you |
Token ID | 345 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
\": | +0.278 |
aints | +0.276 |
confir | +0.272 |
Sod | +0.256 |
wcs | +0.255 |
Neg logit contributions | |
collateral | -0.241 |
atari | -0.226 |
リ | -0.191 |
hers | -0.190 |
Admiral | -0.184 |
Token | can |
Token ID | 460 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
\": | +0.009 |
aints | +0.009 |
confir | +0.009 |
wcs | +0.009 |
Sod | +0.009 |
Neg logit contributions | |
collateral | -0.009 |
atari | -0.009 |
リ | -0.007 |
hers | -0.007 |
intern | -0.007 |
Token | tell |
Token ID | 1560 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
collateral | +0.031 |
atari | +0.029 |
リ | +0.024 |
hers | +0.024 |
intern | +0.023 |
Neg logit contributions | |
\": | -0.038 |
aints | -0.038 |
confir | -0.037 |
Sod | -0.035 |
wcs | -0.035 |
Token | which |
Token ID | 543 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
collateral | +0.343 |
atari | +0.316 |
hers | +0.270 |
リ | +0.267 |
Admiral | +0.261 |
Neg logit contributions | |
\": | -0.424 |
aints | -0.420 |
confir | -0.413 |
jriwal | -0.388 |
wcs | -0.388 |
Token | Wall |
Token ID | 5007 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
collateral | +0.091 |
atari | +0.084 |
リ | +0.071 |
hers | +0.071 |
intern | +0.069 |
Neg logit contributions | |
\": | -0.105 |
aints | -0.105 |
confir | -0.103 |
wcs | -0.097 |
rid | -0.097 |
Token | Street |
Token ID | 3530 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
collateral | +0.261 |
atari | +0.247 |
リ | +0.210 |
hers | +0.208 |
intern | +0.203 |
Neg logit contributions | |
confir | -0.288 |
\": | -0.284 |
aints | -0.278 |
wcs | -0.262 |
Sod | -0.262 |
Token | entities |
Token ID | 12066 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
collateral | +1.972 |
atari | +1.802 |
リ | +1.502 |
hers | +1.494 |
intern | +1.480 |
Neg logit contributions | |
\": | -2.392 |
aints | -2.381 |
confir | -2.364 |
wcs | -2.245 |
rid | -2.219 |
Token | provoke |
Token ID | 29791 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
\": | +0.289 |
aints | +0.287 |
confir | +0.282 |
rid | +0.266 |
wcs | +0.265 |
Neg logit contributions | |
collateral | -0.245 |
atari | -0.231 |
リ | -0.195 |
hers | -0.193 |
Admiral | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
collateral | +0.675 |
atari | +0.617 |
hers | +0.522 |
リ | +0.519 |
Admiral | +0.506 |
Neg logit contributions | |
\": | -0.844 |
aints | -0.836 |
confir | -0.828 |
wcs | -0.773 |
rid | -0.773 |
Token | most |
Token ID | 749 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
collateral | +0.148 |
atari | +0.137 |
リ | +0.117 |
hers | +0.117 |
Admiral | +0.114 |
Neg logit contributions | |
\": | -0.159 |
aints | -0.157 |
confir | -0.155 |
wcs | -0.146 |
rid | -0.145 |
Token | grip |
Token ID | 11762 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
collateral | +0.214 |
atari | +0.198 |
hers | +0.170 |
リ | +0.170 |
inert | +0.166 |
Neg logit contributions | |
\": | -0.214 |
aints | -0.211 |
confir | -0.209 |
wcs | -0.195 |
Sod | -0.195 |
Token | being |
Token ID | 852 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
\": | +0.128 |
aints | +0.126 |
confir | +0.124 |
Sod | +0.116 |
rid | +0.116 |
Neg logit contributions | |
collateral | -0.119 |
atari | -0.113 |
リ | -0.096 |
hers | -0.096 |
inert | -0.093 |
Token | involved |
Token ID | 2950 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
\": | +0.450 |
aints | +0.445 |
confir | +0.436 |
Sod | +0.410 |
rid | +0.409 |
Neg logit contributions | |
collateral | -0.455 |
atari | -0.433 |
リ | -0.371 |
hers | -0.367 |
inert | -0.358 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
\": | +0.739 |
aints | +0.732 |
confir | +0.717 |
Sod | +0.676 |
rid | +0.674 |
Neg logit contributions | |
collateral | -0.721 |
atari | -0.687 |
リ | -0.588 |
hers | -0.580 |
inert | -0.566 |
Token | Counter |
Token ID | 15034 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
collateral | +0.162 |
atari | +0.151 |
リ | +0.128 |
hers | +0.127 |
inert | +0.124 |
Neg logit contributions | |
\": | -0.184 |
aints | -0.182 |
confir | -0.178 |
Sod | -0.169 |
rid | -0.168 |
Token | - |
Token ID | 12 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
collateral | +0.136 |
atari | +0.131 |
リ | +0.114 |
hers | +0.112 |
inert | +0.110 |
Neg logit contributions | |
\": | -0.109 |
aints | -0.108 |
confir | -0.105 |
Sod | -0.098 |
rid | -0.098 |
Token | Strike |
Token ID | 31584 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
collateral | +0.136 |
atari | +0.128 |
リ | +0.106 |
hers | +0.104 |
Admiral | +0.100 |
Neg logit contributions | |
\": | -0.200 |
aints | -0.198 |
confir | -0.198 |
Sod | -0.185 |
rid | -0.184 |
Token | becoming |
Token ID | 5033 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
collateral | +2.130 |
atari | +1.984 |
リ | +1.705 |
hers | +1.700 |
inert | +1.675 |
Neg logit contributions | |
\": | -2.207 |
aints | -2.184 |
confir | -2.127 |
jriwal | -2.013 |
wcs | -2.004 |
Token | increasingly |
Token ID | 6481 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
\": | +0.644 |
aints | +0.638 |
confir | +0.627 |
Sod | +0.585 |
rid | +0.583 |
Neg logit contributions | |
collateral | -0.607 |
atari | -0.566 |
リ | -0.486 |
hers | -0.484 |
inert | -0.474 |
Token | professional |
Token ID | 4708 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
\": | +0.073 |
aints | +0.072 |
confir | +0.071 |
Sod | +0.066 |
rid | +0.066 |
Neg logit contributions | |
collateral | -0.071 |
atari | -0.067 |
リ | -0.057 |
hers | -0.057 |
inert | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
\": | +0.040 |
aints | +0.040 |
confir | +0.039 |
Sod | +0.037 |
rid | +0.037 |
Neg logit contributions | |
collateral | -0.037 |
atari | -0.034 |
リ | -0.029 |
hers | -0.029 |
inert | -0.028 |
Token | we |
Token ID | 356 |
Feature activation | +2.24e-04 |
Pos logit contributions | |
collateral | +0.024 |
atari | +0.023 |
リ | +0.019 |
hers | +0.019 |
inert | +0.019 |
Neg logit contributions | |
\": | -0.028 |
aints | -0.028 |
confir | -0.027 |
Sod | -0.026 |
rid | -0.026 |
Token | 6 |
Token ID | 21 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
collateral | +0.226 |
atari | +0.217 |
リ | +0.186 |
hers | +0.181 |
Admiral | +0.176 |
Neg logit contributions | |
confir | -0.248 |
\": | -0.246 |
aints | -0.246 |
wcs | -0.228 |
jriwal | -0.228 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
collateral | +0.028 |
atari | +0.027 |
リ | +0.023 |
hers | +0.022 |
Admiral | +0.022 |
Neg logit contributions | |
\": | -0.031 |
aints | -0.031 |
confir | -0.030 |
rid | -0.029 |
Sod | -0.029 |
Token | 500 |
Token ID | 4059 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
collateral | +0.014 |
atari | +0.013 |
リ | +0.011 |
hers | +0.011 |
inert | +0.010 |
Neg logit contributions | |
\": | -0.020 |
aints | -0.020 |
confir | -0.020 |
Sod | -0.019 |
rid | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
\": | +0.034 |
aints | +0.034 |
confir | +0.033 |
Sod | +0.031 |
rid | +0.031 |
Neg logit contributions | |
collateral | -0.030 |
atari | -0.028 |
リ | -0.024 |
hers | -0.023 |
Admiral | -0.023 |
Token | wh |
Token ID | 348 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
\": | +0.205 |
aints | +0.203 |
confir | +0.199 |
Sod | +0.187 |
rid | +0.187 |
Neg logit contributions | |
collateral | -0.197 |
atari | -0.186 |
リ | -0.159 |
hers | -0.158 |
inert | -0.153 |
Token | ack |
Token ID | 441 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
collateral | +0.483 |
atari | +0.466 |
リ | +0.399 |
hers | +0.386 |
intern | +0.380 |
Neg logit contributions | |
\": | -0.472 |
confir | -0.466 |
aints | -0.463 |
wcs | -0.430 |
Sod | -0.429 |
Token | , |
Token ID | 11 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
collateral | +1.949 |
atari | +1.841 |
リ | +1.537 |
hers | +1.516 |
intern | +1.476 |
Neg logit contributions | |
\": | -2.342 |
aints | -2.316 |
confir | -2.307 |
wcs | -2.162 |
Sod | -2.161 |
Token | � |
Token ID | 447 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
\": | +0.035 |
aints | +0.035 |
confir | +0.034 |
rid | +0.032 |
Sod | +0.032 |
Neg logit contributions | |
collateral | -0.032 |
atari | -0.030 |
リ | -0.025 |
hers | -0.025 |
inert | -0.024 |
Token | � |
Token ID | 251 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
\": | +0.129 |
aints | +0.128 |
confir | +0.125 |
Sod | +0.118 |
rid | +0.118 |
Neg logit contributions | |
collateral | -0.115 |
atari | -0.109 |
リ | -0.093 |
hers | -0.091 |
inert | -0.089 |
Token | L |
Token ID | 406 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
\": | +0.100 |
aints | +0.099 |
confir | +0.097 |
Sod | +0.091 |
wcs | +0.091 |
Neg logit contributions | |
collateral | -0.098 |
atari | -0.092 |
リ | -0.079 |
hers | -0.078 |
Admiral | -0.076 |
Token | ave |
Token ID | 1015 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
collateral | +0.515 |
atari | +0.495 |
リ | +0.423 |
hers | +0.414 |
Admiral | +0.404 |
Neg logit contributions | |
\": | -0.501 |
confir | -0.495 |
aints | -0.494 |
Sod | -0.461 |
wcs | -0.456 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
\": | +0.139 |
aints | +0.138 |
confir | +0.135 |
rid | +0.128 |
Sod | +0.127 |
Neg logit contributions | |
collateral | -0.120 |
atari | -0.112 |
リ | -0.095 |
hers | -0.094 |
inert | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
\": | +0.246 |
aints | +0.243 |
confir | +0.239 |
Sod | +0.225 |
rid | +0.225 |
Neg logit contributions | |
collateral | -0.214 |
atari | -0.201 |
リ | -0.170 |
hers | -0.169 |
inert | -0.164 |
Token |
|
Token ID | 198 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
\": | +0.195 |
aints | +0.193 |
confir | +0.187 |
Sod | +0.178 |
rid | +0.176 |
Neg logit contributions | |
collateral | -0.218 |
atari | -0.209 |
リ | -0.180 |
hers | -0.178 |
inert | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
confir | +0.076 |
\": | +0.075 |
aints | +0.075 |
wcs | +0.069 |
jriwal | +0.069 |
Neg logit contributions | |
collateral | -0.076 |
atari | -0.073 |
リ | -0.063 |
hers | -0.062 |
Admiral | -0.060 |
Token | Det |
Token ID | 11242 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
collateral | +0.012 |
atari | +0.011 |
リ | +0.010 |
hers | +0.010 |
Admiral | +0.009 |
Neg logit contributions | |
confir | -0.011 |
\": | -0.011 |
aints | -0.011 |
Sod | -0.010 |
wcs | -0.010 |
Token | Sgt |
Token ID | 22925 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
\": | +0.505 |
confir | +0.493 |
aints | +0.491 |
wcs | +0.464 |
Sod | +0.458 |
Neg logit contributions | |
collateral | -0.499 |
atari | -0.472 |
リ | -0.405 |
hers | -0.400 |
Admiral | -0.395 |
Token | Ronnie |
Token ID | 40892 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
aints | +2.878 |
\": | +2.871 |
confir | +2.788 |
Sod | +2.681 |
rid | +2.654 |
Neg logit contributions | |
collateral | -2.371 |
atari | -2.271 |
リ | -1.913 |
hers | -1.865 |
inert | -1.819 |
Token | Payne |
Token ID | 32788 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
\": | +0.616 |
aints | +0.608 |
confir | +0.603 |
wcs | +0.564 |
rid | +0.562 |
Neg logit contributions | |
collateral | -0.558 |
atari | -0.529 |
リ | -0.450 |
hers | -0.445 |
Admiral | -0.435 |
Token | asked |
Token ID | 1965 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
collateral | +0.276 |
atari | +0.260 |
リ | +0.220 |
hers | +0.218 |
Admiral | +0.216 |
Neg logit contributions | |
\": | -0.299 |
aints | -0.294 |
confir | -0.290 |
wcs | -0.272 |
rid | -0.272 |
Token | anyone |
Token ID | 2687 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
\": | +0.667 |
aints | +0.660 |
confir | +0.648 |
Sod | +0.613 |
rid | +0.612 |
Neg logit contributions | |
collateral | -0.556 |
atari | -0.526 |
リ | -0.443 |
hers | -0.438 |
inert | -0.425 |
Token | with |
Token ID | 351 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
collateral | +0.182 |
atari | +0.168 |
hers | +0.143 |
リ | +0.142 |
inert | +0.140 |
Neg logit contributions | |
\": | -0.211 |
aints | -0.208 |
confir | -0.206 |
rid | -0.195 |
Sod | -0.194 |
Token | Topics |
Token ID | 25902 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
collateral | +0.385 |
atari | +0.375 |
リ | +0.328 |
hers | +0.317 |
Admiral | +0.311 |
Neg logit contributions | |
confir | -0.330 |
\": | -0.325 |
aints | -0.324 |
Sod | -0.299 |
wcs | -0.297 |
Token | : |
Token ID | 25 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
collateral | +0.228 |
atari | +0.212 |
リ | +0.183 |
hers | +0.180 |
Admiral | +0.179 |
Neg logit contributions | |
aints | -0.237 |
\": | -0.234 |
confir | -0.232 |
wcs | -0.217 |
rid | -0.217 |
Token | Hispanic |
Token ID | 16949 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
collateral | +0.183 |
atari | +0.174 |
リ | +0.150 |
hers | +0.148 |
intern | +0.145 |
Neg logit contributions | |
\": | -0.182 |
aints | -0.180 |
confir | -0.175 |
rid | -0.165 |
Sod | -0.164 |
Token | / |
Token ID | 14 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
\": | +0.273 |
aints | +0.270 |
confir | +0.263 |
rid | +0.247 |
Sod | +0.247 |
Neg logit contributions | |
collateral | -0.295 |
atari | -0.281 |
リ | -0.243 |
hers | -0.241 |
Admiral | -0.235 |
Token | Lat |
Token ID | 24220 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
\": | +0.172 |
aints | +0.171 |
confir | +0.168 |
Sod | +0.159 |
jriwal | +0.158 |
Neg logit contributions | |
collateral | -0.139 |
atari | -0.134 |
リ | -0.113 |
hers | -0.110 |
intern | -0.107 |
Token | ino |
Token ID | 2879 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
collateral | +0.329 |
atari | +0.316 |
リ | +0.283 |
hers | +0.274 |
intern | +0.273 |
Neg logit contributions | |
\": | -0.205 |
confir | -0.205 |
aints | -0.204 |
Sod | -0.184 |
wcs | -0.182 |
Token | Vote |
Token ID | 19175 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
\": | +2.142 |
aints | +2.109 |
confir | +2.076 |
Sod | +1.946 |
rid | +1.934 |
Neg logit contributions | |
collateral | -2.558 |
atari | -2.452 |
リ | -2.128 |
hers | -2.097 |
inert | -2.060 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
\": | +0.402 |
aints | +0.396 |
confir | +0.390 |
rid | +0.365 |
wcs | +0.363 |
Neg logit contributions | |
collateral | -0.396 |
atari | -0.379 |
リ | -0.322 |
hers | -0.319 |
Admiral | -0.315 |
Token | Access |
Token ID | 15457 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
\": | +0.027 |
confir | +0.027 |
aints | +0.027 |
Sod | +0.024 |
wcs | +0.024 |
Neg logit contributions | |
collateral | -0.030 |
atari | -0.029 |
リ | -0.025 |
hers | -0.025 |
Admiral | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
collateral | +0.601 |
atari | +0.570 |
リ | +0.489 |
hers | +0.477 |
inert | +0.468 |
Neg logit contributions | |
\": | -0.653 |
aints | -0.646 |
confir | -0.637 |
Sod | -0.598 |
wcs | -0.596 |
Token | medical |
Token ID | 3315 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
\": | +0.267 |
aints | +0.265 |
confir | +0.260 |
Sod | +0.245 |
rid | +0.245 |
Neg logit contributions | |
collateral | -0.226 |
atari | -0.214 |
リ | -0.181 |
hers | -0.178 |
inert | -0.174 |
Token | about |
Token ID | 546 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
\": | +0.355 |
aints | +0.352 |
confir | +0.345 |
Sod | +0.325 |
rid | +0.323 |
Neg logit contributions | |
collateral | -0.347 |
atari | -0.330 |
リ | -0.282 |
hers | -0.278 |
Admiral | -0.271 |
Token | this |
Token ID | 428 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
\": | +0.167 |
aints | +0.165 |
confir | +0.162 |
wcs | +0.153 |
Sod | +0.153 |
Neg logit contributions | |
collateral | -0.136 |
atari | -0.128 |
リ | -0.107 |
hers | -0.107 |
inert | -0.104 |
Token | fish |
Token ID | 5916 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
collateral | +0.060 |
atari | +0.056 |
リ | +0.048 |
hers | +0.047 |
inert | +0.047 |
Neg logit contributions | |
aints | -0.065 |
\": | -0.065 |
confir | -0.064 |
wcs | -0.060 |
rid | -0.060 |
Token | - |
Token ID | 12 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
collateral | +0.018 |
atari | +0.017 |
リ | +0.014 |
hers | +0.014 |
inert | +0.014 |
Neg logit contributions | |
\": | -0.019 |
aints | -0.019 |
confir | -0.019 |
Sod | -0.018 |
wcs | -0.018 |
Token | tra |
Token ID | 9535 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
collateral | +0.034 |
atari | +0.033 |
リ | +0.029 |
hers | +0.028 |
inert | +0.028 |
Neg logit contributions | |
\": | -0.029 |
confir | -0.028 |
aints | -0.028 |
Sod | -0.026 |
wcs | -0.026 |
Token | umat |
Token ID | 27798 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
collateral | +0.367 |
atari | +0.351 |
リ | +0.300 |
hers | +0.295 |
inert | +0.287 |
Neg logit contributions | |
\": | -0.379 |
aints | -0.373 |
confir | -0.372 |
Sod | -0.345 |
rid | -0.342 |
Token | izing |
Token ID | 2890 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
\": | +1.878 |
aints | +1.847 |
confir | +1.797 |
rid | +1.680 |
Sod | +1.678 |
Neg logit contributions | |
collateral | -2.707 |
atari | -2.604 |
リ | -2.286 |
hers | -2.272 |
inert | -2.223 |
Token | f |
Token ID | 277 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
\": | +1.466 |
aints | +1.457 |
confir | +1.428 |
Sod | +1.335 |
rid | +1.335 |
Neg logit contributions | |
collateral | -1.476 |
atari | -1.401 |
リ | -1.199 |
hers | -1.185 |
inert | -1.164 |
Token | auc |
Token ID | 14272 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
\": | +0.057 |
confir | +0.057 |
aints | +0.055 |
Sod | +0.050 |
wcs | +0.049 |
Neg logit contributions | |
collateral | -0.134 |
atari | -0.130 |
リ | -0.116 |
hers | -0.114 |
Admiral | -0.113 |
Token | et |
Token ID | 316 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
\": | +0.662 |
aints | +0.655 |
confir | +0.649 |
Sod | +0.600 |
wcs | +0.596 |
Neg logit contributions | |
collateral | -0.867 |
atari | -0.833 |
リ | -0.727 |
hers | -0.717 |
inert | -0.703 |
Token | . |
Token ID | 13 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
collateral | +0.196 |
atari | +0.185 |
リ | +0.156 |
hers | +0.156 |
inert | +0.153 |
Neg logit contributions | |
\": | -0.209 |
aints | -0.209 |
confir | -0.204 |
wcs | -0.192 |
rid | -0.190 |
Token | website |
Token ID | 3052 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
collateral | +0.295 |
atari | +0.279 |
リ | +0.233 |
hers | +0.229 |
inert | +0.223 |
Neg logit contributions | |
\": | -0.376 |
aints | -0.371 |
confir | -0.365 |
Sod | -0.346 |
rid | -0.345 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
collateral | +0.056 |
atari | +0.053 |
リ | +0.045 |
hers | +0.044 |
inert | +0.043 |
Neg logit contributions | |
\": | -0.065 |
aints | -0.065 |
confir | -0.064 |
Sod | -0.060 |
rid | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
collateral | +0.189 |
atari | +0.181 |
リ | +0.156 |
hers | +0.154 |
Admiral | +0.151 |
Neg logit contributions | |
\": | -0.174 |
aints | -0.172 |
confir | -0.170 |
wcs | -0.158 |
rid | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
collateral | +0.262 |
atari | +0.250 |
リ | +0.215 |
hers | +0.212 |
Admiral | +0.207 |
Neg logit contributions | |
confir | -0.279 |
aints | -0.269 |
\": | -0.268 |
wcs | -0.250 |
jriwal | -0.249 |
Token | M |
Token ID | 44 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
collateral | +0.313 |
atari | +0.302 |
リ | +0.261 |
hers | +0.255 |
Admiral | +0.249 |
Neg logit contributions | |
\": | -0.283 |
confir | -0.282 |
aints | -0.282 |
Sod | -0.261 |
wcs | -0.258 |
Token | ISS |
Token ID | 16744 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
\": | +0.240 |
confir | +0.235 |
aints | +0.234 |
Sod | +0.220 |
wcs | +0.218 |
Neg logit contributions | |
collateral | -0.271 |
atari | -0.263 |
リ | -0.226 |
hers | -0.221 |
inert | -0.217 |
Token | ING |
Token ID | 2751 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
\": | +1.939 |
aints | +1.916 |
confir | +1.875 |
Sod | +1.742 |
rid | +1.738 |
Neg logit contributions | |
collateral | -2.597 |
atari | -2.490 |
リ | -2.182 |
hers | -2.156 |
inert | -2.112 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
\": | +0.080 |
aints | +0.080 |
confir | +0.078 |
wcs | +0.074 |
rid | +0.073 |
Neg logit contributions | |
collateral | -0.078 |
atari | -0.074 |
リ | -0.063 |
hers | -0.063 |
Admiral | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
\": | +0.178 |
aints | +0.176 |
confir | +0.173 |
wcs | +0.163 |
Sod | +0.162 |
Neg logit contributions | |
collateral | -0.178 |
atari | -0.168 |
リ | -0.145 |
hers | -0.143 |
inert | -0.140 |
Token | Y |
Token ID | 56 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
collateral | +0.028 |
atari | +0.027 |
リ | +0.024 |
hers | +0.023 |
Admiral | +0.023 |
Neg logit contributions | |
\": | -0.027 |
aints | -0.026 |
confir | -0.026 |
Sod | -0.024 |
wcs | -0.024 |
Token | EAR |
Token ID | 17133 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
\": | +0.456 |
aints | +0.448 |
confir | +0.445 |
Sod | +0.413 |
wcs | +0.411 |
Neg logit contributions | |
collateral | -0.549 |
atari | -0.528 |
リ | -0.454 |
hers | -0.452 |
inert | -0.446 |
Token | � |
Token ID | 447 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
\": | +0.229 |
aints | +0.228 |
confir | +0.223 |
wcs | +0.210 |
Sod | +0.210 |
Neg logit contributions | |
collateral | -0.227 |
atari | -0.215 |
リ | -0.185 |
hers | -0.182 |
intern | -0.178 |
Token | � |
Token ID | 247 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
\": | +0.355 |
aints | +0.352 |
confir | +0.346 |
Sod | +0.328 |
rid | +0.327 |
Neg logit contributions | |
collateral | -0.272 |
atari | -0.257 |
リ | -0.214 |
hers | -0.211 |
inert | -0.205 |
Token | s |
Token ID | 82 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
\": | +0.125 |
aints | +0.124 |
confir | +0.122 |
wcs | +0.114 |
Sod | +0.113 |
Neg logit contributions | |
collateral | -0.157 |
atari | -0.151 |
リ | -0.132 |
hers | -0.130 |
Admiral | -0.127 |
Token | where |
Token ID | 810 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
\": | +0.132 |
aints | +0.131 |
confir | +0.128 |
wcs | +0.122 |
Sod | +0.121 |
Neg logit contributions | |
collateral | -0.111 |
atari | -0.104 |
リ | -0.088 |
hers | -0.087 |
Admiral | -0.084 |
Token | we |
Token ID | 356 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
\": | +1.078 |
aints | +1.067 |
confir | +1.050 |
Sod | +0.990 |
rid | +0.986 |
Neg logit contributions | |
collateral | -1.008 |
atari | -0.956 |
リ | -0.816 |
hers | -0.805 |
inert | -0.783 |
Token | met |
Token ID | 1138 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
\": | +0.341 |
aints | +0.339 |
confir | +0.332 |
wcs | +0.312 |
Sod | +0.312 |
Neg logit contributions | |
collateral | -0.343 |
atari | -0.326 |
リ | -0.279 |
hers | -0.275 |
intern | -0.270 |
Token | each |
Token ID | 1123 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
\": | +2.373 |
aints | +2.348 |
confir | +2.294 |
Sod | +2.179 |
rid | +2.165 |
Neg logit contributions | |
collateral | -2.124 |
atari | -2.024 |
リ | -1.721 |
hers | -1.685 |
inert | -1.653 |
Token | other |
Token ID | 584 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
\": | +0.731 |
aints | +0.722 |
confir | +0.707 |
Sod | +0.675 |
rid | +0.675 |
Neg logit contributions | |
collateral | -0.505 |
atari | -0.477 |
リ | -0.391 |
hers | -0.384 |
inert | -0.375 |
Token | , |
Token ID | 11 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
\": | +0.057 |
aints | +0.056 |
confir | +0.055 |
Sod | +0.052 |
wcs | +0.052 |
Neg logit contributions | |
collateral | -0.051 |
atari | -0.048 |
リ | -0.041 |
hers | -0.041 |
inert | -0.040 |
Token | after |
Token ID | 706 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
\": | +0.162 |
aints | +0.161 |
confir | +0.158 |
wcs | +0.149 |
Sod | +0.149 |
Neg logit contributions | |
collateral | -0.146 |
atari | -0.138 |
リ | -0.117 |
hers | -0.116 |
inert | -0.113 |
Token | some |
Token ID | 617 |
Feature activation | -6.69e-01 |
Pos logit contributions | |
\": | +0.183 |
aints | +0.181 |
confir | +0.178 |
Sod | +0.168 |
rid | +0.168 |
Neg logit contributions | |
collateral | -0.161 |
atari | -0.152 |
リ | -0.129 |
hers | -0.127 |
inert | -0.124 |
Token | Party |
Token ID | 3615 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
\": | +0.417 |
aints | +0.411 |
confir | +0.401 |
Sod | +0.370 |
rid | +0.368 |
Neg logit contributions | |
collateral | -0.670 |
atari | -0.643 |
リ | -0.570 |
hers | -0.565 |
inert | -0.554 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
\": | +0.280 |
aints | +0.277 |
confir | +0.272 |
Sod | +0.256 |
rid | +0.256 |
Neg logit contributions | |
collateral | -0.267 |
atari | -0.254 |
リ | -0.217 |
hers | -0.214 |
inert | -0.209 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
confir | +0.014 |
\": | +0.014 |
aints | +0.013 |
wcs | +0.013 |
jriwal | +0.013 |
Neg logit contributions | |
collateral | -0.015 |
atari | -0.014 |
リ | -0.012 |
Admiral | -0.012 |
hers | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
collateral | +0.151 |
atari | +0.144 |
リ | +0.124 |
hers | +0.122 |
Admiral | +0.120 |
Neg logit contributions | |
confir | -0.162 |
aints | -0.156 |
\": | -0.155 |
wcs | -0.145 |
jriwal | -0.144 |
Token | Lat |
Token ID | 24220 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
collateral | +0.186 |
atari | +0.181 |
リ | +0.159 |
hers | +0.153 |
Admiral | +0.151 |
Neg logit contributions | |
confir | -0.159 |
\": | -0.156 |
aints | -0.156 |
Sod | -0.143 |
wcs | -0.142 |
Token | ino |
Token ID | 2879 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
collateral | +0.337 |
atari | +0.323 |
リ | +0.290 |
hers | +0.280 |
intern | +0.278 |
Neg logit contributions | |
\": | -0.221 |
confir | -0.217 |
aints | -0.215 |
wcs | -0.197 |
jriwal | -0.197 |
Token | voters |
Token ID | 4446 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
\": | +2.320 |
aints | +2.296 |
confir | +2.255 |
Sod | +2.125 |
rid | +2.118 |
Neg logit contributions | |
collateral | -2.182 |
atari | -2.079 |
リ | -1.772 |
hers | -1.746 |
inert | -1.704 |
Token | have |
Token ID | 423 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
\": | +0.291 |
aints | +0.288 |
confir | +0.281 |
Sod | +0.269 |
rid | +0.268 |
Neg logit contributions | |
collateral | -0.265 |
atari | -0.249 |
リ | -0.212 |
hers | -0.209 |
Admiral | -0.205 |
Token | leaned |
Token ID | 23831 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
\": | +0.022 |
aints | +0.022 |
confir | +0.021 |
rid | +0.020 |
Sod | +0.020 |
Neg logit contributions | |
collateral | -0.024 |
atari | -0.023 |
リ | -0.020 |
hers | -0.020 |
intern | -0.019 |
Token | more |
Token ID | 517 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
collateral | +0.009 |
atari | +0.008 |
hers | +0.007 |
リ | +0.007 |
inert | +0.007 |
Neg logit contributions | |
\": | -0.009 |
aints | -0.009 |
confir | -0.009 |
wcs | -0.008 |
Sod | -0.008 |
Token | towards |
Token ID | 3371 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
\": | +0.010 |
aints | +0.010 |
confir | +0.010 |
Sod | +0.009 |
wcs | +0.009 |
Neg logit contributions | |
collateral | -0.010 |
atari | -0.009 |
hers | -0.008 |
リ | -0.008 |
inert | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
\": | +0.222 |
aints | +0.219 |
confir | +0.215 |
wcs | +0.202 |
Sod | +0.202 |
Neg logit contributions | |
collateral | -0.221 |
atari | -0.208 |
リ | -0.178 |
hers | -0.177 |
inert | -0.174 |
Token | Transport |
Token ID | 19940 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
\": | +0.106 |
aints | +0.104 |
confir | +0.102 |
wcs | +0.096 |
Sod | +0.096 |
Neg logit contributions | |
collateral | -0.099 |
atari | -0.093 |
リ | -0.079 |
hers | -0.078 |
inert | -0.077 |
Token | Department |
Token ID | 2732 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
\": | +0.781 |
aints | +0.772 |
confir | +0.762 |
Sod | +0.726 |
rid | +0.724 |
Neg logit contributions | |
collateral | -0.438 |
atari | -0.407 |
リ | -0.324 |
hers | -0.318 |
inert | -0.308 |
Token | . |
Token ID | 13 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
collateral | +0.478 |
atari | +0.446 |
リ | +0.376 |
hers | +0.372 |
Admiral | +0.366 |
Neg logit contributions | |
\": | -0.559 |
aints | -0.546 |
confir | -0.541 |
wcs | -0.509 |
Sod | -0.508 |
Token | Stre |
Token ID | 9737 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
\": | +0.032 |
confir | +0.031 |
aints | +0.031 |
wcs | +0.029 |
rid | +0.029 |
Neg logit contributions | |
collateral | -0.034 |
atari | -0.032 |
リ | -0.028 |
Admiral | -0.027 |
hers | -0.027 |
Token | ng |
Token ID | 782 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
\": | +0.185 |
aints | +0.181 |
confir | +0.179 |
Sod | +0.165 |
rid | +0.163 |
Neg logit contributions | |
collateral | -0.277 |
atari | -0.266 |
リ | -0.233 |
hers | -0.230 |
inert | -0.227 |
Token | thening |
Token ID | 20563 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
\": | +1.878 |
aints | +1.857 |
confir | +1.811 |
rid | +1.689 |
Sod | +1.682 |
Neg logit contributions | |
collateral | -2.611 |
atari | -2.502 |
リ | -2.202 |
hers | -2.179 |
inert | -2.133 |
Token | rural |
Token ID | 10016 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
\": | +0.075 |
aints | +0.074 |
confir | +0.073 |
wcs | +0.068 |
Sod | +0.068 |
Neg logit contributions | |
collateral | -0.069 |
atari | -0.065 |
リ | -0.055 |
hers | -0.054 |
inert | -0.054 |
Token | transport |
Token ID | 4839 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
collateral | +0.490 |
atari | +0.455 |
リ | +0.389 |
hers | +0.384 |
inert | +0.379 |
Neg logit contributions | |
\": | -0.532 |
aints | -0.524 |
confir | -0.513 |
wcs | -0.489 |
rid | -0.484 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
collateral | +0.122 |
atari | +0.114 |
リ | +0.097 |
hers | +0.096 |
inert | +0.094 |
Neg logit contributions | |
\": | -0.137 |
aints | -0.134 |
confir | -0.132 |
Sod | -0.125 |
wcs | -0.124 |
Token | last |
Token ID | 938 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
collateral | +0.088 |
atari | +0.082 |
リ | +0.071 |
hers | +0.070 |
Admiral | +0.069 |
Neg logit contributions | |
\": | -0.093 |
aints | -0.091 |
confir | -0.089 |
wcs | -0.085 |
rid | -0.084 |
Token | � |
Token ID | 447 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
confir | +0.052 |
\": | +0.052 |
aints | +0.052 |
wcs | +0.048 |
rid | +0.047 |
Neg logit contributions | |
collateral | -0.057 |
atari | -0.054 |
リ | -0.047 |
hers | -0.046 |
Admiral | -0.045 |
Token | � |
Token ID | 251 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
collateral | +0.020 |
atari | +0.019 |
リ | +0.017 |
hers | +0.017 |
inert | +0.016 |
Neg logit contributions | |
\": | -0.017 |
aints | -0.017 |
confir | -0.016 |
wcs | -0.015 |
Sod | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
collateral | +0.152 |
atari | +0.145 |
リ | +0.125 |
hers | +0.124 |
Admiral | +0.122 |
Neg logit contributions | |
\": | -0.146 |
confir | -0.146 |
aints | -0.146 |
wcs | -0.136 |
jriwal | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
confir | +0.237 |
aints | +0.228 |
\": | +0.226 |
wcs | +0.213 |
jriwal | +0.211 |
Neg logit contributions | |
collateral | -0.221 |
atari | -0.212 |
リ | -0.182 |
hers | -0.180 |
Admiral | -0.175 |
Token | C |
Token ID | 34 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
confir | +0.197 |
\": | +0.195 |
aints | +0.195 |
Sod | +0.179 |
wcs | +0.179 |
Neg logit contributions | |
collateral | -0.217 |
atari | -0.209 |
リ | -0.182 |
hers | -0.176 |
Admiral | -0.173 |
Token | ob |
Token ID | 672 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
\": | +0.217 |
aints | +0.214 |
confir | +0.213 |
wcs | +0.195 |
Sod | +0.194 |
Neg logit contributions | |
collateral | -0.322 |
atari | -0.314 |
リ | -0.273 |
hers | -0.270 |
inert | -0.264 |
Token | ain |
Token ID | 391 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
\": | +1.680 |
aints | +1.654 |
confir | +1.570 |
rid | +1.480 |
Sod | +1.469 |
Neg logit contributions | |
collateral | -2.773 |
atari | -2.657 |
リ | -2.361 |
hers | -2.336 |
inert | -2.302 |
Token | says |
Token ID | 1139 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
\": | +1.243 |
aints | +1.232 |
confir | +1.205 |
Sod | +1.127 |
rid | +1.122 |
Neg logit contributions | |
collateral | -1.497 |
atari | -1.432 |
リ | -1.244 |
hers | -1.229 |
inert | -1.205 |
Token | he |
Token ID | 339 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
collateral | +0.503 |
atari | +0.473 |
リ | +0.401 |
hers | +0.399 |
Admiral | +0.386 |
Neg logit contributions | |
\": | -0.584 |
aints | -0.579 |
confir | -0.570 |
wcs | -0.538 |
rid | -0.532 |
Token | listened |
Token ID | 16399 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
\": | +0.473 |
aints | +0.471 |
confir | +0.462 |
Sod | +0.431 |
wcs | +0.429 |
Neg logit contributions | |
collateral | -0.573 |
atari | -0.548 |
リ | -0.476 |
hers | -0.470 |
intern | -0.460 |
Token | to |
Token ID | 284 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
collateral | +0.284 |
atari | +0.267 |
リ | +0.221 |
hers | +0.217 |
inert | +0.210 |
Neg logit contributions | |
\": | -0.418 |
aints | -0.414 |
confir | -0.408 |
Sod | -0.387 |
rid | -0.385 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
\": | +0.049 |
confir | +0.048 |
aints | +0.048 |
wcs | +0.045 |
jriwal | +0.045 |
Neg logit contributions | |
collateral | -0.052 |
atari | -0.048 |
リ | -0.042 |
hers | -0.042 |
inert | -0.041 |
Token | ers |
Token ID | 364 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
\": | +0.683 |
aints | +0.661 |
confir | +0.659 |
wcs | +0.612 |
Sod | +0.605 |
Neg logit contributions | |
collateral | -1.012 |
atari | -0.967 |
リ | -0.850 |
hers | -0.841 |
inert | -0.834 |
Token | we |
Token ID | 356 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
collateral | +0.494 |
atari | +0.463 |
リ | +0.394 |
hers | +0.391 |
inert | +0.382 |
Neg logit contributions | |
\": | -0.529 |
aints | -0.520 |
confir | -0.514 |
wcs | -0.486 |
Sod | -0.485 |
Token | get |
Token ID | 651 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
\": | +0.394 |
aints | +0.391 |
confir | +0.386 |
wcs | +0.363 |
Sod | +0.362 |
Neg logit contributions | |
collateral | -0.368 |
atari | -0.349 |
リ | -0.298 |
hers | -0.291 |
intern | -0.285 |
Token | to |
Token ID | 284 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
\": | +0.191 |
aints | +0.190 |
confir | +0.187 |
wcs | +0.177 |
Sod | +0.177 |
Neg logit contributions | |
collateral | -0.143 |
atari | -0.134 |
リ | -0.112 |
hers | -0.111 |
inert | -0.107 |
Token | feature |
Token ID | 3895 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
\": | +0.086 |
aints | +0.084 |
confir | +0.083 |
wcs | +0.079 |
jriwal | +0.078 |
Neg logit contributions | |
collateral | -0.070 |
atari | -0.065 |
リ | -0.055 |
hers | -0.055 |
intern | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
\": | +2.302 |
aints | +2.278 |
confir | +2.239 |
Sod | +2.110 |
rid | +2.103 |
Neg logit contributions | |
collateral | -2.108 |
atari | -2.003 |
リ | -1.703 |
hers | -1.679 |
inert | -1.637 |
Token | horror |
Token ID | 9961 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
\": | +0.222 |
aints | +0.221 |
confir | +0.218 |
wcs | +0.206 |
jriwal | +0.204 |
Neg logit contributions | |
collateral | -0.188 |
atari | -0.175 |
リ | -0.149 |
hers | -0.149 |
inert | -0.144 |
Token | nights |
Token ID | 12513 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
\": | +0.386 |
aints | +0.381 |
confir | +0.377 |
Sod | +0.352 |
wcs | +0.351 |
Neg logit contributions | |
collateral | -0.427 |
atari | -0.403 |
リ | -0.347 |
hers | -0.345 |
inert | -0.337 |
Token | , |
Token ID | 11 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
\": | +1.289 |
aints | +1.277 |
confir | +1.258 |
Sod | +1.188 |
wcs | +1.184 |
Neg logit contributions | |
collateral | -1.127 |
atari | -1.065 |
リ | -0.903 |
hers | -0.889 |
inert | -0.864 |
Token | so |
Token ID | 523 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
\": | +0.119 |
aints | +0.117 |
confir | +0.116 |
wcs | +0.110 |
Sod | +0.109 |
Neg logit contributions | |
collateral | -0.104 |
atari | -0.098 |
リ | -0.083 |
hers | -0.082 |
inert | -0.080 |
Token | Comp |
Token ID | 3082 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
collateral | +0.472 |
atari | +0.445 |
リ | +0.382 |
hers | +0.382 |
Admiral | +0.377 |
Neg logit contributions | |
\": | -0.506 |
confir | -0.503 |
aints | -0.498 |
wcs | -0.476 |
jriwal | -0.468 |
Token | . |
Token ID | 13 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
collateral | +0.307 |
atari | +0.290 |
リ | +0.241 |
hers | +0.238 |
Admiral | +0.232 |
Neg logit contributions | |
\": | -0.408 |
aints | -0.405 |
confir | -0.401 |
wcs | -0.379 |
rid | -0.376 |
Token | Rating |
Token ID | 12028 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
\": | +0.063 |
aints | +0.063 |
confir | +0.063 |
wcs | +0.059 |
jriwal | +0.059 |
Neg logit contributions | |
collateral | -0.059 |
atari | -0.055 |
リ | -0.047 |
hers | -0.047 |
Admiral | -0.046 |
Token | 247 |
Token ID | 30179 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
\": | +0.476 |
aints | +0.469 |
confir | +0.465 |
wcs | +0.438 |
jriwal | +0.435 |
Neg logit contributions | |
collateral | -0.433 |
atari | -0.408 |
リ | -0.345 |
hers | -0.343 |
Admiral | -0.339 |
Token | ESPN |
Token ID | 10409 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
\": | +0.958 |
aints | +0.946 |
confir | +0.932 |
wcs | +0.878 |
Sod | +0.876 |
Neg logit contributions | |
collateral | -0.871 |
atari | -0.823 |
リ | -0.704 |
hers | -0.693 |
Admiral | -0.678 |
Token | Rivals |
Token ID | 42307 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
\": | +0.531 |
aints | +0.525 |
confir | +0.516 |
Sod | +0.487 |
wcs | +0.487 |
Neg logit contributions | |
collateral | -0.467 |
atari | -0.443 |
リ | -0.375 |
hers | -0.370 |
inert | -0.360 |
Token | Scout |
Token ID | 22529 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
\": | +2.434 |
aints | +2.415 |
confir | +2.369 |
Sod | +2.252 |
rid | +2.246 |
Neg logit contributions | |
collateral | -1.946 |
atari | -1.853 |
リ | -1.550 |
hers | -1.522 |
inert | -1.483 |
Token | Others |
Token ID | 12691 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
collateral | +0.012 |
atari | +0.011 |
リ | +0.010 |
hers | +0.009 |
Admiral | +0.009 |
Neg logit contributions | |
\": | -0.014 |
aints | -0.014 |
confir | -0.014 |
wcs | -0.013 |
Sod | -0.013 |
Token | Marvin |
Token ID | 35105 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
\": | +0.322 |
aints | +0.318 |
confir | +0.313 |
wcs | +0.296 |
rid | +0.294 |
Neg logit contributions | |
collateral | -0.291 |
atari | -0.275 |
リ | -0.232 |
hers | -0.231 |
Admiral | -0.227 |
Token | Wilson |
Token ID | 8127 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
\": | +0.799 |
aints | +0.792 |
confir | +0.779 |
Sod | +0.741 |
rid | +0.739 |
Neg logit contributions | |
collateral | -0.548 |
atari | -0.517 |
リ | -0.425 |
hers | -0.417 |
inert | -0.405 |
Token | DT |
Token ID | 24311 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
\": | +0.576 |
aints | +0.568 |
confir | +0.560 |
wcs | +0.528 |
rid | +0.526 |
Neg logit contributions | |
collateral | -0.523 |
atari | -0.495 |
リ | -0.420 |
hers | -0.415 |
Admiral | -0.408 |
Token | stories |
Token ID | 3923 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
\": | +0.827 |
aints | +0.818 |
confir | +0.803 |
Sod | +0.753 |
wcs | +0.751 |
Neg logit contributions | |
collateral | -0.852 |
atari | -0.813 |
リ | -0.699 |
hers | -0.688 |
inert | -0.673 |
Token | : |
Token ID | 25 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
\": | +0.491 |
aints | +0.490 |
confir | +0.478 |
wcs | +0.454 |
Sod | +0.451 |
Neg logit contributions | |
collateral | -0.452 |
atari | -0.424 |
リ | -0.359 |
hers | -0.356 |
intern | -0.350 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
\": | +0.022 |
aints | +0.022 |
confir | +0.021 |
Sod | +0.020 |
rid | +0.020 |
Neg logit contributions | |
collateral | -0.024 |
atari | -0.023 |
リ | -0.020 |
hers | -0.020 |
inert | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
collateral | +0.020 |
atari | +0.019 |
リ | +0.016 |
hers | +0.016 |
Admiral | +0.016 |
Neg logit contributions | |
confir | -0.020 |
aints | -0.020 |
\": | -0.020 |
wcs | -0.018 |
jriwal | -0.018 |
Token | Gen |
Token ID | 13746 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
collateral | +0.067 |
atari | +0.065 |
リ | +0.056 |
hers | +0.055 |
Admiral | +0.054 |
Neg logit contributions | |
\": | -0.061 |
aints | -0.061 |
confir | -0.061 |
Sod | -0.056 |
wcs | -0.055 |
Token | isc |
Token ID | 2304 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
\": | +0.066 |
aints | +0.065 |
confir | +0.065 |
wcs | +0.061 |
Sod | +0.060 |
Neg logit contributions | |
collateral | -0.066 |
atari | -0.063 |
リ | -0.054 |
hers | -0.053 |
Admiral | -0.052 |
Token | ale |
Token ID | 1000 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
\": | +1.961 |
aints | +1.940 |
confir | +1.895 |
rid | +1.777 |
Sod | +1.774 |
Neg logit contributions | |
collateral | -2.330 |
atari | -2.234 |
リ | -1.941 |
hers | -1.914 |
inert | -1.879 |
Token | : |
Token ID | 25 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
collateral | +0.083 |
atari | +0.079 |
リ | +0.067 |
hers | +0.067 |
Admiral | +0.066 |
Neg logit contributions | |
\": | -0.082 |
aints | -0.082 |
confir | -0.080 |
wcs | -0.075 |
Sod | -0.075 |
Token | A |
Token ID | 317 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
collateral | +0.188 |
atari | +0.179 |
リ | +0.154 |
hers | +0.151 |
Admiral | +0.150 |
Neg logit contributions | |
\": | -0.186 |
aints | -0.185 |
confir | -0.182 |
wcs | -0.170 |
rid | -0.169 |
Token | multi |
Token ID | 5021 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
collateral | +0.015 |
atari | +0.014 |
リ | +0.012 |
hers | +0.012 |
Admiral | +0.012 |
Neg logit contributions | |
\": | -0.016 |
aints | -0.016 |
confir | -0.015 |
wcs | -0.014 |
Sod | -0.014 |
Token | functional |
Token ID | 10345 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
\": | +0.650 |
aints | +0.641 |
confir | +0.626 |
Sod | +0.586 |
rid | +0.585 |
Neg logit contributions | |
collateral | -0.842 |
atari | -0.806 |
リ | -0.707 |
hers | -0.700 |
inert | -0.684 |
Token | has |
Token ID | 468 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
\": | +0.199 |
aints | +0.196 |
confir | +0.195 |
Sod | +0.180 |
rid | +0.180 |
Neg logit contributions | |
collateral | -0.218 |
atari | -0.204 |
リ | -0.176 |
hers | -0.175 |
inert | -0.173 |
Token | also |
Token ID | 635 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
\": | +0.311 |
aints | +0.308 |
confir | +0.302 |
Sod | +0.282 |
rid | +0.282 |
Neg logit contributions | |
collateral | -0.296 |
atari | -0.278 |
リ | -0.236 |
hers | -0.236 |
inert | -0.230 |
Token | been |
Token ID | 587 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
collateral | +0.164 |
atari | +0.153 |
hers | +0.131 |
リ | +0.131 |
inert | +0.128 |
Neg logit contributions | |
\": | -0.165 |
aints | -0.164 |
confir | -0.161 |
Sod | -0.150 |
rid | -0.150 |
Token | a |
Token ID | 257 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
\": | +0.363 |
aints | +0.359 |
confir | +0.352 |
Sod | +0.331 |
rid | +0.330 |
Neg logit contributions | |
collateral | -0.348 |
atari | -0.331 |
リ | -0.283 |
hers | -0.279 |
inert | -0.272 |
Token | major |
Token ID | 1688 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
collateral | +0.080 |
atari | +0.075 |
リ | +0.065 |
hers | +0.064 |
inert | +0.063 |
Neg logit contributions | |
\": | -0.080 |
aints | -0.079 |
confir | -0.077 |
Sod | -0.072 |
wcs | -0.072 |
Token | feature |
Token ID | 3895 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
collateral | +0.219 |
atari | +0.206 |
リ | +0.178 |
hers | +0.176 |
inert | +0.173 |
Neg logit contributions | |
\": | -0.206 |
aints | -0.203 |
confir | -0.200 |
Sod | -0.187 |
wcs | -0.186 |
Token | of |
Token ID | 286 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
\": | +1.904 |
aints | +1.884 |
confir | +1.840 |
Sod | +1.723 |
rid | +1.721 |
Neg logit contributions | |
collateral | -2.327 |
atari | -2.239 |
リ | -1.948 |
hers | -1.919 |
inert | -1.879 |
Token | politics |
Token ID | 4819 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
\": | +0.312 |
aints | +0.310 |
confir | +0.305 |
rid | +0.288 |
wcs | +0.287 |
Neg logit contributions | |
collateral | -0.234 |
atari | -0.220 |
リ | -0.183 |
hers | -0.181 |
inert | -0.176 |
Token | , |
Token ID | 11 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
\": | +0.736 |
aints | +0.728 |
confir | +0.720 |
Sod | +0.677 |
rid | +0.674 |
Neg logit contributions | |
collateral | -0.658 |
atari | -0.620 |
リ | -0.522 |
hers | -0.519 |
inert | -0.507 |
Token | going |
Token ID | 1016 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
\": | +0.107 |
aints | +0.105 |
confir | +0.104 |
rid | +0.098 |
Sod | +0.098 |
Neg logit contributions | |
collateral | -0.095 |
atari | -0.088 |
リ | -0.075 |
hers | -0.075 |
inert | -0.073 |
Token | as |
Token ID | 355 |
Feature activation | -7.81e-02 |
Pos logit contributions | |
\": | +0.612 |
aints | +0.601 |
confir | +0.588 |
Sod | +0.554 |
wcs | +0.551 |
Neg logit contributions | |
collateral | -0.553 |
atari | -0.513 |
リ | -0.441 |
hers | -0.438 |
inert | -0.430 |
Token | / |
Token ID | 14 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
collateral | +0.839 |
atari | +0.798 |
リ | +0.690 |
hers | +0.684 |
inert | +0.674 |
Neg logit contributions | |
\": | -0.743 |
aints | -0.732 |
confir | -0.717 |
Sod | -0.669 |
rid | -0.669 |
Token | kg |
Token ID | 10025 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
collateral | +0.104 |
atari | +0.100 |
リ | +0.086 |
hers | +0.085 |
inert | +0.083 |
Neg logit contributions | |
\": | -0.099 |
aints | -0.098 |
confir | -0.096 |
Sod | -0.090 |
rid | -0.090 |
Token | ), |
Token ID | 828 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
collateral | +0.677 |
atari | +0.643 |
リ | +0.553 |
hers | +0.548 |
inert | +0.539 |
Neg logit contributions | |
\": | -0.646 |
aints | -0.636 |
confir | -0.623 |
Sod | -0.582 |
wcs | -0.581 |
Token | a |
Token ID | 257 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
\": | +0.230 |
aints | +0.227 |
confir | +0.221 |
Sod | +0.208 |
rid | +0.208 |
Neg logit contributions | |
collateral | -0.237 |
atari | -0.223 |
リ | -0.192 |
hers | -0.190 |
inert | -0.187 |
Token | selective |
Token ID | 21792 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
\": | +0.037 |
aints | +0.037 |
confir | +0.036 |
Sod | +0.034 |
rid | +0.034 |
Neg logit contributions | |
collateral | -0.033 |
atari | -0.031 |
リ | -0.026 |
hers | -0.026 |
inert | -0.026 |
Token | serotonin |
Token ID | 32236 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
\": | +0.664 |
aints | +0.657 |
confir | +0.642 |
Sod | +0.603 |
rid | +0.602 |
Neg logit contributions | |
collateral | -0.666 |
atari | -0.632 |
リ | -0.543 |
hers | -0.536 |
inert | -0.526 |
Token | re |
Token ID | 302 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
\": | +2.264 |
aints | +2.231 |
confir | +2.203 |
Sod | +2.076 |
rid | +2.070 |
Neg logit contributions | |
collateral | -1.960 |
atari | -1.861 |
リ | -1.571 |
hers | -1.555 |
inert | -1.507 |
Token | upt |
Token ID | 37623 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
\": | +0.276 |
aints | +0.272 |
confir | +0.267 |
Sod | +0.248 |
wcs | +0.246 |
Neg logit contributions | |
collateral | -0.381 |
atari | -0.366 |
リ | -0.321 |
hers | -0.317 |
inert | -0.311 |
Token | ake |
Token ID | 539 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
\": | +0.224 |
aints | +0.221 |
confir | +0.220 |
Sod | +0.206 |
wcs | +0.206 |
Neg logit contributions | |
collateral | -0.180 |
atari | -0.173 |
リ | -0.143 |
hers | -0.141 |
inert | -0.137 |
Token | inhibitor |
Token ID | 41704 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
\": | +0.189 |
aints | +0.187 |
confir | +0.184 |
Sod | +0.174 |
wcs | +0.174 |
Neg logit contributions | |
collateral | -0.154 |
atari | -0.146 |
リ | -0.123 |
hers | -0.121 |
inert | -0.118 |
Token | ( |
Token ID | 357 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
collateral | +0.546 |
atari | +0.511 |
リ | +0.429 |
hers | +0.427 |
inert | +0.421 |
Neg logit contributions | |
\": | -0.640 |
aints | -0.630 |
confir | -0.614 |
wcs | -0.580 |
rid | -0.580 |
Token | * |
Token ID | 9 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
confir | +0.188 |
\": | +0.182 |
aints | +0.182 |
wcs | +0.169 |
jriwal | +0.168 |
Neg logit contributions | |
collateral | -0.214 |
atari | -0.207 |
リ | -0.180 |
hers | -0.176 |
Admiral | -0.173 |
Token | 3 |
Token ID | 513 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
\": | +0.495 |
aints | +0.491 |
confir | +0.478 |
Sod | +0.449 |
rid | +0.446 |
Neg logit contributions | |
collateral | -0.606 |
atari | -0.581 |
リ | -0.506 |
hers | -0.499 |
inert | -0.489 |
Token | * |
Token ID | 9 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
confir | +0.314 |
aints | +0.303 |
\": | +0.302 |
wcs | +0.280 |
jriwal | +0.280 |
Neg logit contributions | |
collateral | -0.355 |
atari | -0.343 |
リ | -0.299 |
hers | -0.292 |
Admiral | -0.286 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
\": | +0.590 |
aints | +0.583 |
confir | +0.571 |
Sod | +0.534 |
rid | +0.532 |
Neg logit contributions | |
collateral | -0.698 |
atari | -0.668 |
リ | -0.581 |
hers | -0.573 |
inert | -0.561 |
Token | * |
Token ID | 9 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
confir | +0.384 |
aints | +0.372 |
\": | +0.372 |
wcs | +0.345 |
jriwal | +0.344 |
Neg logit contributions | |
collateral | -0.438 |
atari | -0.424 |
リ | -0.369 |
hers | -0.361 |
Admiral | -0.355 |
Token | LSU |
Token ID | 28078 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
\": | +0.745 |
aints | +0.736 |
confir | +0.728 |
wcs | +0.681 |
rid | +0.679 |
Neg logit contributions | |
collateral | -0.708 |
atari | -0.672 |
リ | -0.573 |
hers | -0.567 |
Admiral | -0.555 |
Token | ( |
Token ID | 357 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
\": | +2.222 |
aints | +2.202 |
confir | +2.151 |
Sod | +2.051 |
rid | +2.038 |
Neg logit contributions | |
collateral | -1.953 |
atari | -1.860 |
リ | -1.575 |
hers | -1.550 |
inert | -1.511 |
Token | commit |
Token ID | 41509 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
\": | +0.161 |
aints | +0.159 |
confir | +0.156 |
Sod | +0.146 |
rid | +0.145 |
Neg logit contributions | |
collateral | -0.186 |
atari | -0.178 |
リ | -0.154 |
hers | -0.152 |
inert | -0.149 |
Token | ) |
Token ID | 8 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
collateral | +0.354 |
atari | +0.337 |
リ | +0.289 |
hers | +0.285 |
inert | +0.278 |
Neg logit contributions | |
\": | -0.355 |
aints | -0.352 |
confir | -0.346 |
Sod | -0.325 |
rid | -0.324 |
Token | B |
Token ID | 347 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
collateral | +0.023 |
atari | +0.021 |
リ | +0.018 |
hers | +0.018 |
Admiral | +0.018 |
Neg logit contributions | |
\": | -0.026 |
aints | -0.026 |
confir | -0.026 |
wcs | -0.024 |
rid | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
\": | +0.662 |
aints | +0.653 |
confir | +0.649 |
Sod | +0.605 |
wcs | +0.604 |
Neg logit contributions | |
collateral | -0.646 |
atari | -0.619 |
リ | -0.526 |
hers | -0.517 |
inert | -0.506 |
Token | . |
Token ID | 13 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
collateral | +0.258 |
atari | +0.242 |
リ | +0.205 |
hers | +0.204 |
Admiral | +0.198 |
Neg logit contributions | |
\": | -0.299 |
aints | -0.295 |
confir | -0.290 |
wcs | -0.273 |
Sod | -0.273 |
Token |
|
Token ID | 198 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
\": | +0.253 |
aints | +0.248 |
confir | +0.246 |
wcs | +0.229 |
rid | +0.228 |
Neg logit contributions | |
collateral | -0.267 |
atari | -0.256 |
リ | -0.220 |
hers | -0.217 |
Admiral | -0.213 |
Token |
|
Token ID | 198 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
confir | +0.450 |
\": | +0.443 |
aints | +0.442 |
wcs | +0.409 |
Sod | +0.406 |
Neg logit contributions | |
collateral | -0.451 |
atari | -0.432 |
リ | -0.372 |
hers | -0.367 |
Admiral | -0.359 |
Token | In |
Token ID | 818 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
\": | +0.368 |
confir | +0.366 |
aints | +0.363 |
Sod | +0.336 |
wcs | +0.336 |
Neg logit contributions | |
collateral | -0.410 |
atari | -0.397 |
リ | -0.344 |
hers | -0.336 |
Admiral | -0.329 |
Token | Car |
Token ID | 1879 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
\": | +0.205 |
aints | +0.202 |
confir | +0.199 |
wcs | +0.189 |
rid | +0.186 |
Neg logit contributions | |
collateral | -0.182 |
atari | -0.172 |
リ | -0.147 |
hers | -0.145 |
Admiral | -0.142 |
Token | ros |
Token ID | 4951 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
collateral | +0.089 |
atari | +0.086 |
リ | +0.073 |
hers | +0.073 |
Admiral | +0.072 |
Neg logit contributions | |
\": | -0.072 |
confir | -0.071 |
aints | -0.070 |
wcs | -0.064 |
Sod | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
\": | +2.037 |
aints | +2.011 |
confir | +1.973 |
wcs | +1.849 |
Sod | +1.847 |
Neg logit contributions | |
collateral | -2.144 |
atari | -2.048 |
リ | -1.760 |
hers | -1.736 |
Admiral | -1.698 |
Token | north |
Token ID | 5093 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
\": | +0.234 |
aints | +0.230 |
confir | +0.225 |
wcs | +0.215 |
rid | +0.213 |
Neg logit contributions | |
collateral | -0.202 |
atari | -0.190 |
リ | -0.160 |
hers | -0.159 |
Admiral | -0.156 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
collateral | +0.157 |
atari | +0.150 |
リ | +0.130 |
hers | +0.129 |
inert | +0.126 |
Neg logit contributions | |
\": | -0.130 |
aints | -0.129 |
confir | -0.126 |
Sod | -0.118 |
rid | -0.117 |
Token | Nice |
Token ID | 18460 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
collateral | +0.133 |
atari | +0.126 |
リ | +0.107 |
hers | +0.107 |
Admiral | +0.104 |
Neg logit contributions | |
\": | -0.140 |
aints | -0.138 |
confir | -0.136 |
wcs | -0.129 |
rid | -0.127 |
Token | on |
Token ID | 319 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
collateral | +0.498 |
atari | +0.473 |
リ | +0.403 |
hers | +0.397 |
Admiral | +0.388 |
Neg logit contributions | |
\": | -0.523 |
aints | -0.515 |
confir | -0.505 |
Sod | -0.475 |
wcs | -0.474 |
Token | a |
Token ID | 257 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
\": | +0.948 |
aints | +0.938 |
confir | +0.922 |
Sod | +0.871 |
rid | +0.869 |
Neg logit contributions | |
collateral | -0.799 |
atari | -0.757 |
リ | -0.639 |
hers | -0.629 |
inert | -0.613 |
Token | compromise |
Token ID | 13110 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
\": | +0.299 |
aints | +0.296 |
confir | +0.290 |
Sod | +0.272 |
rid | +0.272 |
Neg logit contributions | |
collateral | -0.279 |
atari | -0.264 |
リ | -0.225 |
hers | -0.222 |
inert | -0.216 |
Token | version |
Token ID | 2196 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
\": | +0.841 |
aints | +0.833 |
confir | +0.813 |
Sod | +0.764 |
rid | +0.763 |
Neg logit contributions | |
collateral | -0.819 |
atari | -0.772 |
リ | -0.662 |
hers | -0.656 |
inert | -0.640 |
Token | of |
Token ID | 286 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
\": | +0.837 |
aints | +0.827 |
confir | +0.808 |
Sod | +0.757 |
rid | +0.753 |
Neg logit contributions | |
collateral | -0.957 |
atari | -0.909 |
リ | -0.791 |
hers | -0.783 |
inert | -0.765 |
Token | a |
Token ID | 257 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
\": | +0.283 |
aints | +0.280 |
confir | +0.276 |
rid | +0.260 |
Sod | +0.260 |
Neg logit contributions | |
collateral | -0.209 |
atari | -0.197 |
リ | -0.164 |
hers | -0.163 |
Admiral | -0.156 |
Token | bill |
Token ID | 2855 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
\": | +0.160 |
aints | +0.158 |
confir | +0.155 |
Sod | +0.145 |
rid | +0.145 |
Neg logit contributions | |
collateral | -0.149 |
atari | -0.141 |
リ | -0.120 |
hers | -0.119 |
inert | -0.115 |
Token | originally |
Token ID | 6198 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
\": | +2.014 |
aints | +1.990 |
confir | +1.957 |
Sod | +1.848 |
rid | +1.840 |
Neg logit contributions | |
collateral | -2.055 |
atari | -1.983 |
リ | -1.692 |
hers | -1.657 |
inert | -1.625 |
Token | introduced |
Token ID | 5495 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
collateral | +0.224 |
atari | +0.210 |
リ | +0.181 |
hers | +0.180 |
inert | +0.175 |
Neg logit contributions | |
\": | -0.233 |
aints | -0.231 |
confir | -0.226 |
Sod | -0.212 |
rid | -0.211 |
Token | by |
Token ID | 416 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
\": | +1.102 |
aints | +1.090 |
confir | +1.068 |
Sod | +1.005 |
rid | +1.001 |
Neg logit contributions | |
collateral | -1.127 |
atari | -1.076 |
リ | -0.924 |
hers | -0.911 |
inert | -0.890 |
Token | Evans |
Token ID | 13922 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
\": | +0.384 |
aints | +0.380 |
confir | +0.374 |
wcs | +0.351 |
rid | +0.351 |
Neg logit contributions | |
collateral | -0.341 |
atari | -0.322 |
リ | -0.274 |
hers | -0.272 |
Admiral | -0.265 |
Token | that |
Token ID | 326 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
\": | +0.389 |
aints | +0.386 |
confir | +0.379 |
Sod | +0.357 |
rid | +0.355 |
Neg logit contributions | |
collateral | -0.362 |
atari | -0.344 |
リ | -0.294 |
hers | -0.290 |
inert | -0.282 |
Token | featuring |
Token ID | 9593 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
\": | +0.051 |
aints | +0.051 |
confir | +0.050 |
wcs | +0.047 |
rid | +0.047 |
Neg logit contributions | |
collateral | -0.048 |
atari | -0.045 |
リ | -0.038 |
hers | -0.038 |
Admiral | -0.037 |
Token | Tone |
Token ID | 45362 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
\": | +0.807 |
aints | +0.799 |
confir | +0.785 |
Sod | +0.739 |
rid | +0.738 |
Neg logit contributions | |
collateral | -0.743 |
atari | -0.706 |
リ | -0.601 |
hers | -0.592 |
inert | -0.578 |
Token | controls |
Token ID | 6973 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
collateral | +0.462 |
atari | +0.444 |
リ | +0.383 |
hers | +0.375 |
Admiral | +0.371 |
Neg logit contributions | |
\": | -0.430 |
aints | -0.426 |
confir | -0.421 |
wcs | -0.388 |
jriwal | -0.387 |
Token | , |
Token ID | 11 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
collateral | +0.053 |
atari | +0.050 |
リ | +0.042 |
hers | +0.042 |
inert | +0.041 |
Neg logit contributions | |
\": | -0.059 |
aints | -0.059 |
confir | -0.058 |
rid | -0.054 |
Sod | -0.054 |
Token | Comp |
Token ID | 3082 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
\": | +0.568 |
aints | +0.561 |
confir | +0.551 |
Sod | +0.518 |
rid | +0.518 |
Neg logit contributions | |
collateral | -0.530 |
atari | -0.504 |
リ | -0.429 |
hers | -0.424 |
inert | -0.414 |
Token | ression |
Token ID | 2234 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
collateral | +0.472 |
atari | +0.454 |
リ | +0.396 |
hers | +0.392 |
Admiral | +0.384 |
Neg logit contributions | |
\": | -0.367 |
aints | -0.359 |
confir | -0.356 |
Sod | -0.329 |
wcs | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
\": | +2.071 |
aints | +2.046 |
confir | +2.009 |
Sod | +1.886 |
rid | +1.884 |
Neg logit contributions | |
collateral | -2.027 |
atari | -1.930 |
リ | -1.650 |
hers | -1.628 |
inert | -1.592 |
Token | and |
Token ID | 290 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
\": | +0.383 |
aints | +0.379 |
confir | +0.373 |
wcs | +0.349 |
rid | +0.349 |
Neg logit contributions | |
collateral | -0.368 |
atari | -0.349 |
リ | -0.298 |
hers | -0.294 |
inert | -0.288 |
Token | Analog |
Token ID | 50088 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
\": | +0.415 |
aints | +0.410 |
confir | +0.402 |
wcs | +0.377 |
rid | +0.377 |
Neg logit contributions | |
collateral | -0.406 |
atari | -0.385 |
リ | -0.330 |
hers | -0.326 |
inert | -0.319 |
Token | Tape |
Token ID | 40849 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
collateral | +0.058 |
atari | +0.055 |
リ | +0.047 |
hers | +0.046 |
inert | +0.045 |
Neg logit contributions | |
\": | -0.060 |
aints | -0.059 |
confir | -0.058 |
wcs | -0.054 |
Sod | -0.054 |
Token | S |
Token ID | 311 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
\": | +0.166 |
aints | +0.163 |
confir | +0.161 |
wcs | +0.151 |
Sod | +0.151 |
Neg logit contributions | |
collateral | -0.162 |
atari | -0.153 |
リ | -0.131 |
hers | -0.129 |
inert | -0.127 |
Token | to |
Token ID | 284 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
\": | +0.347 |
aints | +0.345 |
confir | +0.338 |
Sod | +0.320 |
rid | +0.318 |
Neg logit contributions | |
collateral | -0.278 |
atari | -0.262 |
リ | -0.220 |
hers | -0.217 |
inert | -0.211 |
Token | force |
Token ID | 2700 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
collateral | +0.074 |
atari | +0.070 |
リ | +0.059 |
hers | +0.059 |
inert | +0.057 |
Neg logit contributions | |
\": | -0.083 |
aints | -0.082 |
confir | -0.080 |
Sod | -0.077 |
wcs | -0.076 |
Token | back |
Token ID | 736 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
\": | +0.626 |
aints | +0.620 |
confir | +0.610 |
wcs | +0.576 |
Sod | +0.574 |
Neg logit contributions | |
collateral | -0.545 |
atari | -0.511 |
リ | -0.436 |
hers | -0.430 |
inert | -0.422 |
Token | this |
Token ID | 428 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
\": | +0.053 |
aints | +0.052 |
confir | +0.052 |
wcs | +0.049 |
Sod | +0.048 |
Neg logit contributions | |
collateral | -0.044 |
atari | -0.041 |
リ | -0.035 |
hers | -0.034 |
inert | -0.034 |
Token | unwelcome |
Token ID | 47207 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
collateral | +0.042 |
atari | +0.039 |
リ | +0.034 |
hers | +0.033 |
inert | +0.033 |
Neg logit contributions | |
\": | -0.043 |
aints | -0.043 |
confir | -0.042 |
wcs | -0.040 |
Sod | -0.039 |
Token | intrusion |
Token ID | 34396 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
\": | +0.656 |
aints | +0.649 |
confir | +0.638 |
wcs | +0.599 |
Sod | +0.597 |
Neg logit contributions | |
collateral | -0.608 |
atari | -0.571 |
リ | -0.488 |
hers | -0.481 |
inert | -0.475 |
Token | : |
Token ID | 25 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
\": | +1.910 |
aints | +1.890 |
confir | +1.849 |
Sod | +1.738 |
rid | +1.733 |
Neg logit contributions | |
collateral | -2.144 |
atari | -2.057 |
リ | -1.776 |
hers | -1.752 |
inert | -1.711 |
Token | from |
Token ID | 422 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
\": | +0.176 |
aints | +0.174 |
confir | +0.171 |
wcs | +0.162 |
Sod | +0.162 |
Neg logit contributions | |
collateral | -0.145 |
atari | -0.137 |
リ | -0.116 |
hers | -0.114 |
inert | -0.112 |
Token | id |
Token ID | 4686 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
\": | +0.200 |
aints | +0.198 |
confir | +0.195 |
wcs | +0.185 |
Sod | +0.183 |
Neg logit contributions | |
collateral | -0.165 |
atari | -0.154 |
リ | -0.131 |
hers | -0.129 |
inert | -0.127 |
Token | to |
Token ID | 284 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
\": | +0.176 |
aints | +0.174 |
confir | +0.171 |
Sod | +0.159 |
wcs | +0.159 |
Neg logit contributions | |
collateral | -0.220 |
atari | -0.210 |
リ | -0.184 |
hers | -0.181 |
inert | -0.178 |
Token | ego |
Token ID | 19225 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
\": | +0.168 |
aints | +0.167 |
confir | +0.163 |
wcs | +0.153 |
Sod | +0.153 |
Neg logit contributions | |
collateral | -0.162 |
atari | -0.153 |
リ | -0.131 |
hers | -0.130 |
inert | -0.127 |
Token | than |
Token ID | 621 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
collateral | +0.010 |
atari | +0.009 |
リ | +0.008 |
hers | +0.008 |
inert | +0.008 |
Neg logit contributions | |
\": | -0.012 |
aints | -0.012 |
confir | -0.011 |
Sod | -0.011 |
rid | -0.011 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
collateral | +0.529 |
atari | +0.504 |
リ | +0.427 |
hers | +0.420 |
inert | +0.410 |
Neg logit contributions | |
\": | -0.599 |
aints | -0.592 |
confir | -0.582 |
Sod | -0.550 |
rid | -0.548 |
Token | years |
Token ID | 812 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
collateral | +0.082 |
atari | +0.079 |
リ | +0.067 |
hers | +0.067 |
inert | +0.065 |
Neg logit contributions | |
\": | -0.077 |
aints | -0.076 |
confir | -0.074 |
Sod | -0.070 |
rid | -0.069 |
Token | in |
Token ID | 287 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
\": | +0.088 |
aints | +0.087 |
confir | +0.085 |
Sod | +0.080 |
rid | +0.080 |
Neg logit contributions | |
collateral | -0.094 |
atari | -0.090 |
リ | -0.077 |
hers | -0.076 |
inert | -0.074 |
Token | prison |
Token ID | 3770 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
collateral | +0.159 |
atari | +0.149 |
リ | +0.127 |
hers | +0.125 |
inert | +0.122 |
Neg logit contributions | |
\": | -0.184 |
aints | -0.182 |
confir | -0.179 |
Sod | -0.169 |
rid | -0.168 |
Token | MORE |
Token ID | 12011 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
\": | +0.223 |
aints | +0.220 |
confir | +0.217 |
wcs | +0.204 |
rid | +0.204 |
Neg logit contributions | |
collateral | -0.197 |
atari | -0.185 |
リ | -0.157 |
hers | -0.155 |
Admiral | -0.153 |
Token | and |
Token ID | 290 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
\": | +2.107 |
aints | +2.086 |
confir | +2.047 |
Sod | +1.931 |
rid | +1.925 |
Neg logit contributions | |
collateral | -1.955 |
atari | -1.861 |
リ | -1.584 |
hers | -1.560 |
inert | -1.522 |
Token | tick |
Token ID | 4378 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
\": | +0.180 |
aints | +0.178 |
confir | +0.174 |
wcs | +0.165 |
Sod | +0.165 |
Neg logit contributions | |
collateral | -0.153 |
atari | -0.144 |
hers | -0.122 |
リ | -0.121 |
Admiral | -0.118 |
Token | ed |
Token ID | 276 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
collateral | +0.676 |
atari | +0.638 |
リ | +0.537 |
hers | +0.535 |
inert | +0.518 |
Neg logit contributions | |
\": | -0.830 |
aints | -0.818 |
confir | -0.806 |
wcs | -0.764 |
Sod | -0.759 |
Token | through |
Token ID | 832 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
\": | +0.237 |
aints | +0.234 |
confir | +0.232 |
wcs | +0.221 |
Sod | +0.220 |
Neg logit contributions | |
collateral | -0.139 |
atari | -0.130 |
hers | -0.104 |
リ | -0.104 |
inert | -0.100 |
Token | her |
Token ID | 607 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
collateral | +0.387 |
atari | +0.360 |
hers | +0.305 |
リ | +0.302 |
inert | +0.292 |
Neg logit contributions | |
\": | -0.485 |
aints | -0.478 |
confir | -0.470 |
wcs | -0.445 |
Sod | -0.444 |
Token | than |
Token ID | 621 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
\": | +0.669 |
aints | +0.662 |
confir | +0.650 |
Sod | +0.612 |
rid | +0.611 |
Neg logit contributions | |
collateral | -0.581 |
atari | -0.547 |
リ | -0.459 |
hers | -0.457 |
inert | -0.446 |
Token | anything |
Token ID | 1997 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
collateral | +0.135 |
atari | +0.126 |
リ | +0.107 |
hers | +0.107 |
inert | +0.104 |
Neg logit contributions | |
\": | -0.150 |
aints | -0.148 |
confir | -0.144 |
wcs | -0.138 |
rid | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
collateral | +0.276 |
atari | +0.260 |
リ | +0.220 |
hers | +0.218 |
Admiral | +0.212 |
Neg logit contributions | |
\": | -0.314 |
aints | -0.311 |
confir | -0.305 |
wcs | -0.288 |
Sod | -0.287 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
\": | +0.016 |
confir | +0.016 |
aints | +0.016 |
wcs | +0.015 |
jriwal | +0.015 |
Neg logit contributions | |
collateral | -0.018 |
atari | -0.017 |
リ | -0.015 |
hers | -0.014 |
Admiral | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
confir | +0.187 |
aints | +0.182 |
\": | +0.181 |
wcs | +0.169 |
jriwal | +0.167 |
Neg logit contributions | |
collateral | -0.180 |
atari | -0.172 |
リ | -0.148 |
hers | -0.146 |
Admiral | -0.143 |
Token | RELATED |
Token ID | 20112 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
\": | +0.200 |
confir | +0.199 |
aints | +0.198 |
Sod | +0.182 |
wcs | +0.182 |
Neg logit contributions | |
collateral | -0.226 |
atari | -0.220 |
リ | -0.191 |
hers | -0.186 |
Admiral | -0.181 |
Token | : |
Token ID | 25 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
\": | +1.942 |
aints | +1.910 |
confir | +1.864 |
Sod | +1.767 |
rid | +1.752 |
Neg logit contributions | |
collateral | -2.101 |
atari | -1.995 |
リ | -1.721 |
hers | -1.708 |
inert | -1.668 |
Token |
|
Token ID | 198 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
\": | +0.223 |
aints | +0.221 |
confir | +0.219 |
wcs | +0.205 |
rid | +0.205 |
Neg logit contributions | |
collateral | -0.192 |
atari | -0.184 |
リ | -0.155 |
hers | -0.152 |
Admiral | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
confir | +0.399 |
aints | +0.393 |
\": | +0.393 |
wcs | +0.363 |
Sod | +0.360 |
Neg logit contributions | |
collateral | -0.401 |
atari | -0.384 |
リ | -0.331 |
hers | -0.326 |
Admiral | -0.318 |
Token | ' |
Token ID | 6 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
\": | +0.272 |
aints | +0.271 |
confir | +0.270 |
Sod | +0.249 |
wcs | +0.248 |
Neg logit contributions | |
collateral | -0.297 |
atari | -0.287 |
リ | -0.249 |
hers | -0.242 |
Admiral | -0.237 |
Token | King |
Token ID | 15708 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
collateral | +0.344 |
atari | +0.334 |
リ | +0.290 |
hers | +0.281 |
Admiral | +0.275 |
Neg logit contributions | |
confir | -0.324 |
\": | -0.323 |
aints | -0.321 |
wcs | -0.296 |
jriwal | -0.296 |
Token | I |
Token ID | 314 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
collateral | +0.088 |
atari | +0.083 |
リ | +0.069 |
hers | +0.068 |
Admiral | +0.066 |
Neg logit contributions | |
\": | -0.123 |
aints | -0.121 |
confir | -0.119 |
wcs | -0.113 |
rid | -0.113 |
Token | started |
Token ID | 2067 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
collateral | +0.032 |
atari | +0.031 |
リ | +0.026 |
hers | +0.026 |
intern | +0.025 |
Neg logit contributions | |
\": | -0.035 |
aints | -0.035 |
confir | -0.034 |
wcs | -0.032 |
Sod | -0.032 |
Token | thinking |
Token ID | 3612 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
\": | +0.359 |
aints | +0.355 |
confir | +0.349 |
Sod | +0.331 |
rid | +0.330 |
Neg logit contributions | |
collateral | -0.273 |
atari | -0.258 |
リ | -0.215 |
hers | -0.212 |
inert | -0.206 |
Token | about |
Token ID | 546 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
collateral | +0.092 |
atari | +0.087 |
リ | +0.074 |
hers | +0.074 |
inert | +0.072 |
Neg logit contributions | |
\": | -0.094 |
aints | -0.094 |
confir | -0.092 |
wcs | -0.086 |
Sod | -0.085 |
Token | W |
Token ID | 370 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
\": | +0.073 |
aints | +0.072 |
confir | +0.071 |
wcs | +0.067 |
rid | +0.067 |
Neg logit contributions | |
collateral | -0.063 |
atari | -0.059 |
リ | -0.050 |
hers | -0.050 |
Admiral | -0.049 |
Token | ile |
Token ID | 576 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
collateral | +0.041 |
atari | +0.040 |
リ | +0.034 |
hers | +0.033 |
intern | +0.032 |
Neg logit contributions | |
\": | -0.038 |
aints | -0.037 |
confir | -0.037 |
wcs | -0.034 |
Sod | -0.034 |
Token | E |
Token ID | 412 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
collateral | +1.327 |
atari | +1.227 |
hers | +1.011 |
リ | +1.004 |
inert | +0.997 |
Neg logit contributions | |
\": | -1.773 |
aints | -1.731 |
confir | -1.719 |
wcs | -1.625 |
jriwal | -1.612 |
Token | . |
Token ID | 13 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
\": | +0.067 |
aints | +0.066 |
confir | +0.066 |
wcs | +0.062 |
Sod | +0.061 |
Neg logit contributions | |
collateral | -0.054 |
atari | -0.050 |
リ | -0.042 |
hers | -0.042 |
Admiral | -0.041 |
Token | Coy |
Token ID | 26887 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
confir | +0.043 |
\": | +0.043 |
aints | +0.043 |
wcs | +0.041 |
jriwal | +0.040 |
Neg logit contributions | |
collateral | -0.040 |
atari | -0.038 |
リ | -0.032 |
hers | -0.032 |
Admiral | -0.032 |
Token | ote |
Token ID | 1258 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
collateral | +0.209 |
atari | +0.202 |
リ | +0.177 |
hers | +0.175 |
Admiral | +0.172 |
Neg logit contributions | |
\": | -0.147 |
aints | -0.146 |
confir | -0.144 |
wcs | -0.132 |
rid | -0.132 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
\": | +0.570 |
aints | +0.567 |
confir | +0.559 |
wcs | +0.525 |
Sod | +0.523 |
Neg logit contributions | |
collateral | -0.517 |
atari | -0.492 |
リ | -0.417 |
hers | -0.409 |
Admiral | -0.400 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
\": | +0.385 |
aints | +0.380 |
confir | +0.374 |
Sod | +0.352 |
wcs | +0.351 |
Neg logit contributions | |
collateral | -0.338 |
atari | -0.321 |
リ | -0.271 |
hers | -0.268 |
inert | -0.261 |
Token | Jill |
Token ID | 22772 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
collateral | +0.184 |
atari | +0.175 |
リ | +0.148 |
hers | +0.146 |
Admiral | +0.142 |
Neg logit contributions | |
\": | -0.221 |
aints | -0.219 |
confir | -0.217 |
wcs | -0.203 |
rid | -0.201 |
Token | Stein |
Token ID | 15215 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
collateral | +0.350 |
atari | +0.326 |
リ | +0.261 |
hers | +0.259 |
Admiral | +0.248 |
Neg logit contributions | |
\": | -0.620 |
aints | -0.612 |
confir | -0.607 |
wcs | -0.576 |
rid | -0.574 |
Token | � |
Token ID | 8582 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
collateral | +1.156 |
atari | +1.114 |
リ | +0.996 |
hers | +0.987 |
Admiral | +0.971 |
Neg logit contributions | |
\": | -0.613 |
aints | -0.607 |
confir | -0.591 |
wcs | -0.530 |
Sod | -0.530 |
Token | � |
Token ID | 234 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
collateral | +0.406 |
atari | +0.385 |
リ | +0.334 |
hers | +0.328 |
inert | +0.319 |
Neg logit contributions | |
\": | -0.391 |
aints | -0.386 |
confir | -0.378 |
Sod | -0.356 |
rid | -0.354 |
Token | � |
Token ID | 119 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
collateral | +0.877 |
atari | +0.835 |
リ | +0.715 |
hers | +0.698 |
Admiral | +0.674 |
Neg logit contributions | |
\": | -0.989 |
aints | -0.982 |
confir | -0.962 |
Sod | -0.908 |
wcs | -0.906 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
collateral | +1.832 |
atari | +1.764 |
リ | +1.572 |
hers | +1.546 |
Admiral | +1.509 |
Neg logit contributions | |
\": | -1.205 |
aints | -1.196 |
confir | -1.173 |
Sod | -1.077 |
wcs | -1.065 |
Token | Dr |
Token ID | 6187 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
collateral | +0.148 |
atari | +0.143 |
リ | +0.125 |
hers | +0.123 |
inert | +0.120 |
Neg logit contributions | |
\": | -0.120 |
aints | -0.119 |
confir | -0.118 |
Sod | -0.109 |
wcs | -0.107 |
Token | J |
Token ID | 41 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
collateral | +0.421 |
atari | +0.403 |
リ | +0.349 |
hers | +0.345 |
inert | +0.337 |
Neg logit contributions | |
\": | -0.374 |
aints | -0.369 |
confir | -0.363 |
Sod | -0.339 |
rid | -0.337 |
Token | ill |
Token ID | 359 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
collateral | +0.240 |
atari | +0.230 |
リ | +0.201 |
hers | +0.199 |
inert | +0.194 |
Neg logit contributions | |
\": | -0.192 |
aints | -0.190 |
confir | -0.187 |
Sod | -0.174 |
wcs | -0.172 |
Token | Ste |
Token ID | 7447 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
collateral | +1.098 |
atari | +1.057 |
リ | +0.939 |
hers | +0.927 |
inert | +0.901 |
Neg logit contributions | |
\": | -0.764 |
aints | -0.749 |
confir | -0.746 |
Sod | -0.683 |
rid | -0.668 |
Token | your |
Token ID | 534 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
collateral | +0.164 |
atari | +0.154 |
リ | +0.128 |
hers | +0.127 |
Admiral | +0.123 |
Neg logit contributions | |
\": | -0.216 |
aints | -0.214 |
confir | -0.210 |
rid | -0.199 |
wcs | -0.199 |
Token | Windows |
Token ID | 3964 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
collateral | +0.229 |
atari | +0.216 |
リ | +0.183 |
hers | +0.181 |
inert | +0.177 |
Neg logit contributions | |
\": | -0.252 |
aints | -0.249 |
confir | -0.243 |
Sod | -0.231 |
rid | -0.230 |
Token | Mobile |
Token ID | 12173 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
collateral | +0.420 |
atari | +0.398 |
リ | +0.337 |
hers | +0.332 |
inert | +0.327 |
Neg logit contributions | |
\": | -0.449 |
aints | -0.447 |
confir | -0.436 |
Sod | -0.415 |
wcs | -0.414 |
Token | - |
Token ID | 12 |
Feature activation | -1.72e-03 |
Pos logit contributions | |
collateral | +1.180 |
atari | +1.110 |
リ | +0.939 |
hers | +0.928 |
inert | +0.913 |
Neg logit contributions | |
\": | -1.275 |
aints | -1.269 |
confir | -1.236 |
rid | -1.175 |
wcs | -1.174 |
Token | based |
Token ID | 3106 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
\": | +0.001 |
aints | +0.001 |
confir | +0.001 |
Sod | +0.001 |
rid | +0.001 |
Neg logit contributions | |
collateral | -0.001 |
atari | -0.001 |
リ | -0.001 |
hers | -0.001 |
inert | -0.001 |
Token | smartphone |
Token ID | 11745 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
\": | +0.634 |
aints | +0.627 |
confir | +0.617 |
Sod | +0.583 |
rid | +0.581 |
Neg logit contributions | |
collateral | -0.534 |
atari | -0.507 |
リ | -0.428 |
hers | -0.421 |
inert | -0.410 |
Token | has |
Token ID | 468 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
collateral | +1.654 |
atari | +1.568 |
リ | +1.336 |
intern | +1.330 |
hers | +1.330 |
Neg logit contributions | |
\": | -1.465 |
aints | -1.461 |
confir | -1.416 |
Sod | -1.341 |
rid | -1.337 |
Token | the |
Token ID | 262 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
\": | +0.669 |
aints | +0.663 |
confir | +0.651 |
Sod | +0.615 |
rid | +0.613 |
Neg logit contributions | |
collateral | -0.571 |
atari | -0.542 |
リ | -0.457 |
hers | -0.451 |
inert | -0.439 |
Token | Compact |
Token ID | 37904 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
\": | +0.304 |
aints | +0.302 |
confir | +0.295 |
Sod | +0.280 |
rid | +0.279 |
Neg logit contributions | |
collateral | -0.265 |
atari | -0.251 |
リ | -0.212 |
hers | -0.209 |
inert | -0.205 |
Token | . |
Token ID | 764 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
collateral | +0.544 |
atari | +0.521 |
リ | +0.455 |
hers | +0.444 |
inert | +0.438 |
Neg logit contributions | |
\": | -0.476 |
aints | -0.470 |
confir | -0.460 |
Sod | -0.428 |
wcs | -0.428 |
Token | NET |
Token ID | 12884 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
collateral | +0.330 |
atari | +0.318 |
リ | +0.274 |
hers | +0.267 |
Admiral | +0.264 |
Neg logit contributions | |
\": | -0.296 |
aints | -0.291 |
confir | -0.286 |
Sod | -0.266 |
rid | -0.265 |
Token | a |
Token ID | 257 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
collateral | +0.134 |
atari | +0.125 |
リ | +0.106 |
hers | +0.105 |
inert | +0.102 |
Neg logit contributions | |
\": | -0.159 |
aints | -0.157 |
confir | -0.155 |
wcs | -0.146 |
rid | -0.145 |
Token | parad |
Token ID | 11497 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
collateral | +0.010 |
atari | +0.009 |
リ | +0.008 |
hers | +0.008 |
inert | +0.007 |
Neg logit contributions | |
\": | -0.010 |
aints | -0.010 |
confir | -0.010 |
wcs | -0.009 |
rid | -0.009 |
Token | igmatic |
Token ID | 38860 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
collateral | +0.373 |
atari | +0.359 |
リ | +0.300 |
hers | +0.300 |
Admiral | +0.292 |
Neg logit contributions | |
\": | -0.404 |
confir | -0.400 |
aints | -0.396 |
Sod | -0.371 |
wcs | -0.365 |
Token | shift |
Token ID | 6482 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
collateral | +0.099 |
atari | +0.093 |
リ | +0.080 |
hers | +0.079 |
inert | +0.077 |
Neg logit contributions | |
\": | -0.102 |
aints | -0.101 |
confir | -0.100 |
rid | -0.093 |
wcs | -0.093 |
Token | in |
Token ID | 287 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
collateral | +0.483 |
atari | +0.451 |
hers | +0.387 |
リ | +0.385 |
inert | +0.377 |
Neg logit contributions | |
\": | -0.523 |
aints | -0.519 |
confir | -0.514 |
Sod | -0.479 |
rid | -0.476 |
Token | urban |
Token ID | 7876 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
collateral | +0.111 |
atari | +0.104 |
リ | +0.087 |
hers | +0.087 |
inert | +0.085 |
Neg logit contributions | |
\": | -0.135 |
aints | -0.133 |
confir | -0.132 |
rid | -0.124 |
wcs | -0.123 |
Token | governance |
Token ID | 18848 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
collateral | +1.499 |
atari | +1.406 |
リ | +1.202 |
hers | +1.192 |
inert | +1.172 |
Neg logit contributions | |
\": | -1.558 |
aints | -1.535 |
confir | -1.521 |
wcs | -1.429 |
rid | -1.424 |
Token | and |
Token ID | 290 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
collateral | +0.346 |
atari | +0.322 |
hers | +0.271 |
リ | +0.270 |
intern | +0.265 |
Neg logit contributions | |
\": | -0.407 |
aints | -0.401 |
confir | -0.398 |
rid | -0.374 |
Sod | -0.371 |
Token | problem |
Token ID | 1917 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
collateral | +0.111 |
atari | +0.104 |
リ | +0.088 |
hers | +0.088 |
inert | +0.086 |
Neg logit contributions | |
\": | -0.125 |
aints | -0.123 |
confir | -0.121 |
wcs | -0.114 |
rid | -0.114 |
Token | solving |
Token ID | 18120 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
collateral | +0.852 |
atari | +0.807 |
リ | +0.699 |
hers | +0.684 |
inert | +0.674 |
Neg logit contributions | |
\": | -0.802 |
aints | -0.787 |
confir | -0.785 |
wcs | -0.738 |
rid | -0.733 |
Token | that |
Token ID | 326 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
collateral | +0.012 |
atari | +0.011 |
リ | +0.009 |
hers | +0.009 |
intern | +0.009 |
Neg logit contributions | |
\": | -0.014 |
aints | -0.013 |
confir | -0.013 |
rid | -0.013 |
Sod | -0.013 |
Token | — |
Token ID | 851 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
collateral | +0.032 |
atari | +0.030 |
リ | +0.026 |
hers | +0.025 |
Admiral | +0.025 |
Neg logit contributions | |
\": | -0.036 |
aints | -0.035 |
confir | -0.035 |
Sod | -0.033 |
wcs | -0.033 |
Token | Winnipeg |
Token ID | 23434 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
collateral | +0.858 |
atari | +0.805 |
リ | +0.687 |
hers | +0.679 |
Admiral | +0.666 |
Neg logit contributions | |
\": | -0.969 |
aints | -0.960 |
confir | -0.946 |
wcs | -0.890 |
rid | -0.889 |
Token | Jets |
Token ID | 14728 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
\": | +0.003 |
aints | +0.003 |
confir | +0.003 |
rid | +0.003 |
Sod | +0.003 |
Neg logit contributions | |
collateral | -0.003 |
atari | -0.003 |
リ | -0.003 |
hers | -0.003 |
Admiral | -0.003 |
Token | (@ |
Token ID | 4275 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
collateral | +0.138 |
atari | +0.132 |
リ | +0.117 |
hers | +0.115 |
Admiral | +0.115 |
Neg logit contributions | |
\": | -0.081 |
aints | -0.080 |
confir | -0.078 |
Sod | -0.072 |
rid | -0.072 |
Token | N |
Token ID | 45 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
collateral | +0.209 |
atari | +0.201 |
リ | +0.174 |
hers | +0.171 |
inert | +0.166 |
Neg logit contributions | |
\": | -0.185 |
confir | -0.182 |
aints | -0.181 |
Sod | -0.170 |
rid | -0.165 |
Token | HL |
Token ID | 6581 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
collateral | +0.158 |
atari | +0.151 |
リ | +0.127 |
hers | +0.125 |
inert | +0.121 |
Neg logit contributions | |
\": | -0.187 |
aints | -0.185 |
confir | -0.184 |
Sod | -0.174 |
wcs | -0.172 |
Token | J |
Token ID | 41 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
collateral | +1.571 |
atari | +1.505 |
リ | +1.298 |
hers | +1.290 |
Admiral | +1.233 |
Neg logit contributions | |
\": | -1.507 |
confir | -1.490 |
aints | -1.459 |
Sod | -1.395 |
wcs | -1.346 |
Token | ets |
Token ID | 1039 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
collateral | +0.157 |
atari | +0.151 |
リ | +0.126 |
hers | +0.125 |
Admiral | +0.121 |
Neg logit contributions | |
\": | -0.180 |
confir | -0.177 |
aints | -0.175 |
Sod | -0.167 |
wcs | -0.165 |
Token | ) |
Token ID | 8 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
collateral | +1.480 |
atari | +1.427 |
リ | +1.208 |
hers | +1.177 |
Admiral | +1.143 |
Neg logit contributions | |
\": | -1.704 |
confir | -1.678 |
aints | -1.662 |
Sod | -1.573 |
wcs | -1.542 |
Token | October |
Token ID | 3267 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
collateral | +0.363 |
atari | +0.343 |
リ | +0.292 |
hers | +0.289 |
Admiral | +0.282 |
Neg logit contributions | |
\": | -0.423 |
aints | -0.420 |
confir | -0.420 |
wcs | -0.392 |
jriwal | -0.391 |
Token | 21 |
Token ID | 2310 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
collateral | +0.128 |
atari | +0.122 |
リ | +0.102 |
hers | +0.101 |
Admiral | +0.099 |
Neg logit contributions | |
confir | -0.157 |
\": | -0.157 |
aints | -0.156 |
wcs | -0.146 |
jriwal | -0.145 |
Token | A |
Token ID | 32 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
\": | +0.053 |
confir | +0.053 |
aints | +0.053 |
Sod | +0.049 |
wcs | +0.048 |
Neg logit contributions | |
collateral | -0.062 |
atari | -0.060 |
リ | -0.052 |
hers | -0.051 |
inert | -0.050 |
Token | judge |
Token ID | 5052 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
collateral | +0.088 |
atari | +0.083 |
リ | +0.071 |
hers | +0.070 |
inert | +0.068 |
Neg logit contributions | |
\": | -0.095 |
aints | -0.094 |
confir | -0.092 |
wcs | -0.087 |
Sod | -0.086 |
Token | ordered |
Token ID | 6149 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
\": | +0.729 |
aints | +0.721 |
confir | +0.704 |
wcs | +0.667 |
Sod | +0.663 |
Neg logit contributions | |
collateral | -0.659 |
atari | -0.617 |
hers | -0.522 |
リ | -0.520 |
inert | -0.511 |
Token | him |
Token ID | 683 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
\": | +0.519 |
aints | +0.514 |
confir | +0.504 |
Sod | +0.475 |
rid | +0.475 |
Neg logit contributions | |
collateral | -0.457 |
atari | -0.432 |
リ | -0.366 |
hers | -0.362 |
inert | -0.352 |
Token | released |
Token ID | 2716 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
\": | +0.273 |
aints | +0.270 |
confir | +0.265 |
Sod | +0.251 |
rid | +0.251 |
Neg logit contributions | |
collateral | -0.207 |
atari | -0.195 |
リ | -0.163 |
hers | -0.160 |
inert | -0.156 |
Token | during |
Token ID | 1141 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
\": | +0.333 |
aints | +0.329 |
confir | +0.322 |
wcs | +0.302 |
rid | +0.302 |
Neg logit contributions | |
collateral | -0.303 |
atari | -0.283 |
hers | -0.240 |
リ | -0.239 |
inert | -0.235 |
Token | a |
Token ID | 257 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
collateral | +0.507 |
atari | +0.476 |
リ | +0.400 |
hers | +0.395 |
inert | +0.384 |
Neg logit contributions | |
\": | -0.631 |
aints | -0.624 |
confir | -0.612 |
Sod | -0.578 |
rid | -0.576 |
Token | brief |
Token ID | 4506 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
\": | +0.034 |
aints | +0.034 |
confir | +0.034 |
Sod | +0.032 |
rid | +0.032 |
Neg logit contributions | |
collateral | -0.026 |
atari | -0.025 |
リ | -0.021 |
hers | -0.020 |
inert | -0.020 |
Token | bond |
Token ID | 6314 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
collateral | +0.462 |
atari | +0.432 |
リ | +0.356 |
hers | +0.350 |
inert | +0.340 |
Neg logit contributions | |
\": | -0.676 |
aints | -0.670 |
confir | -0.658 |
Sod | -0.624 |
wcs | -0.623 |
Token | hearing |
Token ID | 4854 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
collateral | +0.175 |
atari | +0.156 |
hers | +0.117 |
リ | +0.116 |
Admiral | +0.111 |
Neg logit contributions | |
\": | -0.412 |
aints | -0.410 |
confir | -0.401 |
wcs | -0.387 |
Sod | -0.386 |
Token | last |
Token ID | 938 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
collateral | +0.748 |
atari | +0.691 |
hers | +0.595 |
リ | +0.584 |
Admiral | +0.582 |
Neg logit contributions | |
\": | -0.806 |
aints | -0.796 |
confir | -0.778 |
wcs | -0.731 |
rid | -0.725 |
Token | Future |
Token ID | 10898 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
\": | +0.136 |
aints | +0.136 |
confir | +0.135 |
rid | +0.125 |
wcs | +0.125 |
Neg logit contributions | |
collateral | -0.120 |
atari | -0.114 |
リ | -0.097 |
hers | -0.096 |
Admiral | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
confir | +0.074 |
aints | +0.073 |
\": | +0.073 |
rid | +0.068 |
wcs | +0.067 |
Neg logit contributions | |
collateral | -0.073 |
atari | -0.070 |
リ | -0.060 |
Admiral | -0.058 |
hers | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
collateral | +0.207 |
atari | +0.198 |
リ | +0.171 |
hers | +0.168 |
Admiral | +0.164 |
Neg logit contributions | |
confir | -0.231 |
aints | -0.220 |
\": | -0.218 |
wcs | -0.206 |
jriwal | -0.205 |
Token | On |
Token ID | 2202 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
collateral | +0.290 |
atari | +0.283 |
リ | +0.248 |
hers | +0.239 |
Admiral | +0.234 |
Neg logit contributions | |
confir | -0.254 |
aints | -0.247 |
\": | -0.246 |
Sod | -0.227 |
wcs | -0.227 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
collateral | +0.635 |
atari | +0.594 |
リ | +0.502 |
hers | +0.495 |
Admiral | +0.481 |
Neg logit contributions | |
\": | -0.796 |
aints | -0.788 |
confir | -0.777 |
wcs | -0.735 |
rid | -0.730 |
Token | stage |
Token ID | 3800 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
collateral | +0.163 |
atari | +0.152 |
リ | +0.127 |
hers | +0.126 |
inert | +0.123 |
Neg logit contributions | |
\": | -0.212 |
aints | -0.210 |
confir | -0.206 |
wcs | -0.195 |
rid | -0.194 |
Token | of |
Token ID | 286 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
collateral | +0.201 |
atari | +0.189 |
リ | +0.160 |
hers | +0.158 |
Admiral | +0.154 |
Neg logit contributions | |
\": | -0.233 |
aints | -0.233 |
confir | -0.229 |
wcs | -0.215 |
rid | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
collateral | +0.059 |
atari | +0.055 |
リ | +0.047 |
hers | +0.047 |
Admiral | +0.045 |
Neg logit contributions | |
\": | -0.070 |
aints | -0.070 |
confir | -0.068 |
wcs | -0.065 |
rid | -0.064 |
Token | 2008 |
Token ID | 3648 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
collateral | +0.209 |
atari | +0.197 |
リ | +0.168 |
hers | +0.166 |
Admiral | +0.163 |
Neg logit contributions | |
aints | -0.231 |
\": | -0.231 |
confir | -0.226 |
wcs | -0.213 |
rid | -0.211 |
Token | Web |
Token ID | 5313 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
collateral | +0.094 |
atari | +0.088 |
リ | +0.075 |
hers | +0.073 |
Admiral | +0.072 |
Neg logit contributions | |
\": | -0.114 |
aints | -0.113 |
confir | -0.111 |
wcs | -0.105 |
rid | -0.104 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
\": | +0.196 |
aints | +0.194 |
confir | +0.191 |
Sod | +0.180 |
wcs | +0.180 |
Neg logit contributions | |
collateral | -0.181 |
atari | -0.171 |
リ | -0.147 |
hers | -0.144 |
Admiral | -0.141 |
Token | thrown |
Token ID | 8754 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
collateral | +0.452 |
atari | +0.422 |
リ | +0.359 |
hers | +0.357 |
inert | +0.347 |
Neg logit contributions | |
\": | -0.511 |
aints | -0.505 |
confir | -0.500 |
wcs | -0.472 |
Sod | -0.470 |
Token | his |
Token ID | 465 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
\": | +0.821 |
aints | +0.813 |
confir | +0.801 |
Sod | +0.755 |
rid | +0.753 |
Neg logit contributions | |
collateral | -0.655 |
atari | -0.616 |
リ | -0.516 |
hers | -0.512 |
inert | -0.498 |
Token | way |
Token ID | 835 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
collateral | +0.201 |
atari | +0.191 |
リ | +0.170 |
hers | +0.169 |
inert | +0.166 |
Neg logit contributions | |
\": | -0.123 |
aints | -0.121 |
confir | -0.118 |
Sod | -0.109 |
wcs | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
collateral | +0.393 |
atari | +0.371 |
リ | +0.313 |
hers | +0.311 |
intern | +0.302 |
Neg logit contributions | |
\": | -0.451 |
aints | -0.447 |
confir | -0.441 |
Sod | -0.416 |
rid | -0.414 |
Token | His |
Token ID | 2399 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
collateral | +0.035 |
atari | +0.034 |
リ | +0.030 |
Admiral | +0.029 |
hers | +0.029 |
Neg logit contributions | |
confir | -0.032 |
aints | -0.031 |
\": | -0.031 |
jriwal | -0.029 |
wcs | -0.029 |
Token | catch |
Token ID | 4929 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
\": | +0.030 |
aints | +0.030 |
confir | +0.029 |
wcs | +0.028 |
Sod | +0.028 |
Neg logit contributions | |
collateral | -0.028 |
atari | -0.027 |
リ | -0.023 |
hers | -0.022 |
inert | -0.022 |
Token | radius |
Token ID | 16874 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
collateral | +0.246 |
atari | +0.233 |
リ | +0.196 |
hers | +0.194 |
inert | +0.190 |
Neg logit contributions | |
\": | -0.267 |
aints | -0.264 |
confir | -0.260 |
Sod | -0.248 |
wcs | -0.248 |
Token | , |
Token ID | 11 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
collateral | +0.037 |
atari | +0.035 |
リ | +0.030 |
hers | +0.030 |
intern | +0.029 |
Neg logit contributions | |
\": | -0.037 |
aints | -0.037 |
confir | -0.036 |
wcs | -0.034 |
Sod | -0.034 |
Token | combined |
Token ID | 5929 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
collateral | +0.352 |
atari | +0.326 |
hers | +0.278 |
リ | +0.278 |
inert | +0.272 |
Neg logit contributions | |
\": | -0.381 |
aints | -0.378 |
confir | -0.369 |
wcs | -0.349 |
Sod | -0.346 |
Token | with |
Token ID | 351 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
collateral | +0.595 |
atari | +0.558 |
リ | +0.471 |
hers | +0.469 |
inert | +0.457 |
Neg logit contributions | |
\": | -0.714 |
aints | -0.711 |
confir | -0.706 |
Sod | -0.658 |
wcs | -0.656 |
Token | his |
Token ID | 465 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
collateral | +0.082 |
atari | +0.076 |
リ | +0.063 |
hers | +0.063 |
inert | +0.061 |
Neg logit contributions | |
\": | -0.107 |
aints | -0.107 |
confir | -0.105 |
wcs | -0.099 |
Sod | -0.098 |
Token | election |
Token ID | 3071 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
collateral | +0.880 |
atari | +0.827 |
リ | +0.712 |
hers | +0.703 |
intern | +0.692 |
Neg logit contributions | |
\": | -0.837 |
aints | -0.827 |
confir | -0.806 |
rid | -0.759 |
wcs | -0.758 |
Token | matchup |
Token ID | 18406 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
collateral | +0.030 |
atari | +0.028 |
hers | +0.024 |
リ | +0.024 |
inert | +0.023 |
Neg logit contributions | |
\": | -0.032 |
aints | -0.032 |
confir | -0.032 |
rid | -0.029 |
wcs | -0.029 |
Token | between |
Token ID | 1022 |
Feature activation | -8.61e-01 |
Pos logit contributions | |
collateral | +0.037 |
atari | +0.035 |
hers | +0.030 |
リ | +0.030 |
Admiral | +0.030 |
Neg logit contributions | |
\": | -0.036 |
aints | -0.036 |
confir | -0.035 |
rid | -0.033 |
wcs | -0.033 |
Token | Donald |
Token ID | 3759 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
\": | +0.726 |
aints | +0.718 |
confir | +0.706 |
rid | +0.665 |
wcs | +0.664 |
Neg logit contributions | |
collateral | -0.640 |
atari | -0.606 |
リ | -0.512 |
hers | -0.510 |
Admiral | -0.497 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
collateral | +0.215 |
atari | +0.206 |
リ | +0.180 |
hers | +0.178 |
Admiral | +0.175 |
Neg logit contributions | |
\": | -0.167 |
aints | -0.165 |
confir | -0.162 |
Sod | -0.150 |
rid | -0.150 |
Token | Donald |
Token ID | 3759 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
collateral | +0.162 |
atari | +0.154 |
リ | +0.131 |
hers | +0.129 |
inert | +0.126 |
Neg logit contributions | |
\": | -0.183 |
aints | -0.181 |
confir | -0.178 |
Sod | -0.168 |
rid | -0.168 |
Token | John |
Token ID | 1757 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
collateral | +0.299 |
atari | +0.279 |
リ | +0.233 |
hers | +0.227 |
Admiral | +0.223 |
Neg logit contributions | |
\": | -0.419 |
confir | -0.419 |
aints | -0.415 |
wcs | -0.390 |
rid | -0.389 |
Token | Trump |
Token ID | 1301 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
collateral | +0.270 |
atari | +0.259 |
リ | +0.226 |
hers | +0.224 |
Admiral | +0.219 |
Neg logit contributions | |
\": | -0.207 |
aints | -0.205 |
confir | -0.202 |
Sod | -0.187 |
rid | -0.186 |
Token | House |
Token ID | 18102 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
collateral | +0.242 |
atari | +0.232 |
リ | +0.204 |
hers | +0.199 |
Admiral | +0.196 |
Neg logit contributions | |
\": | -0.205 |
confir | -0.202 |
aints | -0.202 |
Sod | -0.187 |
wcs | -0.186 |
Token | committee |
Token ID | 5583 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
collateral | +0.400 |
atari | +0.388 |
リ | +0.333 |
hers | +0.332 |
inert | +0.324 |
Neg logit contributions | |
\": | -0.340 |
aints | -0.334 |
confir | -0.331 |
rid | -0.307 |
Sod | -0.307 |
Token | believes |
Token ID | 5804 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
collateral | +0.364 |
atari | +0.354 |
リ | +0.313 |
hers | +0.310 |
inert | +0.305 |
Neg logit contributions | |
\": | -0.204 |
aints | -0.201 |
confir | -0.197 |
Sod | -0.178 |
rid | -0.177 |
Token | bou |
Token ID | 35833 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
collateral | +0.278 |
atari | +0.262 |
リ | +0.222 |
hers | +0.222 |
inert | +0.217 |
Neg logit contributions | |
\": | -0.297 |
aints | -0.296 |
confir | -0.288 |
Sod | -0.272 |
wcs | -0.270 |
Token | levard |
Token ID | 22123 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
collateral | +0.479 |
atari | +0.455 |
リ | +0.393 |
hers | +0.385 |
inert | +0.376 |
Neg logit contributions | |
\": | -0.456 |
aints | -0.449 |
confir | -0.444 |
Sod | -0.413 |
rid | -0.409 |
Token | in |
Token ID | 287 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
\": | +0.978 |
aints | +0.968 |
confir | +0.949 |
Sod | +0.892 |
rid | +0.887 |
Neg logit contributions | |
collateral | -0.960 |
atari | -0.911 |
リ | -0.778 |
hers | -0.772 |
inert | -0.751 |
Token | the |
Token ID | 262 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
\": | +0.077 |
aints | +0.077 |
confir | +0.075 |
wcs | +0.071 |
rid | +0.071 |
Neg logit contributions | |
collateral | -0.061 |
atari | -0.057 |
リ | -0.048 |
hers | -0.047 |
inert | -0.046 |
Token | country |
Token ID | 1499 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
collateral | +0.073 |
atari | +0.068 |
リ | +0.058 |
hers | +0.058 |
intern | +0.056 |
Neg logit contributions | |
\": | -0.080 |
aints | -0.080 |
confir | -0.078 |
wcs | -0.073 |
rid | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
\": | +0.514 |
aints | +0.510 |
confir | +0.500 |
Sod | +0.472 |
rid | +0.469 |
Neg logit contributions | |
collateral | -0.460 |
atari | -0.436 |
リ | -0.370 |
hers | -0.365 |
inert | -0.355 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
collateral | +0.239 |
atari | +0.228 |
リ | +0.198 |
hers | +0.197 |
Admiral | +0.193 |
Neg logit contributions | |
confir | -0.236 |
\": | -0.235 |
aints | -0.234 |
wcs | -0.218 |
jriwal | -0.216 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
collateral | +0.195 |
atari | +0.187 |
リ | +0.161 |
hers | +0.158 |
Admiral | +0.154 |
Neg logit contributions | |
confir | -0.213 |
aints | -0.204 |
\": | -0.203 |
wcs | -0.191 |
jriwal | -0.190 |
Token | The |
Token ID | 464 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
collateral | +0.204 |
atari | +0.198 |
リ | +0.173 |
hers | +0.170 |
Admiral | +0.164 |
Neg logit contributions | |
confir | -0.179 |
\": | -0.176 |
aints | -0.176 |
Sod | -0.162 |
wcs | -0.161 |
Token | city |
Token ID | 1748 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
collateral | +0.040 |
atari | +0.037 |
hers | +0.032 |
リ | +0.032 |
Admiral | +0.031 |
Neg logit contributions | |
\": | -0.039 |
aints | -0.038 |
confir | -0.037 |
wcs | -0.035 |
Sod | -0.035 |
Token | is |
Token ID | 318 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
collateral | +0.097 |
atari | +0.091 |
hers | +0.079 |
リ | +0.078 |
Admiral | +0.076 |
Neg logit contributions | |
\": | -0.091 |
aints | -0.091 |
confir | -0.089 |
Sod | -0.083 |
wcs | -0.083 |
Token | 6 |
Token ID | 718 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
\": | +0.545 |
aints | +0.539 |
confir | +0.529 |
Sod | +0.499 |
rid | +0.498 |
Neg logit contributions | |
collateral | -0.502 |
atari | -0.478 |
リ | -0.407 |
hers | -0.400 |
inert | -0.390 |
Token | , |
Token ID | 11 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
collateral | +0.189 |
atari | +0.179 |
リ | +0.150 |
hers | +0.149 |
inert | +0.146 |
Neg logit contributions | |
\": | -0.208 |
aints | -0.205 |
confir | -0.202 |
Sod | -0.191 |
wcs | -0.191 |
Token | 7 |
Token ID | 767 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
\": | +0.583 |
aints | +0.577 |
confir | +0.566 |
Sod | +0.535 |
rid | +0.533 |
Neg logit contributions | |
collateral | -0.530 |
atari | -0.505 |
リ | -0.430 |
hers | -0.422 |
inert | -0.412 |
Token | , |
Token ID | 11 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
\": | +0.183 |
aints | +0.181 |
confir | +0.178 |
Sod | +0.168 |
wcs | +0.167 |
Neg logit contributions | |
collateral | -0.168 |
atari | -0.159 |
リ | -0.134 |
hers | -0.133 |
inert | -0.130 |
Token | 8 |
Token ID | 807 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
\": | +0.580 |
aints | +0.574 |
confir | +0.564 |
Sod | +0.530 |
rid | +0.529 |
Neg logit contributions | |
collateral | -0.544 |
atari | -0.517 |
リ | -0.440 |
hers | -0.434 |
inert | -0.424 |
Token | , |
Token ID | 11 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
\": | +0.069 |
aints | +0.068 |
confir | +0.067 |
Sod | +0.063 |
wcs | +0.063 |
Neg logit contributions | |
collateral | -0.063 |
atari | -0.059 |
リ | -0.050 |
hers | -0.050 |
inert | -0.049 |
Token | & |
Token ID | 1222 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
\": | +0.601 |
aints | +0.596 |
confir | +0.585 |
Sod | +0.555 |
rid | +0.553 |
Neg logit contributions | |
collateral | -0.484 |
atari | -0.459 |
リ | -0.385 |
hers | -0.379 |
inert | -0.368 |
Token | 9 |
Token ID | 860 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
\": | +0.836 |
aints | +0.829 |
confir | +0.815 |
Sod | +0.773 |
rid | +0.771 |
Neg logit contributions | |
collateral | -0.636 |
atari | -0.602 |
リ | -0.501 |
hers | -0.493 |
inert | -0.479 |
Token | metre |
Token ID | 42760 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
collateral | +0.063 |
atari | +0.060 |
リ | +0.050 |
hers | +0.050 |
inert | +0.049 |
Neg logit contributions | |
\": | -0.073 |
aints | -0.072 |
confir | -0.070 |
Sod | -0.067 |
wcs | -0.067 |
Token | positions |
Token ID | 6116 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
collateral | +0.131 |
atari | +0.122 |
リ | +0.102 |
hers | +0.101 |
inert | +0.098 |
Neg logit contributions | |
\": | -0.174 |
aints | -0.171 |
confir | -0.168 |
Sod | -0.160 |
wcs | -0.159 |
Token | , |
Token ID | 11 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
\": | +0.100 |
aints | +0.099 |
confir | +0.097 |
Sod | +0.092 |
wcs | +0.092 |
Neg logit contributions | |
collateral | -0.086 |
atari | -0.081 |
リ | -0.068 |
hers | -0.067 |
inert | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
collateral | +0.179 |
atari | +0.168 |
リ | +0.142 |
hers | +0.140 |
inert | +0.138 |
Neg logit contributions | |
\": | -0.220 |
aints | -0.218 |
confir | -0.213 |
wcs | -0.202 |
rid | -0.201 |
Token | fluid |
Token ID | 11711 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
collateral | +0.008 |
atari | +0.007 |
リ | +0.006 |
hers | +0.006 |
inert | +0.006 |
Neg logit contributions | |
\": | -0.009 |
aints | -0.009 |
confir | -0.008 |
wcs | -0.008 |
rid | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
\": | +0.748 |
aints | +0.742 |
confir | +0.726 |
Sod | +0.683 |
wcs | +0.681 |
Neg logit contributions | |
collateral | -0.720 |
atari | -0.682 |
リ | -0.582 |
hers | -0.577 |
inert | -0.566 |
Token | some |
Token ID | 617 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
collateral | +0.080 |
atari | +0.075 |
リ | +0.063 |
hers | +0.063 |
inert | +0.062 |
Neg logit contributions | |
\": | -0.093 |
aints | -0.092 |
confir | -0.090 |
wcs | -0.085 |
rid | -0.085 |
Token | uniform |
Token ID | 8187 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
\": | +0.379 |
aints | +0.376 |
confir | +0.367 |
wcs | +0.346 |
rid | +0.345 |
Neg logit contributions | |
collateral | -0.401 |
atari | -0.375 |
リ | -0.324 |
inert | -0.323 |
hers | -0.322 |
Token | ambient |
Token ID | 25237 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
collateral | +0.881 |
atari | +0.822 |
inert | +0.718 |
リ | +0.715 |
hers | +0.710 |
Neg logit contributions | |
\": | -0.767 |
aints | -0.758 |
confir | -0.747 |
wcs | -0.703 |
rid | -0.692 |
Token | density |
Token ID | 12109 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
\": | +0.030 |
aints | +0.030 |
confir | +0.029 |
wcs | +0.027 |
Sod | +0.027 |
Neg logit contributions | |
collateral | -0.036 |
atari | -0.034 |
リ | -0.030 |
hers | -0.030 |
inert | -0.029 |
Token | ( |
Token ID | 357 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
\": | +0.150 |
aints | +0.149 |
confir | +0.146 |
Sod | +0.138 |
wcs | +0.137 |
Neg logit contributions | |
collateral | -0.136 |
atari | -0.128 |
リ | -0.108 |
hers | -0.108 |
inert | -0.106 |
Token | as |
Token ID | 292 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
collateral | +0.178 |
atari | +0.171 |
リ | +0.148 |
hers | +0.145 |
inert | +0.143 |
Neg logit contributions | |
\": | -0.158 |
aints | -0.156 |
confir | -0.155 |
Sod | -0.144 |
wcs | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
\": | +0.134 |
aints | +0.133 |
confir | +0.130 |
wcs | +0.123 |
Sod | +0.122 |
Neg logit contributions | |
collateral | -0.129 |
atari | -0.122 |
リ | -0.105 |
hers | -0.103 |
inert | -0.102 |
Token | gray |
Token ID | 12768 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
\": | +0.015 |
aints | +0.015 |
confir | +0.015 |
wcs | +0.014 |
rid | +0.014 |
Neg logit contributions | |
collateral | -0.015 |
atari | -0.014 |
リ | -0.012 |
hers | -0.012 |
inert | -0.012 |
Token | gonna |
Token ID | 8066 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
\": | +0.039 |
aints | +0.039 |
confir | +0.038 |
Sod | +0.036 |
rid | +0.036 |
Neg logit contributions | |
collateral | -0.038 |
atari | -0.036 |
リ | -0.031 |
hers | -0.030 |
inert | -0.030 |
Token | do |
Token ID | 466 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
\": | +0.327 |
aints | +0.325 |
confir | +0.318 |
Sod | +0.301 |
wcs | +0.300 |
Neg logit contributions | |
collateral | -0.286 |
atari | -0.270 |
リ | -0.229 |
hers | -0.226 |
inert | -0.220 |
Token | . |
Token ID | 13 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
\": | +0.148 |
aints | +0.148 |
confir | +0.146 |
Sod | +0.138 |
rid | +0.137 |
Neg logit contributions | |
collateral | -0.127 |
atari | -0.120 |
リ | -0.101 |
hers | -0.100 |
Admiral | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
\": | +0.247 |
aints | +0.245 |
confir | +0.243 |
wcs | +0.227 |
rid | +0.225 |
Neg logit contributions | |
collateral | -0.262 |
atari | -0.250 |
リ | -0.216 |
hers | -0.213 |
Admiral | -0.209 |
Token |
|
Token ID | 198 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
confir | +0.068 |
aints | +0.066 |
\": | +0.066 |
wcs | +0.061 |
jriwal | +0.061 |
Neg logit contributions | |
collateral | -0.064 |
atari | -0.061 |
リ | -0.053 |
hers | -0.052 |
Admiral | -0.051 |
Token | The |
Token ID | 464 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
\": | +0.054 |
confir | +0.054 |
aints | +0.054 |
Sod | +0.050 |
wcs | +0.049 |
Neg logit contributions | |
collateral | -0.064 |
atari | -0.062 |
リ | -0.054 |
hers | -0.053 |
inert | -0.051 |
Token | Two |
Token ID | 4930 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
\": | +0.120 |
aints | +0.119 |
confir | +0.116 |
wcs | +0.109 |
Sod | +0.108 |
Neg logit contributions | |
collateral | -0.135 |
atari | -0.127 |
リ | -0.110 |
hers | -0.109 |
intern | -0.108 |
Token | Different |
Token ID | 20615 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
\": | +0.276 |
aints | +0.271 |
confir | +0.270 |
wcs | +0.246 |
rid | +0.244 |
Neg logit contributions | |
collateral | -0.411 |
atari | -0.393 |
リ | -0.347 |
hers | -0.344 |
Admiral | -0.340 |
Token | Block |
Token ID | 9726 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
\": | +0.989 |
aints | +0.974 |
confir | +0.955 |
Sod | +0.878 |
rid | +0.876 |
Neg logit contributions | |
collateral | -1.516 |
atari | -1.458 |
リ | -1.288 |
hers | -1.273 |
inert | -1.248 |
Token | Not |
Token ID | 1892 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
collateral | +0.040 |
atari | +0.038 |
リ | +0.033 |
hers | +0.033 |
Admiral | +0.032 |
Neg logit contributions | |
\": | -0.031 |
confir | -0.030 |
aints | -0.030 |
wcs | -0.028 |
rid | -0.028 |
Token | ations |
Token ID | 602 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
\": | +0.811 |
aints | +0.796 |
confir | +0.792 |
wcs | +0.739 |
Sod | +0.737 |
Neg logit contributions | |
collateral | -0.793 |
atari | -0.754 |
リ | -0.646 |
hers | -0.634 |
intern | -0.621 |
Token | had |
Token ID | 550 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
collateral | +0.096 |
atari | +0.088 |
リ | +0.076 |
hers | +0.076 |
Admiral | +0.074 |
Neg logit contributions | |
\": | -0.105 |
aints | -0.104 |
confir | -0.102 |
wcs | -0.096 |
rid | -0.096 |
Token | it |
Token ID | 340 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
\": | +0.076 |
aints | +0.076 |
confir | +0.074 |
rid | +0.069 |
wcs | +0.069 |
Neg logit contributions | |
collateral | -0.067 |
atari | -0.062 |
リ | -0.053 |
hers | -0.053 |
inert | -0.052 |
Token | installed |
Token ID | 6589 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
\": | +0.156 |
aints | +0.154 |
confir | +0.150 |
Sod | +0.143 |
rid | +0.142 |
Neg logit contributions | |
collateral | -0.131 |
atari | -0.123 |
hers | -0.103 |
リ | -0.103 |
inert | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
collateral | +0.083 |
atari | +0.078 |
hers | +0.066 |
リ | +0.066 |
inert | +0.064 |
Neg logit contributions | |
\": | -0.094 |
aints | -0.093 |
confir | -0.092 |
Sod | -0.086 |
rid | -0.086 |
Token | according |
Token ID | 1864 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
\": | +0.098 |
aints | +0.096 |
confir | +0.094 |
rid | +0.089 |
wcs | +0.089 |
Neg logit contributions | |
collateral | -0.085 |
atari | -0.079 |
リ | -0.067 |
hers | -0.067 |
Admiral | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
collateral | +0.291 |
atari | +0.273 |
リ | +0.225 |
hers | +0.221 |
Admiral | +0.214 |
Neg logit contributions | |
\": | -0.437 |
aints | -0.434 |
confir | -0.431 |
Sod | -0.405 |
rid | -0.404 |
Token | court |
Token ID | 2184 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
\": | +0.197 |
aints | +0.195 |
confir | +0.192 |
Sod | +0.181 |
rid | +0.181 |
Neg logit contributions | |
collateral | -0.160 |
atari | -0.151 |
リ | -0.127 |
hers | -0.125 |
inert | -0.121 |
Token | documents |
Token ID | 4963 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
\": | +0.562 |
aints | +0.556 |
confir | +0.546 |
Sod | +0.516 |
rid | +0.514 |
Neg logit contributions | |
collateral | -0.505 |
atari | -0.480 |
リ | -0.407 |
hers | -0.401 |
inert | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
\": | +0.075 |
aints | +0.074 |
confir | +0.072 |
Sod | +0.069 |
wcs | +0.069 |
Neg logit contributions | |
collateral | -0.065 |
atari | -0.061 |
リ | -0.051 |
hers | -0.051 |
Admiral | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
\": | +0.091 |
confir | +0.091 |
aints | +0.090 |
wcs | +0.084 |
rid | +0.083 |
Neg logit contributions | |
collateral | -0.094 |
atari | -0.090 |
リ | -0.078 |
hers | -0.076 |
Admiral | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
collateral | +0.080 |
atari | +0.077 |
リ | +0.066 |
hers | +0.065 |
Admiral | +0.064 |
Neg logit contributions | |
confir | -0.084 |
aints | -0.081 |
\": | -0.081 |
wcs | -0.075 |
jriwal | -0.075 |
Token | Ten |
Token ID | 9368 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
\": | +0.223 |
aints | +0.221 |
confir | +0.215 |
Sod | +0.204 |
rid | +0.204 |
Neg logit contributions | |
collateral | -0.209 |
atari | -0.198 |
リ | -0.168 |
hers | -0.166 |
inert | -0.163 |
Token | - |
Token ID | 12 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
\": | +0.650 |
aints | +0.635 |
confir | +0.621 |
Sod | +0.580 |
wcs | +0.576 |
Neg logit contributions | |
collateral | -0.723 |
atari | -0.694 |
リ | -0.597 |
hers | -0.584 |
Admiral | -0.580 |
Token | Day |
Token ID | 12393 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
\": | +0.112 |
aints | +0.110 |
confir | +0.109 |
Sod | +0.102 |
wcs | +0.101 |
Neg logit contributions | |
collateral | -0.101 |
atari | -0.097 |
リ | -0.082 |
hers | -0.080 |
Admiral | -0.078 |
Token | War |
Token ID | 1810 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
\": | +0.655 |
aints | +0.649 |
confir | +0.638 |
wcs | +0.601 |
Sod | +0.601 |
Neg logit contributions | |
collateral | -0.541 |
atari | -0.513 |
リ | -0.434 |
hers | -0.426 |
inert | -0.415 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
collateral | +0.243 |
atari | +0.231 |
リ | +0.197 |
hers | +0.193 |
Admiral | +0.191 |
Neg logit contributions | |
\": | -0.261 |
aints | -0.258 |
confir | -0.254 |
Sod | -0.237 |
wcs | -0.237 |
Token | a |
Token ID | 257 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
collateral | +0.081 |
atari | +0.076 |
リ | +0.065 |
hers | +0.064 |
Admiral | +0.063 |
Neg logit contributions | |
\": | -0.092 |
aints | -0.091 |
confir | -0.089 |
rid | -0.084 |
wcs | -0.084 |
Token | referendum |
Token ID | 11467 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
collateral | +0.020 |
atari | +0.019 |
リ | +0.016 |
hers | +0.016 |
inert | +0.015 |
Neg logit contributions | |
\": | -0.022 |
aints | -0.022 |
confir | -0.021 |
Sod | -0.020 |
rid | -0.020 |
Token | supported |
Token ID | 4855 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
collateral | +0.725 |
atari | +0.679 |
リ | +0.574 |
hers | +0.570 |
inert | +0.563 |
Neg logit contributions | |
\": | -0.792 |
aints | -0.781 |
confir | -0.763 |
Sod | -0.717 |
rid | -0.715 |
Token | by |
Token ID | 416 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
collateral | +0.424 |
atari | +0.401 |
リ | +0.345 |
hers | +0.342 |
Admiral | +0.333 |
Neg logit contributions | |
\": | -0.427 |
aints | -0.423 |
confir | -0.412 |
Sod | -0.389 |
rid | -0.388 |
Token | all |
Token ID | 477 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
\": | +0.230 |
aints | +0.229 |
confir | +0.223 |
wcs | +0.212 |
rid | +0.211 |
Neg logit contributions | |
collateral | -0.192 |
atari | -0.178 |
リ | -0.152 |
hers | -0.150 |
Admiral | -0.146 |
Token | Sloven |
Token ID | 30694 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
\": | +0.144 |
aints | +0.142 |
confir | +0.139 |
rid | +0.131 |
Sod | +0.131 |
Neg logit contributions | |
collateral | -0.143 |
atari | -0.135 |
リ | -0.116 |
hers | -0.115 |
inert | -0.112 |
Token | line |
Token ID | 1627 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
collateral | +0.009 |
atari | +0.009 |
リ | +0.008 |
hers | +0.007 |
inert | +0.007 |
Neg logit contributions | |
\": | -0.009 |
aints | -0.009 |
confir | -0.009 |
wcs | -0.008 |
Sod | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
\": | +0.039 |
aints | +0.039 |
confir | +0.038 |
Sod | +0.036 |
rid | +0.036 |
Neg logit contributions | |
collateral | -0.034 |
atari | -0.032 |
リ | -0.027 |
hers | -0.027 |
inert | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
confir | +0.195 |
\": | +0.194 |
aints | +0.194 |
wcs | +0.180 |
jriwal | +0.179 |
Neg logit contributions | |
collateral | -0.204 |
atari | -0.195 |
リ | -0.170 |
hers | -0.167 |
Admiral | -0.165 |
Token |
|
Token ID | 198 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
confir | +0.465 |
aints | +0.451 |
\": | +0.448 |
wcs | +0.419 |
jriwal | +0.416 |
Neg logit contributions | |
collateral | -0.442 |
atari | -0.424 |
リ | -0.367 |
hers | -0.359 |
Admiral | -0.351 |
Token | If |
Token ID | 1532 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
confir | +0.367 |
aints | +0.364 |
\": | +0.364 |
Sod | +0.335 |
wcs | +0.333 |
Neg logit contributions | |
collateral | -0.424 |
atari | -0.408 |
リ | -0.357 |
hers | -0.348 |
Admiral | -0.339 |
Token | Os |
Token ID | 8834 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
\": | +0.739 |
aints | +0.733 |
confir | +0.717 |
Sod | +0.675 |
wcs | +0.675 |
Neg logit contributions | |
collateral | -0.660 |
atari | -0.619 |
リ | -0.528 |
hers | -0.526 |
inert | -0.512 |
Token | so |
Token ID | 568 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
\": | +1.176 |
aints | +1.152 |
confir | +1.150 |
wcs | +1.067 |
Sod | +1.044 |
Neg logit contributions | |
collateral | -1.972 |
atari | -1.897 |
hers | -1.678 |
リ | -1.677 |
inert | -1.639 |
Token | ff |
Token ID | 487 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
\": | +0.771 |
aints | +0.768 |
confir | +0.757 |
wcs | +0.715 |
rid | +0.715 |
Neg logit contributions | |
collateral | -0.552 |
atari | -0.513 |
リ | -0.425 |
hers | -0.409 |
Admiral | -0.405 |
Token | wins |
Token ID | 7864 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
\": | +0.519 |
aints | +0.514 |
confir | +0.504 |
Sod | +0.472 |
rid | +0.470 |
Neg logit contributions | |
collateral | -0.603 |
atari | -0.575 |
リ | -0.499 |
hers | -0.494 |
inert | -0.483 |
Token | this |
Token ID | 428 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
\": | +0.146 |
aints | +0.145 |
confir | +0.142 |
wcs | +0.134 |
Sod | +0.134 |
Neg logit contributions | |
collateral | -0.130 |
atari | -0.122 |
hers | -0.105 |
リ | -0.104 |
inert | -0.101 |
Token | conservative |
Token ID | 5940 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
\": | +0.012 |
aints | +0.012 |
confir | +0.012 |
Sod | +0.011 |
rid | +0.011 |
Neg logit contributions | |
collateral | -0.013 |
atari | -0.013 |
リ | -0.011 |
hers | -0.011 |
inert | -0.011 |
Token | � |
Token ID | 247 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
\": | +0.056 |
aints | +0.055 |
confir | +0.054 |
Sod | +0.051 |
rid | +0.051 |
Neg logit contributions | |
collateral | -0.048 |
atari | -0.045 |
リ | -0.039 |
hers | -0.038 |
inert | -0.037 |
Token | t |
Token ID | 83 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
collateral | +0.280 |
atari | +0.270 |
リ | +0.240 |
hers | +0.237 |
Admiral | +0.233 |
Neg logit contributions | |
aints | -0.170 |
\": | -0.169 |
confir | -0.165 |
Sod | -0.151 |
wcs | -0.150 |
Token | Kick |
Token ID | 10279 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
\": | +0.480 |
aints | +0.479 |
confir | +0.469 |
wcs | +0.438 |
rid | +0.434 |
Neg logit contributions | |
collateral | -0.521 |
atari | -0.491 |
hers | -0.426 |
リ | -0.425 |
Admiral | -0.419 |
Token | and |
Token ID | 290 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
\": | +0.388 |
confir | +0.385 |
aints | +0.383 |
wcs | +0.358 |
Sod | +0.353 |
Neg logit contributions | |
collateral | -0.360 |
atari | -0.344 |
リ | -0.293 |
hers | -0.290 |
Admiral | -0.284 |
Token | C |
Token ID | 327 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
\": | +0.461 |
aints | +0.458 |
confir | +0.451 |
wcs | +0.419 |
rid | +0.416 |
Neg logit contributions | |
collateral | -0.522 |
atari | -0.495 |
リ | -0.430 |
hers | -0.429 |
Admiral | -0.421 |
Token | aper |
Token ID | 2136 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
\": | +0.384 |
confir | +0.380 |
aints | +0.376 |
Sod | +0.351 |
wcs | +0.348 |
Neg logit contributions | |
collateral | -0.473 |
atari | -0.459 |
リ | -0.394 |
hers | -0.387 |
Admiral | -0.382 |
Token | About |
Token ID | 7994 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
\": | +1.365 |
aints | +1.354 |
confir | +1.341 |
Sod | +1.251 |
wcs | +1.250 |
Neg logit contributions | |
collateral | -1.202 |
atari | -1.139 |
リ | -0.967 |
hers | -0.954 |
Admiral | -0.930 |
Token | . |
Token ID | 13 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
\": | +0.159 |
confir | +0.158 |
aints | +0.157 |
wcs | +0.147 |
jriwal | +0.145 |
Neg logit contributions | |
collateral | -0.145 |
atari | -0.136 |
hers | -0.116 |
リ | -0.116 |
Admiral | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
\": | +0.283 |
aints | +0.280 |
confir | +0.273 |
Sod | +0.258 |
rid | +0.256 |
Neg logit contributions | |
collateral | -0.316 |
atari | -0.302 |
リ | -0.261 |
hers | -0.258 |
inert | -0.253 |
Token |
|
Token ID | 198 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
confir | +0.297 |
aints | +0.288 |
\": | +0.288 |
wcs | +0.268 |
jriwal | +0.266 |
Neg logit contributions | |
collateral | -0.286 |
atari | -0.274 |
リ | -0.236 |
hers | -0.233 |
Admiral | -0.227 |
Token | � |
Token ID | 447 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
\": | +0.215 |
aints | +0.214 |
confir | +0.213 |
Sod | +0.196 |
wcs | +0.194 |
Neg logit contributions | |
collateral | -0.263 |
atari | -0.254 |
リ | -0.222 |
hers | -0.216 |
Admiral | -0.211 |
Token | characters |
Token ID | 3435 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
collateral | +0.058 |
atari | +0.055 |
リ | +0.047 |
hers | +0.046 |
inert | +0.045 |
Neg logit contributions | |
\": | -0.060 |
aints | -0.059 |
confir | -0.058 |
Sod | -0.054 |
rid | -0.054 |
Token | are |
Token ID | 389 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
collateral | +0.193 |
atari | +0.180 |
リ | +0.150 |
hers | +0.150 |
inert | +0.147 |
Neg logit contributions | |
\": | -0.231 |
aints | -0.230 |
confir | -0.225 |
Sod | -0.214 |
wcs | -0.214 |
Token | de |
Token ID | 390 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
collateral | +0.100 |
atari | +0.095 |
リ | +0.081 |
hers | +0.081 |
inert | +0.079 |
Neg logit contributions | |
\": | -0.097 |
aints | -0.097 |
confir | -0.094 |
wcs | -0.088 |
Sod | -0.088 |
Token | - |
Token ID | 12 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
collateral | +0.101 |
atari | +0.096 |
リ | +0.081 |
hers | +0.080 |
inert | +0.078 |
Neg logit contributions | |
\": | -0.116 |
aints | -0.114 |
confir | -0.113 |
Sod | -0.106 |
wcs | -0.106 |
Token | em |
Token ID | 368 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
collateral | +0.107 |
atari | +0.102 |
リ | +0.088 |
hers | +0.086 |
inert | +0.084 |
Neg logit contributions | |
\": | -0.106 |
aints | -0.104 |
confir | -0.103 |
Sod | -0.096 |
wcs | -0.096 |
Token | phas |
Token ID | 5902 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
\": | +0.014 |
confir | +0.014 |
aints | +0.013 |
Sod | +0.012 |
wcs | +0.012 |
Neg logit contributions | |
collateral | -0.022 |
atari | -0.021 |
リ | -0.019 |
hers | -0.018 |
Admiral | -0.018 |
Token | ized |
Token ID | 1143 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
\": | +1.823 |
aints | +1.807 |
confir | +1.768 |
Sod | +1.674 |
rid | +1.671 |
Neg logit contributions | |
collateral | -1.603 |
atari | -1.525 |
リ | -1.292 |
hers | -1.274 |
inert | -1.241 |
Token | or |
Token ID | 393 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
\": | +0.589 |
aints | +0.584 |
confir | +0.574 |
Sod | +0.540 |
rid | +0.538 |
Neg logit contributions | |
collateral | -0.525 |
atari | -0.495 |
リ | -0.418 |
hers | -0.415 |
inert | -0.404 |
Token | not |
Token ID | 407 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
\": | +0.135 |
aints | +0.133 |
confir | +0.131 |
Sod | +0.123 |
wcs | +0.123 |
Neg logit contributions | |
collateral | -0.122 |
atari | -0.115 |
リ | -0.098 |
hers | -0.097 |
inert | -0.095 |
Token | represented |
Token ID | 7997 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
\": | +0.288 |
aints | +0.284 |
confir | +0.279 |
Sod | +0.262 |
rid | +0.261 |
Neg logit contributions | |
collateral | -0.283 |
atari | -0.269 |
リ | -0.230 |
hers | -0.228 |
inert | -0.222 |
Token | at |
Token ID | 379 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
collateral | +0.064 |
atari | +0.060 |
リ | +0.050 |
hers | +0.050 |
inert | +0.048 |
Neg logit contributions | |
\": | -0.077 |
aints | -0.077 |
confir | -0.076 |
Sod | -0.071 |
rid | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
\": | +0.308 |
aints | +0.305 |
confir | +0.299 |
rid | +0.283 |
wcs | +0.283 |
Neg logit contributions | |
collateral | -0.256 |
atari | -0.240 |
リ | -0.202 |
hers | -0.202 |
Admiral | -0.196 |
Token | Save |
Token ID | 12793 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
collateral | +0.032 |
atari | +0.030 |
hers | +0.026 |
リ | +0.026 |
Admiral | +0.025 |
Neg logit contributions | |
\": | -0.035 |
aints | -0.034 |
confir | -0.033 |
rid | -0.032 |
wcs | -0.032 |
Token | Our |
Token ID | 3954 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
\": | +0.285 |
aints | +0.280 |
confir | +0.277 |
wcs | +0.260 |
rid | +0.258 |
Neg logit contributions | |
collateral | -0.258 |
atari | -0.243 |
リ | -0.208 |
hers | -0.205 |
Admiral | -0.200 |
Token | C |
Token ID | 327 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
\": | +0.361 |
confir | +0.353 |
aints | +0.353 |
wcs | +0.329 |
rid | +0.327 |
Neg logit contributions | |
collateral | -0.382 |
atari | -0.362 |
リ | -0.312 |
hers | -0.310 |
Admiral | -0.305 |
Token | em |
Token ID | 368 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
collateral | +0.063 |
atari | +0.060 |
リ | +0.052 |
hers | +0.051 |
intern | +0.050 |
Neg logit contributions | |
\": | -0.055 |
confir | -0.055 |
aints | -0.054 |
Sod | -0.051 |
wcs | -0.051 |
Token | eter |
Token ID | 2357 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
\": | +0.841 |
aints | +0.827 |
confir | +0.824 |
wcs | +0.772 |
Sod | +0.768 |
Neg logit contributions | |
collateral | -0.755 |
atari | -0.715 |
リ | -0.605 |
hers | -0.596 |
inert | -0.578 |
Token | ies |
Token ID | 444 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
\": | +1.484 |
confir | +1.451 |
aints | +1.436 |
Sod | +1.313 |
wcs | +1.312 |
Neg logit contributions | |
collateral | -2.401 |
atari | -2.317 |
リ | -2.057 |
hers | -2.026 |
Admiral | -1.989 |
Token | organization |
Token ID | 4009 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
collateral | +0.277 |
atari | +0.259 |
リ | +0.218 |
hers | +0.217 |
intern | +0.214 |
Neg logit contributions | |
\": | -0.314 |
aints | -0.308 |
confir | -0.303 |
wcs | -0.287 |
rid | -0.286 |
Token | to |
Token ID | 284 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
collateral | +0.211 |
atari | +0.197 |
リ | +0.166 |
hers | +0.166 |
Admiral | +0.160 |
Neg logit contributions | |
\": | -0.258 |
aints | -0.254 |
confir | -0.249 |
rid | -0.236 |
wcs | -0.235 |
Token | get |
Token ID | 651 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
collateral | +0.252 |
atari | +0.233 |
hers | +0.192 |
リ | +0.191 |
intern | +0.185 |
Neg logit contributions | |
\": | -0.379 |
aints | -0.375 |
confir | -0.365 |
wcs | -0.350 |
Sod | -0.349 |
Token | more |
Token ID | 517 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
collateral | +0.029 |
atari | +0.027 |
hers | +0.023 |
リ | +0.023 |
inert | +0.022 |
Neg logit contributions | |
\": | -0.033 |
aints | -0.033 |
confir | -0.032 |
wcs | -0.030 |
rid | -0.030 |
Token | which |
Token ID | 543 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
collateral | +0.169 |
atari | +0.159 |
リ | +0.136 |
hers | +0.132 |
intern | +0.129 |
Neg logit contributions | |
\": | -0.191 |
aints | -0.190 |
confir | -0.186 |
Sod | -0.177 |
wcs | -0.177 |
Token | we |
Token ID | 356 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
\": | +0.018 |
aints | +0.018 |
confir | +0.018 |
wcs | +0.017 |
Sod | +0.017 |
Neg logit contributions | |
collateral | -0.020 |
atari | -0.019 |
リ | -0.016 |
hers | -0.016 |
Admiral | -0.016 |
Token | � |
Token ID | 447 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
\": | +0.356 |
aints | +0.356 |
confir | +0.345 |
wcs | +0.330 |
Sod | +0.328 |
Neg logit contributions | |
collateral | -0.322 |
atari | -0.305 |
リ | -0.260 |
hers | -0.255 |
intern | -0.250 |
Token | � |
Token ID | 247 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
\": | +0.428 |
aints | +0.425 |
confir | +0.418 |
Sod | +0.396 |
rid | +0.394 |
Neg logit contributions | |
collateral | -0.331 |
atari | -0.313 |
リ | -0.262 |
hers | -0.258 |
inert | -0.250 |
Token | ll |
Token ID | 297 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
\": | +0.107 |
aints | +0.107 |
confir | +0.104 |
wcs | +0.097 |
Sod | +0.096 |
Neg logit contributions | |
collateral | -0.166 |
atari | -0.160 |
リ | -0.142 |
hers | -0.139 |
Admiral | -0.137 |
Token | talk |
Token ID | 1561 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
\": | +0.617 |
aints | +0.612 |
confir | +0.594 |
wcs | +0.567 |
Sod | +0.564 |
Neg logit contributions | |
collateral | -0.573 |
atari | -0.540 |
リ | -0.462 |
hers | -0.456 |
intern | -0.443 |
Token | about |
Token ID | 546 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
\": | +1.310 |
aints | +1.298 |
confir | +1.269 |
Sod | +1.192 |
rid | +1.187 |
Neg logit contributions | |
collateral | -1.414 |
atari | -1.347 |
リ | -1.163 |
hers | -1.145 |
inert | -1.121 |
Token | everything |
Token ID | 2279 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
\": | +0.285 |
aints | +0.285 |
confir | +0.278 |
Sod | +0.262 |
wcs | +0.262 |
Neg logit contributions | |
collateral | -0.270 |
atari | -0.255 |
リ | -0.217 |
hers | -0.214 |
inert | -0.209 |
Token | you |
Token ID | 345 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
collateral | +0.233 |
atari | +0.219 |
リ | +0.188 |
hers | +0.184 |
Admiral | +0.181 |
Neg logit contributions | |
\": | -0.247 |
aints | -0.246 |
confir | -0.241 |
rid | -0.228 |
Sod | -0.228 |
Token | should |
Token ID | 815 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
\": | +0.513 |
aints | +0.511 |
confir | +0.501 |
Sod | +0.472 |
rid | +0.470 |
Neg logit contributions | |
collateral | -0.472 |
atari | -0.449 |
リ | -0.385 |
hers | -0.374 |
Admiral | -0.365 |
Token | expect |
Token ID | 1607 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
collateral | +0.308 |
atari | +0.289 |
リ | +0.227 |
hers | +0.220 |
intern | +0.215 |
Neg logit contributions | |
\": | -0.596 |
aints | -0.594 |
confir | -0.582 |
Sod | -0.559 |
rid | -0.559 |