Token | challenges |
Token ID | 6459 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
arella | +0.015 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.018 |
intend | -0.017 |
ern | -0.016 |
baseman | -0.016 |
coat | -0.015 |
Token | are |
Token ID | 389 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
arella | +0.113 |
zin | +0.108 |
CFR | +0.107 |
RFC | +0.105 |
bish | +0.103 |
Neg logit contributions | |
desired | -0.102 |
intend | -0.099 |
ern | -0.095 |
baseman | -0.094 |
coat | -0.088 |
Token | on |
Token ID | 319 |
Feature activation | +9.40e-04 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | their |
Token ID | 511 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
arella | +0.000 |
zin | +0.000 |
CFR | +0.000 |
RFC | +0.000 |
bish | +0.000 |
Neg logit contributions | |
desired | -0.000 |
intend | -0.000 |
ern | -0.000 |
baseman | -0.000 |
coat | -0.000 |
Token | door |
Token ID | 3420 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
gang | +0.005 |
Neg logit contributions | |
arella | -0.013 |
CFR | -0.012 |
zin | -0.012 |
RFC | -0.012 |
bish | -0.012 |
Token | steps |
Token ID | 20214 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.008 |
CFR | +0.007 |
RFC | +0.007 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.069 |
intend | -0.068 |
ern | -0.066 |
baseman | -0.066 |
coat | -0.064 |
Token | — |
Token ID | 960 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
arella | +0.375 |
zin | +0.359 |
CFR | +0.357 |
RFC | +0.349 |
bish | +0.344 |
Neg logit contributions | |
desired | -0.310 |
intend | -0.299 |
ern | -0.286 |
baseman | -0.284 |
coat | -0.264 |
Token | ref |
Token ID | 5420 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
desired | +0.053 |
intend | +0.051 |
ern | +0.048 |
baseman | +0.048 |
coat | +0.045 |
Neg logit contributions | |
arella | -0.062 |
zin | -0.060 |
CFR | -0.059 |
RFC | -0.058 |
bish | -0.057 |
Token | uge |
Token ID | 2217 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
arella | +0.072 |
zin | +0.069 |
CFR | +0.069 |
RFC | +0.067 |
bish | +0.066 |
Neg logit contributions | |
desired | -0.063 |
intend | -0.060 |
baseman | -0.058 |
ern | -0.058 |
coat | -0.054 |
Token | e |
Token ID | 68 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
desired | +0.025 |
intend | +0.024 |
ern | +0.024 |
baseman | +0.023 |
gang | +0.022 |
Neg logit contributions | |
arella | -0.024 |
zin | -0.023 |
CFR | -0.023 |
RFC | -0.022 |
bish | -0.022 |
Token | integration |
Token ID | 11812 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
arella | +0.036 |
zin | +0.034 |
CFR | +0.034 |
RFC | +0.033 |
bish | +0.032 |
Neg logit contributions | |
desired | -0.044 |
intend | -0.043 |
ern | -0.042 |
baseman | -0.041 |
gang | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +8.63e-03 |
Pos logit contributions | |
arella | +0.028 |
zin | +0.026 |
CFR | +0.026 |
RFC | +0.026 |
bish | +0.025 |
Neg logit contributions | |
desired | -0.023 |
intend | -0.022 |
ern | -0.021 |
baseman | -0.021 |
coat | -0.019 |
Token | South |
Token ID | 2520 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | Carolina |
Token ID | 5913 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
arella | +0.027 |
zin | +0.025 |
CFR | +0.025 |
RFC | +0.025 |
bish | +0.024 |
Neg logit contributions | |
desired | -0.031 |
intend | -0.030 |
ern | -0.029 |
baseman | -0.029 |
coat | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
arella | +0.027 |
zin | +0.026 |
CFR | +0.026 |
RFC | +0.025 |
bish | +0.025 |
Neg logit contributions | |
desired | -0.021 |
intend | -0.020 |
ern | -0.019 |
baseman | -0.019 |
coat | -0.017 |
Token | but |
Token ID | 475 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
desired | +0.000 |
intend | +0.000 |
ern | +0.000 |
baseman | +0.000 |
coat | +0.000 |
Neg logit contributions | |
arella | -0.000 |
zin | -0.000 |
CFR | -0.000 |
RFC | -0.000 |
bish | -0.000 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | refused |
Token ID | 6520 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
arella | +0.350 |
zin | +0.335 |
CFR | +0.334 |
RFC | +0.327 |
bish | +0.322 |
Neg logit contributions | |
desired | -0.295 |
intend | -0.284 |
ern | -0.272 |
baseman | -0.270 |
coat | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.003 |
ern | -0.003 |
baseman | -0.003 |
coat | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.004 |
Token | � |
Token ID | 447 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.005 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
gang | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.005 |
Token | Others |
Token ID | 25599 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
gang | -0.001 |
Token | say |
Token ID | 910 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.007 |
bish | -0.007 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
desired | +0.012 |
intend | +0.011 |
ern | +0.011 |
baseman | +0.011 |
coat | +0.010 |
Neg logit contributions | |
arella | -0.009 |
zin | -0.009 |
CFR | -0.009 |
RFC | -0.009 |
bish | -0.008 |
Token | has |
Token ID | 468 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
arella | +0.316 |
zin | +0.301 |
CFR | +0.299 |
RFC | +0.292 |
bish | +0.287 |
Neg logit contributions | |
desired | -0.327 |
intend | -0.316 |
ern | -0.304 |
baseman | -0.302 |
coat | -0.283 |
Token | been |
Token ID | 587 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
arella | +0.017 |
zin | +0.016 |
CFR | +0.016 |
RFC | +0.016 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.014 |
intend | -0.014 |
ern | -0.013 |
baseman | -0.013 |
coat | -0.012 |
Token | reluctant |
Token ID | 18416 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.017 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.020 |
zin | -0.019 |
CFR | -0.019 |
RFC | -0.018 |
bish | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
desired | +0.101 |
intend | +0.098 |
ern | +0.094 |
baseman | +0.093 |
coat | +0.087 |
Neg logit contributions | |
arella | -0.106 |
zin | -0.101 |
CFR | -0.101 |
RFC | -0.099 |
bish | -0.098 |
Token | take |
Token ID | 1011 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
gang | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.47e-03 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
baseman | -0.002 |
ern | -0.002 |
coat | -0.001 |
Token | But |
Token ID | 1537 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.003 |
Token | according |
Token ID | 1864 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
desired | +0.036 |
intend | +0.035 |
ern | +0.033 |
baseman | +0.033 |
coat | +0.031 |
Neg logit contributions | |
arella | -0.039 |
zin | -0.037 |
CFR | -0.037 |
RFC | -0.036 |
bish | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +7.49e-03 |
Pos logit contributions | |
desired | +0.023 |
intend | +0.022 |
ern | +0.021 |
baseman | +0.021 |
coat | +0.020 |
Neg logit contributions | |
arella | -0.022 |
zin | -0.021 |
CFR | -0.021 |
RFC | -0.020 |
bish | -0.020 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
arella | +0.321 |
zin | +0.306 |
CFR | +0.305 |
RFC | +0.298 |
bish | +0.293 |
Neg logit contributions | |
desired | -0.317 |
intend | -0.306 |
ern | -0.295 |
baseman | -0.292 |
coat | -0.274 |
Token | her |
Token ID | 607 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
arella | +0.011 |
zin | +0.011 |
CFR | +0.011 |
RFC | +0.010 |
bish | +0.010 |
Neg logit contributions | |
desired | -0.012 |
intend | -0.012 |
ern | -0.011 |
baseman | -0.011 |
coat | -0.010 |
Token | allies |
Token ID | 7681 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
arella | +0.039 |
zin | +0.036 |
CFR | +0.036 |
RFC | +0.035 |
bish | +0.035 |
Neg logit contributions | |
desired | -0.049 |
intend | -0.048 |
ern | -0.046 |
baseman | -0.046 |
coat | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
arella | +0.159 |
zin | +0.152 |
CFR | +0.151 |
RFC | +0.148 |
bish | +0.146 |
Neg logit contributions | |
desired | -0.139 |
intend | -0.134 |
ern | -0.129 |
baseman | -0.128 |
coat | -0.119 |
Token | her |
Token ID | 607 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | technical |
Token ID | 6276 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | colleges |
Token ID | 15273 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
arella | +0.062 |
zin | +0.058 |
CFR | +0.057 |
RFC | +0.056 |
bish | +0.055 |
Neg logit contributions | |
desired | -0.088 |
intend | -0.085 |
ern | -0.083 |
baseman | -0.082 |
coat | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
arella | +0.009 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.008 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.007 |
intend | -0.007 |
ern | -0.006 |
baseman | -0.006 |
coat | -0.006 |
Token | Thanks |
Token ID | 6930 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
desired | +0.011 |
intend | +0.011 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.010 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.011 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | � |
Token ID | 447 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
arella | +0.329 |
zin | +0.314 |
CFR | +0.313 |
RFC | +0.306 |
bish | +0.302 |
Neg logit contributions | |
desired | -0.307 |
intend | -0.296 |
ern | -0.285 |
baseman | -0.281 |
coat | -0.264 |
Token | � |
Token ID | 247 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
Emir | +0.005 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.004 |
Token | maneuver |
Token ID | 20186 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | ing |
Token ID | 278 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
arella | +0.066 |
zin | +0.062 |
CFR | +0.062 |
RFC | +0.061 |
bish | +0.060 |
Neg logit contributions | |
desired | -0.063 |
intend | -0.060 |
ern | -0.058 |
baseman | -0.058 |
coat | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
arella | +0.051 |
zin | +0.049 |
CFR | +0.049 |
RFC | +0.048 |
bish | +0.047 |
Neg logit contributions | |
desired | -0.045 |
intend | -0.044 |
ern | -0.042 |
baseman | -0.042 |
coat | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
arella | +0.008 |
zin | +0.008 |
CFR | +0.008 |
RFC | +0.008 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.006 |
ern | -0.006 |
baseman | -0.005 |
coat | -0.005 |
Token | early |
Token ID | 1903 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | voting |
Token ID | 6709 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
desired | +0.103 |
intend | +0.100 |
ern | +0.097 |
baseman | +0.096 |
coat | +0.091 |
Neg logit contributions | |
arella | -0.061 |
zin | -0.057 |
CFR | -0.056 |
RFC | -0.055 |
bish | -0.053 |
Token | period |
Token ID | 2278 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
arella | +0.117 |
zin | +0.112 |
CFR | +0.111 |
RFC | +0.109 |
bish | +0.107 |
Neg logit contributions | |
desired | -0.111 |
intend | -0.107 |
ern | -0.102 |
baseman | -0.102 |
coat | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
desired | +0.094 |
intend | +0.090 |
ern | +0.087 |
baseman | +0.086 |
coat | +0.080 |
Neg logit contributions | |
arella | -0.105 |
zin | -0.101 |
CFR | -0.100 |
RFC | -0.098 |
bish | -0.097 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
desired | +0.000 |
intend | +0.000 |
ern | +0.000 |
baseman | +0.000 |
coat | +0.000 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | told |
Token ID | 1297 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
arella | +0.343 |
zin | +0.328 |
CFR | +0.327 |
RFC | +0.320 |
bish | +0.316 |
Neg logit contributions | |
desired | -0.294 |
intend | -0.282 |
ern | -0.270 |
baseman | -0.268 |
coat | -0.249 |
Token | HuffPost |
Token ID | 35130 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
arella | +0.020 |
zin | +0.019 |
CFR | +0.019 |
RFC | +0.018 |
bish | +0.018 |
Neg logit contributions | |
desired | -0.030 |
intend | -0.029 |
ern | -0.028 |
baseman | -0.028 |
coat | -0.027 |
Token | in |
Token ID | 287 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
arella | +0.102 |
zin | +0.098 |
CFR | +0.098 |
RFC | +0.096 |
bish | +0.095 |
Neg logit contributions | |
desired | -0.080 |
intend | -0.077 |
ern | -0.074 |
baseman | -0.073 |
coat | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.003 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | statement |
Token ID | 2643 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.007 |
CFR | -0.007 |
RFC | -0.007 |
bish | -0.007 |
Token | representative |
Token ID | 8852 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
desired | +0.053 |
intend | +0.051 |
ern | +0.049 |
baseman | +0.049 |
coat | +0.046 |
Neg logit contributions | |
arella | -0.049 |
zin | -0.046 |
CFR | -0.046 |
RFC | -0.045 |
bish | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +9.19e-03 |
Pos logit contributions | |
desired | +0.035 |
intend | +0.034 |
ern | +0.032 |
baseman | +0.032 |
coat | +0.030 |
Neg logit contributions | |
arella | -0.040 |
zin | -0.038 |
CFR | -0.038 |
RFC | -0.037 |
bish | -0.036 |
Token | she |
Token ID | 673 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.013 |
zin | -0.012 |
CFR | -0.012 |
RFC | -0.012 |
bish | -0.012 |
Token | asked |
Token ID | 1965 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.013 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.015 |
CFR | -0.015 |
RFC | -0.014 |
bish | -0.014 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
arella | +0.132 |
zin | +0.126 |
CFR | +0.125 |
RFC | +0.122 |
bish | +0.120 |
Neg logit contributions | |
desired | -0.151 |
intend | -0.146 |
ern | -0.141 |
baseman | -0.140 |
coat | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
arella | +0.302 |
zin | +0.287 |
CFR | +0.285 |
RFC | +0.278 |
bish | +0.274 |
Neg logit contributions | |
desired | -0.328 |
intend | -0.317 |
ern | -0.306 |
baseman | -0.304 |
coat | -0.285 |
Token | initiate |
Token ID | 22118 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
arella | +0.000 |
zin | +0.000 |
CFR | +0.000 |
RFC | +0.000 |
bish | +0.000 |
Neg logit contributions | |
desired | -0.000 |
intend | -0.000 |
ern | -0.000 |
baseman | -0.000 |
coat | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
desired | +0.039 |
intend | +0.038 |
ern | +0.036 |
baseman | +0.036 |
coat | +0.033 |
Neg logit contributions | |
arella | -0.047 |
zin | -0.045 |
CFR | -0.045 |
RFC | -0.044 |
bish | -0.043 |
Token | push |
Token ID | 4574 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
desired | +0.045 |
intend | +0.044 |
ern | +0.042 |
baseman | +0.042 |
coat | +0.039 |
Neg logit contributions | |
arella | -0.043 |
zin | -0.041 |
CFR | -0.041 |
RFC | -0.040 |
bish | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.013 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.015 |
CFR | -0.015 |
RFC | -0.014 |
bish | -0.014 |
Token | For |
Token ID | 1114 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
gang | +0.006 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.005 |
bish | -0.005 |
RFC | -0.005 |
Token | one |
Token ID | 530 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
arella | +0.037 |
zin | +0.035 |
CFR | +0.035 |
RFC | +0.034 |
bish | +0.034 |
Neg logit contributions | |
desired | -0.034 |
intend | -0.033 |
ern | -0.031 |
baseman | -0.031 |
coat | -0.029 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
desired | +0.019 |
intend | +0.018 |
ern | +0.018 |
baseman | +0.017 |
coat | +0.016 |
Neg logit contributions | |
arella | -0.022 |
zin | -0.021 |
CFR | -0.021 |
RFC | -0.021 |
bish | -0.020 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | has |
Token ID | 468 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
arella | +0.300 |
zin | +0.285 |
CFR | +0.284 |
RFC | +0.277 |
bish | +0.273 |
Neg logit contributions | |
desired | -0.330 |
intend | -0.319 |
ern | -0.307 |
baseman | -0.304 |
coat | -0.286 |
Token | embraced |
Token ID | 18079 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.010 |
CFR | +0.010 |
RFC | +0.009 |
bish | +0.009 |
Neg logit contributions | |
desired | -0.009 |
intend | -0.008 |
ern | -0.008 |
baseman | -0.008 |
coat | -0.007 |
Token | Evans |
Token ID | 13922 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
arella | +0.036 |
zin | +0.034 |
CFR | +0.034 |
RFC | +0.034 |
bish | +0.033 |
Neg logit contributions | |
desired | -0.030 |
intend | -0.029 |
ern | -0.028 |
baseman | -0.027 |
coat | -0.026 |
Token | � |
Token ID | 447 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
arella | +0.064 |
zin | +0.061 |
CFR | +0.060 |
RFC | +0.059 |
bish | +0.058 |
Neg logit contributions | |
desired | -0.073 |
intend | -0.071 |
ern | -0.069 |
baseman | -0.068 |
coat | -0.064 |
Token | � |
Token ID | 247 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
arella | +0.008 |
zin | +0.007 |
CFR | +0.007 |
RFC | +0.007 |
bish | +0.007 |
Neg logit contributions | |
desired | -0.007 |
intend | -0.007 |
baseman | -0.006 |
ern | -0.006 |
coat | -0.006 |
Token | we |
Token ID | 356 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
arella | +0.030 |
zin | +0.028 |
CFR | +0.028 |
RFC | +0.027 |
bish | +0.026 |
Neg logit contributions | |
desired | -0.044 |
intend | -0.043 |
ern | -0.041 |
baseman | -0.041 |
coat | -0.039 |
Token | need |
Token ID | 761 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
arella | +0.061 |
zin | +0.059 |
CFR | +0.059 |
RFC | +0.057 |
bish | +0.057 |
Neg logit contributions | |
desired | -0.041 |
intend | -0.040 |
ern | -0.038 |
baseman | -0.037 |
coat | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
desired | +0.045 |
intend | +0.043 |
ern | +0.042 |
baseman | +0.041 |
coat | +0.038 |
Neg logit contributions | |
arella | -0.053 |
zin | -0.051 |
CFR | -0.051 |
RFC | -0.050 |
bish | -0.049 |
Token | � |
Token ID | 447 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
desired | +0.009 |
intend | +0.008 |
ern | +0.008 |
baseman | +0.008 |
coat | +0.008 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | � |
Token ID | 251 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.004 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
desired | +0.015 |
intend | +0.015 |
ern | +0.014 |
baseman | +0.014 |
coat | +0.013 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
arella | +0.346 |
zin | +0.331 |
CFR | +0.330 |
RFC | +0.324 |
bish | +0.319 |
Neg logit contributions | |
desired | -0.283 |
intend | -0.271 |
ern | -0.260 |
baseman | -0.257 |
coat | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.012 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.016 |
zin | -0.016 |
CFR | -0.016 |
RFC | -0.015 |
bish | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.008 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.008 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.005 |
Token | She |
Token ID | 3347 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | His |
Token ID | 2399 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
desired | +0.027 |
intend | +0.026 |
ern | +0.025 |
baseman | +0.025 |
coat | +0.023 |
Neg logit contributions | |
arella | -0.028 |
zin | -0.027 |
CFR | -0.027 |
RFC | -0.026 |
bish | -0.026 |
Token | Cous |
Token ID | 27456 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
desired | +0.067 |
intend | +0.065 |
ern | +0.062 |
baseman | +0.062 |
coat | +0.057 |
Neg logit contributions | |
arella | -0.070 |
zin | -0.067 |
CFR | -0.067 |
RFC | -0.065 |
bish | -0.064 |
Token | in |
Token ID | 259 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
arella | +0.042 |
zin | +0.040 |
CFR | +0.040 |
bish | +0.038 |
RFC | +0.038 |
Neg logit contributions | |
desired | -0.035 |
intend | -0.034 |
baseman | -0.032 |
ern | -0.032 |
ocked | -0.030 |
Token | - |
Token ID | 12 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
desired | +0.027 |
intend | +0.026 |
ern | +0.025 |
baseman | +0.025 |
coat | +0.023 |
Neg logit contributions | |
arella | -0.031 |
zin | -0.030 |
CFR | -0.029 |
RFC | -0.029 |
bish | -0.028 |
Token | JJ |
Token ID | 32178 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
desired | +0.011 |
intend | +0.011 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.010 |
Neg logit contributions | |
arella | -0.010 |
zin | -0.010 |
CFR | -0.010 |
RFC | -0.009 |
bish | -0.009 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
desired | +0.029 |
intend | +0.028 |
ern | +0.027 |
baseman | +0.026 |
coat | +0.025 |
Neg logit contributions | |
arella | -0.029 |
zin | -0.028 |
CFR | -0.027 |
RFC | -0.027 |
bish | -0.026 |
Token | - |
Token ID | 12 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
arella | +0.321 |
zin | +0.307 |
CFR | +0.305 |
RFC | +0.298 |
bish | +0.294 |
Neg logit contributions | |
desired | -0.305 |
intend | -0.295 |
ern | -0.283 |
baseman | -0.281 |
coat | -0.262 |
Token | G |
Token ID | 38 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.009 |
ern | +0.009 |
baseman | +0.009 |
coat | +0.008 |
Neg logit contributions | |
arella | -0.009 |
zin | -0.009 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.008 |
Token | ett |
Token ID | 3087 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
desired | +0.037 |
intend | +0.036 |
ern | +0.035 |
baseman | +0.034 |
coat | +0.032 |
Neg logit contributions | |
arella | -0.038 |
zin | -0.036 |
CFR | -0.036 |
RFC | -0.035 |
bish | -0.034 |
Token | in |
Token ID | 259 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
arella | +0.014 |
zin | +0.013 |
CFR | +0.013 |
RFC | +0.013 |
bish | +0.013 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.011 |
baseman | -0.010 |
ern | -0.010 |
coat | -0.010 |
Token | Old |
Token ID | 5706 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
desired | +0.031 |
intend | +0.030 |
ern | +0.029 |
baseman | +0.029 |
coat | +0.027 |
Neg logit contributions | |
arella | -0.032 |
zin | -0.031 |
CFR | -0.030 |
RFC | -0.030 |
bish | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
desired | +0.033 |
intend | +0.031 |
ern | +0.030 |
baseman | +0.030 |
coat | +0.028 |
Neg logit contributions | |
arella | -0.041 |
zin | -0.040 |
CFR | -0.040 |
RFC | -0.039 |
bish | -0.038 |
Token | approaches |
Token ID | 10581 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
arella | +0.008 |
zin | +0.008 |
CFR | +0.008 |
RFC | +0.008 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.009 |
intend | -0.008 |
ern | -0.008 |
baseman | -0.008 |
coat | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
desired | +0.052 |
intend | +0.050 |
ern | +0.048 |
baseman | +0.047 |
coat | +0.044 |
Neg logit contributions | |
arella | -0.060 |
zin | -0.058 |
CFR | -0.058 |
RFC | -0.056 |
bish | -0.056 |
Token | governing |
Token ID | 15030 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
arella | +0.078 |
zin | +0.075 |
CFR | +0.074 |
RFC | +0.072 |
bish | +0.071 |
Neg logit contributions | |
desired | -0.070 |
intend | -0.068 |
ern | -0.065 |
baseman | -0.065 |
coat | -0.061 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | consistently |
Token ID | 9835 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
arella | +0.320 |
zin | +0.306 |
CFR | +0.304 |
RFC | +0.297 |
bish | +0.293 |
Neg logit contributions | |
desired | -0.306 |
intend | -0.295 |
ern | -0.283 |
baseman | -0.280 |
coat | -0.263 |
Token | favored |
Token ID | 19344 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | compromise |
Token ID | 13110 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
desired | +0.097 |
intend | +0.093 |
ern | +0.089 |
baseman | +0.089 |
coat | +0.083 |
Neg logit contributions | |
arella | -0.109 |
zin | -0.105 |
CFR | -0.104 |
RFC | -0.102 |
bish | -0.100 |
Token | with |
Token ID | 351 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
desired | +0.029 |
intend | +0.028 |
ern | +0.026 |
baseman | +0.026 |
coat | +0.025 |
Neg logit contributions | |
arella | -0.031 |
zin | -0.030 |
CFR | -0.030 |
RFC | -0.029 |
bish | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.010 |
CFR | +0.010 |
RFC | +0.009 |
bish | +0.009 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.010 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.009 |
Token | voting |
Token ID | 6709 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
desired | +0.110 |
intend | +0.107 |
ern | +0.104 |
baseman | +0.103 |
coat | +0.098 |
Neg logit contributions | |
arella | -0.060 |
zin | -0.056 |
CFR | -0.055 |
RFC | -0.054 |
bish | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
arella | +0.113 |
zin | +0.108 |
CFR | +0.107 |
RFC | +0.105 |
bish | +0.103 |
Neg logit contributions | |
desired | -0.102 |
intend | -0.098 |
ern | -0.094 |
baseman | -0.093 |
coat | -0.087 |
Token |
|
Token ID | 198 |
Feature activation | +1.60e-03 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.008 |
ern | +0.008 |
baseman | +0.008 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.007 |
CFR | -0.007 |
RFC | -0.007 |
bish | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
arella | +0.000 |
zin | +0.000 |
CFR | +0.000 |
RFC | +0.000 |
bish | +0.000 |
Neg logit contributions | |
desired | -0.000 |
intend | -0.000 |
ern | -0.000 |
baseman | -0.000 |
coat | -0.000 |
Token | But |
Token ID | 1537 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
CFR | -0.001 |
zin | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | Abrams |
Token ID | 32414 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
desired | +0.047 |
intend | +0.046 |
ern | +0.044 |
baseman | +0.044 |
coat | +0.041 |
Neg logit contributions | |
arella | -0.038 |
zin | -0.036 |
CFR | -0.036 |
RFC | -0.035 |
bish | -0.034 |
Token | � |
Token ID | 447 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
arella | +0.303 |
zin | +0.289 |
CFR | +0.287 |
RFC | +0.280 |
bish | +0.276 |
Neg logit contributions | |
desired | -0.322 |
intend | -0.311 |
ern | -0.300 |
baseman | -0.297 |
coat | -0.279 |
Token | � |
Token ID | 247 |
Feature activation | +2.56e-04 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.004 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.004 |
Token | detractors |
Token ID | 45642 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
arella | +0.000 |
zin | +0.000 |
CFR | +0.000 |
RFC | +0.000 |
bish | +0.000 |
Neg logit contributions | |
desired | -0.000 |
intend | -0.000 |
ern | -0.000 |
baseman | -0.000 |
coat | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
arella | +0.041 |
zin | +0.039 |
CFR | +0.039 |
RFC | +0.038 |
bish | +0.037 |
Neg logit contributions | |
desired | -0.038 |
intend | -0.036 |
ern | -0.035 |
baseman | -0.035 |
coat | -0.032 |
Token | cynical |
Token ID | 28858 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
desired | +0.011 |
intend | +0.010 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.011 |
Token | two |
Token ID | 734 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
arella | +0.043 |
zin | +0.041 |
CFR | +0.041 |
RFC | +0.040 |
bish | +0.039 |
Neg logit contributions | |
desired | -0.040 |
intend | -0.038 |
ern | -0.037 |
baseman | -0.037 |
coat | -0.034 |
Token | more |
Token ID | 517 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
desired | +0.042 |
intend | +0.041 |
ern | +0.039 |
baseman | +0.039 |
coat | +0.037 |
Neg logit contributions | |
arella | -0.035 |
zin | -0.033 |
CFR | -0.033 |
RFC | -0.032 |
bish | -0.031 |
Token | scenarios |
Token ID | 13858 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
arella | +0.007 |
zin | +0.007 |
CFR | +0.007 |
RFC | +0.006 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.008 |
baseman | -0.008 |
coat | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
desired | +0.037 |
intend | +0.036 |
ern | +0.034 |
baseman | +0.034 |
coat | +0.032 |
Neg logit contributions | |
arella | -0.044 |
zin | -0.042 |
CFR | -0.042 |
RFC | -0.041 |
bish | -0.040 |
Token | could |
Token ID | 714 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | shuffle |
Token ID | 36273 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
arella | +0.021 |
zin | +0.020 |
CFR | +0.020 |
RFC | +0.020 |
bish | +0.019 |
Neg logit contributions | |
desired | -0.017 |
intend | -0.016 |
ern | -0.016 |
baseman | -0.015 |
coat | -0.014 |
Token | things |
Token ID | 1243 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
arella | +0.332 |
CFR | +0.318 |
zin | +0.317 |
RFC | +0.308 |
bish | +0.305 |
Neg logit contributions | |
desired | -0.286 |
intend | -0.279 |
ern | -0.266 |
baseman | -0.264 |
coat | -0.246 |
Token | around |
Token ID | 1088 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
desired | +0.042 |
intend | +0.041 |
ern | +0.039 |
baseman | +0.039 |
coat | +0.036 |
Neg logit contributions | |
arella | -0.049 |
zin | -0.047 |
CFR | -0.047 |
RFC | -0.046 |
bish | -0.045 |
Token | for |
Token ID | 329 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
arella | +0.076 |
zin | +0.073 |
CFR | +0.072 |
RFC | +0.071 |
bish | +0.070 |
Neg logit contributions | |
desired | -0.064 |
intend | -0.062 |
ern | -0.059 |
baseman | -0.059 |
coat | -0.055 |
Token | Hong |
Token ID | 9764 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
arella | +0.016 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.015 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.018 |
intend | -0.017 |
ern | -0.017 |
baseman | -0.016 |
coat | -0.016 |
Token | Kong |
Token ID | 9071 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
baseman | +0.009 |
ern | +0.009 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.009 |
zin | -0.009 |
CFR | -0.009 |
RFC | -0.009 |
bish | -0.009 |
Token | group |
Token ID | 1448 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
desired | +0.044 |
intend | +0.043 |
ern | +0.041 |
baseman | +0.041 |
coat | +0.038 |
Neg logit contributions | |
arella | -0.041 |
zin | -0.039 |
CFR | -0.039 |
RFC | -0.038 |
bish | -0.037 |
Token | Raqqa |
Token ID | 30391 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
desired | +0.038 |
intend | +0.037 |
ern | +0.036 |
baseman | +0.035 |
coat | +0.033 |
Neg logit contributions | |
arella | -0.041 |
zin | -0.039 |
CFR | -0.039 |
RFC | -0.038 |
bish | -0.037 |
Token | is |
Token ID | 318 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
desired | +0.065 |
intend | +0.063 |
ern | +0.060 |
baseman | +0.060 |
coat | +0.056 |
Neg logit contributions | |
arella | -0.071 |
zin | -0.067 |
CFR | -0.067 |
RFC | -0.066 |
bish | -0.065 |
Token | Being |
Token ID | 11204 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
baseman | +0.009 |
ern | +0.009 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.008 |
CFR | -0.008 |
zin | -0.008 |
RFC | -0.008 |
Emir | -0.007 |
Token | Sl |
Token ID | 3454 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.007 |
CFR | -0.007 |
zin | -0.007 |
RFC | -0.007 |
bish | -0.006 |
Token | aughtered |
Token ID | 32734 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
desired | +0.141 |
intend | +0.138 |
ern | +0.135 |
baseman | +0.134 |
coat | +0.130 |
Neg logit contributions | |
arella | -0.022 |
zin | -0.018 |
CFR | -0.018 |
RFC | -0.016 |
bish | -0.015 |
Token | Sil |
Token ID | 4243 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
arella | +0.297 |
zin | +0.286 |
CFR | +0.284 |
RFC | +0.276 |
bish | +0.273 |
Neg logit contributions | |
desired | -0.312 |
intend | -0.306 |
ern | -0.292 |
baseman | -0.291 |
coat | -0.272 |
Token | ently |
Token ID | 1473 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
arella | +0.021 |
zin | +0.020 |
CFR | +0.020 |
RFC | +0.020 |
bish | +0.019 |
Neg logit contributions | |
desired | -0.018 |
intend | -0.017 |
ern | -0.016 |
baseman | -0.016 |
coat | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.005 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | unnecessary |
Token ID | 13114 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
arella | +0.008 |
zin | +0.007 |
CFR | +0.007 |
RFC | +0.007 |
bish | +0.007 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.007 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | dupl |
Token ID | 14184 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
desired | +0.120 |
intend | +0.116 |
ern | +0.112 |
baseman | +0.111 |
coat | +0.104 |
Neg logit contributions | |
arella | -0.115 |
zin | -0.109 |
CFR | -0.108 |
RFC | -0.106 |
bish | -0.104 |
Token | icates |
Token ID | 16856 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
arella | +0.013 |
zin | +0.012 |
CFR | +0.012 |
RFC | +0.012 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.014 |
intend | -0.014 |
ern | -0.013 |
baseman | -0.013 |
coat | -0.012 |
Token | . |
Token ID | 764 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
arella | +0.034 |
zin | +0.033 |
CFR | +0.033 |
RFC | +0.032 |
bish | +0.031 |
Neg logit contributions | |
desired | -0.031 |
intend | -0.030 |
ern | -0.029 |
baseman | -0.028 |
coat | -0.027 |
Token | . |
Token ID | 764 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
arella | +0.089 |
zin | +0.083 |
CFR | +0.083 |
RFC | +0.080 |
bish | +0.078 |
Neg logit contributions | |
desired | -0.154 |
intend | -0.150 |
ern | -0.146 |
baseman | -0.145 |
coat | -0.138 |
Token | ." |
Token ID | 22135 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
arella | +0.087 |
zin | +0.081 |
CFR | +0.080 |
RFC | +0.077 |
bish | +0.075 |
Neg logit contributions | |
desired | -0.161 |
intend | -0.157 |
ern | -0.152 |
baseman | -0.151 |
coat | -0.144 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
arella | +0.271 |
zin | +0.258 |
CFR | +0.257 |
RFC | +0.249 |
bish | +0.245 |
Neg logit contributions | |
desired | -0.326 |
intend | -0.317 |
ern | -0.305 |
baseman | -0.304 |
coat | -0.286 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.003 |
baseman | -0.003 |
ern | -0.003 |
coat | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.003 |
ern | -0.003 |
baseman | -0.003 |
coat | -0.002 |
Token | excerpt |
Token ID | 20911 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | from |
Token ID | 422 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
arella | +0.121 |
zin | +0.117 |
CFR | +0.116 |
RFC | +0.114 |
bish | +0.112 |
Neg logit contributions | |
desired | -0.083 |
intend | -0.079 |
ern | -0.076 |
baseman | -0.075 |
coat | -0.069 |
Token | was |
Token ID | 373 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
desired | +0.034 |
intend | +0.033 |
ern | +0.031 |
baseman | +0.031 |
coat | +0.029 |
Neg logit contributions | |
arella | -0.038 |
zin | -0.037 |
CFR | -0.036 |
RFC | -0.036 |
bish | -0.035 |
Token | pulled |
Token ID | 5954 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
desired | +0.022 |
intend | +0.021 |
ern | +0.020 |
baseman | +0.020 |
coat | +0.019 |
Neg logit contributions | |
arella | -0.025 |
zin | -0.024 |
CFR | -0.024 |
RFC | -0.024 |
bish | -0.023 |
Token | at |
Token ID | 379 |
Feature activation | +6.84e-02 |
Pos logit contributions | |
arella | +0.046 |
zin | +0.044 |
CFR | +0.044 |
RFC | +0.043 |
bish | +0.042 |
Neg logit contributions | |
desired | -0.039 |
intend | -0.038 |
ern | -0.036 |
baseman | -0.036 |
coat | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
arella | +0.014 |
zin | +0.013 |
CFR | +0.013 |
RFC | +0.013 |
bish | +0.013 |
Neg logit contributions | |
desired | -0.012 |
intend | -0.012 |
ern | -0.011 |
baseman | -0.011 |
coat | -0.011 |
Token | ele |
Token ID | 9766 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | venth |
Token ID | 20987 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
desired | +0.125 |
intend | +0.123 |
ern | +0.120 |
baseman | +0.119 |
gang | +0.115 |
Neg logit contributions | |
arella | -0.022 |
zin | -0.018 |
CFR | -0.018 |
RFC | -0.017 |
bish | -0.015 |
Token | hour |
Token ID | 1711 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
arella | +0.365 |
zin | +0.351 |
CFR | +0.349 |
RFC | +0.343 |
bish | +0.339 |
Neg logit contributions | |
desired | -0.233 |
intend | -0.223 |
ern | -0.212 |
baseman | -0.210 |
coat | -0.192 |
Token | when |
Token ID | 618 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
arella | +0.012 |
zin | +0.012 |
CFR | +0.012 |
RFC | +0.012 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.010 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
desired | +0.042 |
intend | +0.041 |
ern | +0.039 |
baseman | +0.039 |
coat | +0.036 |
Neg logit contributions | |
arella | -0.045 |
zin | -0.042 |
CFR | -0.042 |
RFC | -0.041 |
bish | -0.041 |
Token | Russian |
Token ID | 3394 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
arella | +0.072 |
zin | +0.068 |
CFR | +0.068 |
RFC | +0.066 |
bish | +0.065 |
Neg logit contributions | |
desired | -0.070 |
intend | -0.067 |
ern | -0.065 |
baseman | -0.064 |
coat | -0.060 |
Token | 's |
Token ID | 338 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
arella | +0.018 |
zin | +0.017 |
CFR | +0.017 |
RFC | +0.017 |
bish | +0.017 |
Neg logit contributions | |
desired | -0.019 |
intend | -0.019 |
ern | -0.018 |
baseman | -0.018 |
gang | -0.017 |
Token | next |
Token ID | 1306 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
arella | +0.026 |
CFR | +0.025 |
zin | +0.025 |
RFC | +0.024 |
bish | +0.024 |
Neg logit contributions | |
desired | -0.029 |
intend | -0.029 |
ern | -0.028 |
baseman | -0.027 |
gang | -0.026 |
Token | president |
Token ID | 1893 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
desired | +0.050 |
intend | +0.048 |
ern | +0.046 |
baseman | +0.046 |
coat | +0.043 |
Neg logit contributions | |
arella | -0.043 |
zin | -0.041 |
CFR | -0.041 |
RFC | -0.040 |
bish | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
desired | +0.014 |
intend | +0.013 |
ern | +0.013 |
baseman | +0.013 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.016 |
zin | -0.016 |
CFR | -0.015 |
RFC | -0.015 |
bish | -0.015 |
Token | former |
Token ID | 1966 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.003 |
ern | -0.003 |
baseman | -0.002 |
coat | -0.002 |
Token | Luxembourg |
Token ID | 31864 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
arella | +0.074 |
zin | +0.069 |
CFR | +0.069 |
RFC | +0.067 |
bish | +0.066 |
Neg logit contributions | |
desired | -0.110 |
intend | -0.107 |
ern | -0.103 |
baseman | -0.103 |
coat | -0.097 |
Token | premier |
Token ID | 18256 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
arella | +0.249 |
zin | +0.235 |
CFR | +0.234 |
RFC | +0.227 |
bish | +0.223 |
Neg logit contributions | |
desired | -0.342 |
intend | -0.332 |
ern | -0.321 |
baseman | -0.319 |
coat | -0.302 |
Token | Jean |
Token ID | 11320 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
arella | +0.025 |
CFR | +0.024 |
zin | +0.024 |
RFC | +0.023 |
bish | +0.023 |
Neg logit contributions | |
desired | -0.027 |
intend | -0.027 |
baseman | -0.025 |
ern | -0.025 |
ocked | -0.024 |
Token | - |
Token ID | 12 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.012 |
ern | +0.012 |
baseman | +0.012 |
ocked | +0.011 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.015 |
CFR | -0.014 |
RFC | -0.014 |
bish | -0.014 |
Token | Cla |
Token ID | 47404 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.008 |
baseman | +0.008 |
ern | +0.008 |
ocked | +0.007 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.007 |
Token | ude |
Token ID | 2507 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
desired | +0.023 |
intend | +0.022 |
ern | +0.021 |
baseman | +0.021 |
plate | +0.020 |
Neg logit contributions | |
arella | -0.026 |
zin | -0.025 |
CFR | -0.025 |
RFC | -0.024 |
bish | -0.024 |
Token | under |
Token ID | 739 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
desired | +0.044 |
intend | +0.042 |
ern | +0.041 |
baseman | +0.040 |
coat | +0.038 |
Neg logit contributions | |
arella | -0.046 |
zin | -0.044 |
CFR | -0.044 |
RFC | -0.043 |
bish | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
arella | +0.068 |
zin | +0.066 |
CFR | +0.065 |
RFC | +0.063 |
bish | +0.063 |
Neg logit contributions | |
desired | -0.065 |
intend | -0.063 |
ern | -0.060 |
baseman | -0.060 |
coat | -0.056 |
Token | sun |
Token ID | 4252 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | . |
Token ID | 764 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.009 |
bish | +0.009 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.008 |
baseman | -0.008 |
coat | -0.007 |
Token | . |
Token ID | 764 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
arella | +0.085 |
zin | +0.079 |
CFR | +0.079 |
RFC | +0.076 |
bish | +0.074 |
Neg logit contributions | |
desired | -0.155 |
intend | -0.151 |
ern | -0.147 |
baseman | -0.146 |
coat | -0.139 |
Token | ." |
Token ID | 22135 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
arella | +0.083 |
zin | +0.077 |
CFR | +0.076 |
RFC | +0.074 |
bish | +0.072 |
Neg logit contributions | |
desired | -0.159 |
intend | -0.155 |
ern | -0.150 |
baseman | -0.150 |
coat | -0.143 |
Token |
|
Token ID | 198 |
Feature activation | +7.17e-04 |
Pos logit contributions | |
arella | +0.259 |
zin | +0.245 |
CFR | +0.244 |
RFC | +0.237 |
bish | +0.233 |
Neg logit contributions | |
desired | -0.327 |
intend | -0.318 |
ern | -0.307 |
baseman | -0.305 |
coat | -0.288 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
arella | +0.000 |
zin | +0.000 |
CFR | +0.000 |
RFC | +0.000 |
bish | +0.000 |
Neg logit contributions | |
desired | -0.000 |
intend | -0.000 |
baseman | -0.000 |
ern | -0.000 |
coat | -0.000 |
Token | - |
Token ID | 12 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | excerpt |
Token ID | 20911 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
desired | +0.018 |
intend | +0.017 |
ern | +0.017 |
baseman | +0.017 |
coat | +0.016 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.014 |
CFR | -0.014 |
RFC | -0.013 |
bish | -0.013 |
Token | from |
Token ID | 422 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
arella | +0.095 |
zin | +0.091 |
CFR | +0.091 |
RFC | +0.089 |
bish | +0.088 |
Neg logit contributions | |
desired | -0.067 |
intend | -0.065 |
baseman | -0.062 |
ern | -0.062 |
coat | -0.057 |
Token | The |
Token ID | 383 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
arella | +0.012 |
zin | +0.011 |
CFR | +0.011 |
RFC | +0.011 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.013 |
intend | -0.012 |
ern | -0.012 |
baseman | -0.012 |
coat | -0.011 |
Token | Complete |
Token ID | 13248 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
arella | +0.015 |
zin | +0.015 |
CFR | +0.014 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.014 |
intend | -0.014 |
ern | -0.013 |
baseman | -0.013 |
coat | -0.012 |
Token | Thirty |
Token ID | 29948 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
desired | +0.045 |
intend | +0.044 |
ern | +0.043 |
baseman | +0.042 |
coat | +0.040 |
Neg logit contributions | |
arella | -0.032 |
zin | -0.030 |
CFR | -0.030 |
RFC | -0.029 |
bish | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
arella | +0.060 |
zin | +0.057 |
CFR | +0.057 |
RFC | +0.056 |
bish | +0.055 |
Neg logit contributions | |
desired | -0.048 |
intend | -0.047 |
ern | -0.045 |
baseman | -0.044 |
coat | -0.041 |
Token | Se |
Token ID | 4653 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.012 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.009 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.008 |
Token | venth |
Token ID | 20987 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
desired | +0.301 |
intend | +0.295 |
ern | +0.289 |
baseman | +0.287 |
coat | +0.277 |
Neg logit contributions | |
arella | -0.050 |
zin | -0.041 |
CFR | -0.040 |
RFC | -0.037 |
bish | -0.034 |
Token | Season |
Token ID | 7369 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
arella | +0.218 |
zin | +0.205 |
CFR | +0.204 |
RFC | +0.196 |
bish | +0.192 |
Neg logit contributions | |
desired | -0.363 |
intend | -0.354 |
ern | -0.342 |
baseman | -0.341 |
coat | -0.324 |
Token | : |
Token ID | 25 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
arella | +0.076 |
zin | +0.073 |
CFR | +0.072 |
RFC | +0.071 |
bish | +0.070 |
Neg logit contributions | |
desired | -0.069 |
intend | -0.067 |
ern | -0.064 |
baseman | -0.063 |
coat | -0.059 |
Token | David |
Token ID | 3271 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
arella | +0.012 |
zin | +0.012 |
CFR | +0.011 |
RFC | +0.011 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.011 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.009 |
Token | vs |
Token ID | 3691 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
desired | +0.056 |
intend | +0.054 |
ern | +0.052 |
baseman | +0.051 |
coat | +0.048 |
Neg logit contributions | |
arella | -0.053 |
zin | -0.051 |
CFR | -0.051 |
RFC | -0.049 |
bish | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.009 |
baseman | +0.009 |
coat | +0.008 |
Neg logit contributions | |
arella | -0.013 |
zin | -0.013 |
CFR | -0.013 |
RFC | -0.012 |
bish | -0.012 |
Token | cited |
Token ID | 9181 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
arella | +0.095 |
zin | +0.091 |
CFR | +0.091 |
RFC | +0.089 |
bish | +0.087 |
Neg logit contributions | |
desired | -0.085 |
intend | -0.082 |
ern | -0.078 |
baseman | -0.078 |
coat | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
arella | +0.102 |
zin | +0.097 |
CFR | +0.097 |
RFC | +0.094 |
bish | +0.093 |
Neg logit contributions | |
desired | -0.107 |
intend | -0.103 |
ern | -0.099 |
baseman | -0.099 |
coat | -0.093 |
Token | Sessions |
Token ID | 15184 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.013 |
ern | +0.013 |
baseman | +0.012 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.012 |
CFR | -0.012 |
RFC | -0.011 |
bish | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
arella | +0.024 |
zin | +0.023 |
CFR | +0.023 |
RFC | +0.022 |
bish | +0.022 |
Neg logit contributions | |
desired | -0.027 |
intend | -0.026 |
ern | -0.025 |
baseman | -0.025 |
coat | -0.023 |
Token | R |
Token ID | 49 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.012 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.013 |
zin | -0.013 |
CFR | -0.013 |
RFC | -0.012 |
bish | -0.012 |
Token | osen |
Token ID | 5233 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
baseman | +0.006 |
ern | +0.006 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.000 |
Token | stein |
Token ID | 5714 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
arella | +0.225 |
zin | +0.209 |
CFR | +0.208 |
RFC | +0.202 |
bish | +0.198 |
Neg logit contributions | |
desired | -0.357 |
intend | -0.347 |
ern | -0.338 |
baseman | -0.333 |
gang | -0.318 |
Token | recommendation |
Token ID | 15602 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
arella | +0.065 |
zin | +0.062 |
CFR | +0.061 |
RFC | +0.060 |
bish | +0.059 |
Neg logit contributions | |
desired | -0.063 |
intend | -0.061 |
ern | -0.058 |
baseman | -0.058 |
coat | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
desired | +0.078 |
intend | +0.075 |
ern | +0.072 |
baseman | +0.071 |
coat | +0.066 |
Neg logit contributions | |
arella | -0.091 |
zin | -0.088 |
CFR | -0.087 |
RFC | -0.085 |
bish | -0.084 |
Token | explain |
Token ID | 4727 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
arella | +0.022 |
zin | +0.021 |
CFR | +0.021 |
RFC | +0.020 |
bish | +0.020 |
Neg logit contributions | |
desired | -0.020 |
intend | -0.020 |
ern | -0.019 |
baseman | -0.019 |
coat | -0.017 |
Token | pen |
Token ID | 3617 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
arella | +0.054 |
zin | +0.052 |
CFR | +0.051 |
RFC | +0.050 |
bish | +0.049 |
Neg logit contributions | |
desired | -0.044 |
intend | -0.042 |
baseman | -0.040 |
ern | -0.040 |
coat | -0.037 |
Token | ian |
Token ID | 666 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
desired | +0.049 |
intend | +0.047 |
baseman | +0.045 |
ern | +0.045 |
coat | +0.041 |
Neg logit contributions | |
arella | -0.068 |
zin | -0.065 |
CFR | -0.065 |
RFC | -0.063 |
bish | -0.062 |
Token | � |
Token ID | 447 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.004 |
CFR | -0.004 |
RFC | -0.004 |
bish | -0.004 |
Token | � |
Token ID | 247 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
arella | +0.007 |
zin | +0.007 |
CFR | +0.007 |
RFC | +0.006 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.006 |
ern | -0.006 |
baseman | -0.006 |
coat | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.007 |
intend | -0.007 |
ern | -0.006 |
baseman | -0.006 |
coat | -0.006 |
Token | Cat |
Token ID | 5181 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
arella | +0.013 |
zin | +0.012 |
CFR | +0.012 |
RFC | +0.012 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.013 |
intend | -0.013 |
ern | -0.012 |
baseman | -0.012 |
coat | -0.011 |
Token | Person |
Token ID | 7755 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
desired | +0.333 |
intend | +0.321 |
ern | +0.308 |
baseman | +0.306 |
coat | +0.285 |
Neg logit contributions | |
arella | -0.381 |
zin | -0.364 |
CFR | -0.362 |
RFC | -0.356 |
bish | -0.350 |
Token | recounts |
Token ID | 39851 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
desired | +0.036 |
intend | +0.035 |
ern | +0.034 |
baseman | +0.033 |
coat | +0.031 |
Neg logit contributions | |
arella | -0.040 |
zin | -0.038 |
CFR | -0.038 |
RFC | -0.037 |
bish | -0.036 |
Token | student |
Token ID | 3710 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
desired | +0.019 |
intend | +0.019 |
ern | +0.018 |
baseman | +0.018 |
coat | +0.016 |
Neg logit contributions | |
arella | -0.025 |
zin | -0.024 |
CFR | -0.023 |
RFC | -0.023 |
bish | -0.023 |
Token | Marg |
Token ID | 11899 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
arella | +0.043 |
zin | +0.041 |
CFR | +0.040 |
RFC | +0.040 |
bish | +0.039 |
Neg logit contributions | |
desired | -0.047 |
intend | -0.045 |
ern | -0.044 |
baseman | -0.043 |
coat | -0.041 |
Token | ot |
Token ID | 313 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.009 |
baseman | +0.009 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.011 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.010 |
bish | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
arella | +0.192 |
zin | +0.184 |
CFR | +0.183 |
RFC | +0.179 |
bish | +0.177 |
Neg logit contributions | |
desired | -0.158 |
intend | -0.153 |
ern | -0.146 |
baseman | -0.145 |
coat | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.007 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +9.27e-03 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | More |
Token ID | 5167 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | from |
Token ID | 422 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
arella | +0.057 |
zin | +0.055 |
CFR | +0.055 |
RFC | +0.053 |
bish | +0.053 |
Neg logit contributions | |
desired | -0.046 |
intend | -0.045 |
ern | -0.043 |
baseman | -0.042 |
coat | -0.039 |
Token | Cat |
Token ID | 5181 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
desired | +0.025 |
intend | +0.024 |
ern | +0.023 |
baseman | +0.023 |
coat | +0.021 |
Neg logit contributions | |
arella | -0.027 |
zin | -0.026 |
CFR | -0.026 |
RFC | -0.025 |
bish | -0.025 |
Token | Sc |
Token ID | 1446 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
desired | +0.338 |
intend | +0.327 |
ern | +0.316 |
baseman | +0.313 |
coat | +0.292 |
Neg logit contributions | |
arella | -0.372 |
zin | -0.358 |
CFR | -0.356 |
RFC | -0.349 |
bish | -0.343 |
Token | ratch |
Token ID | 36722 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
desired | +0.070 |
intend | +0.068 |
baseman | +0.066 |
ern | +0.065 |
coat | +0.062 |
Neg logit contributions | |
arella | -0.050 |
zin | -0.047 |
CFR | -0.047 |
RFC | -0.045 |
bish | -0.044 |
Token | Reader |
Token ID | 25342 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
arella | +0.163 |
zin | +0.156 |
CFR | +0.155 |
RFC | +0.151 |
bish | +0.149 |
Neg logit contributions | |
desired | -0.157 |
intend | -0.152 |
ern | -0.146 |
baseman | -0.145 |
coat | -0.136 |
Token | : |
Token ID | 25 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
desired | +0.084 |
intend | +0.081 |
ern | +0.078 |
baseman | +0.077 |
coat | +0.072 |
Neg logit contributions | |
arella | -0.088 |
zin | -0.084 |
CFR | -0.084 |
RFC | -0.082 |
bish | -0.080 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
arella | +0.014 |
zin | +0.013 |
CFR | +0.013 |
RFC | +0.013 |
bish | +0.013 |
Neg logit contributions | |
desired | -0.015 |
intend | -0.015 |
ern | -0.014 |
baseman | -0.014 |
coat | -0.013 |
Token | accounts |
Token ID | 5504 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
desired | +0.020 |
intend | +0.020 |
ern | +0.019 |
baseman | +0.019 |
coat | +0.018 |
Neg logit contributions | |
arella | -0.018 |
zin | -0.018 |
CFR | -0.017 |
RFC | -0.017 |
bish | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
arella | +0.013 |
zin | +0.012 |
CFR | +0.012 |
RFC | +0.012 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.013 |
intend | -0.012 |
ern | -0.012 |
baseman | -0.012 |
coat | -0.011 |
Token | Desmond |
Token ID | 41045 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | Morris |
Token ID | 14433 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
desired | +0.024 |
intend | +0.023 |
ern | +0.022 |
baseman | +0.022 |
coat | +0.020 |
Neg logit contributions | |
arella | -0.023 |
zin | -0.022 |
CFR | -0.022 |
RFC | -0.022 |
bish | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
arella | +0.016 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.015 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.016 |
intend | -0.015 |
ern | -0.015 |
baseman | -0.015 |
coat | -0.014 |
Token | Cat |
Token ID | 5181 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
arella | +0.028 |
zin | +0.027 |
CFR | +0.027 |
RFC | +0.026 |
bish | +0.025 |
Neg logit contributions | |
desired | -0.027 |
intend | -0.027 |
ern | -0.026 |
baseman | -0.025 |
coat | -0.024 |
Token | World |
Token ID | 2159 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
desired | +0.350 |
intend | +0.340 |
ern | +0.327 |
baseman | +0.324 |
coat | +0.304 |
Neg logit contributions | |
arella | -0.360 |
zin | -0.343 |
CFR | -0.342 |
RFC | -0.335 |
bish | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
arella | +0.025 |
zin | +0.024 |
CFR | +0.024 |
RFC | +0.024 |
bish | +0.023 |
Neg logit contributions | |
desired | -0.024 |
intend | -0.023 |
ern | -0.022 |
baseman | -0.022 |
coat | -0.020 |
Token | published |
Token ID | 3199 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.009 |
CFR | -0.009 |
zin | -0.009 |
RFC | -0.009 |
bish | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
desired | +0.082 |
intend | +0.079 |
ern | +0.076 |
baseman | +0.075 |
coat | +0.070 |
Neg logit contributions | |
arella | -0.086 |
zin | -0.082 |
CFR | -0.082 |
RFC | -0.080 |
bish | -0.078 |
Token | 1996 |
Token ID | 8235 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.004 |
coat | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
arella | +0.121 |
zin | +0.115 |
CFR | +0.115 |
RFC | +0.112 |
bish | +0.110 |
Neg logit contributions | |
desired | -0.128 |
intend | -0.124 |
ern | -0.119 |
baseman | -0.118 |
coat | -0.111 |
Token | B |
Token ID | 33 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
arella | +0.034 |
zin | +0.032 |
CFR | +0.032 |
RFC | +0.031 |
bish | +0.031 |
Neg logit contributions | |
desired | -0.037 |
intend | -0.036 |
ern | -0.035 |
baseman | -0.034 |
coat | -0.032 |
Token | art |
Token ID | 433 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
arella | +0.054 |
zin | +0.052 |
CFR | +0.052 |
RFC | +0.051 |
bish | +0.051 |
Neg logit contributions | |
desired | -0.020 |
intend | -0.019 |
ern | -0.018 |
baseman | -0.017 |
coat | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
desired | +0.145 |
intend | +0.140 |
ern | +0.135 |
baseman | +0.133 |
coat | +0.125 |
Neg logit contributions | |
arella | -0.147 |
zin | -0.140 |
CFR | -0.140 |
RFC | -0.137 |
bish | -0.134 |
Token | Miracle |
Token ID | 33292 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.004 |
CFR | -0.004 |
RFC | -0.004 |
bish | -0.004 |
Token | Cat |
Token ID | 5181 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
desired | +0.116 |
intend | +0.111 |
ern | +0.107 |
baseman | +0.106 |
gang | +0.098 |
Neg logit contributions | |
arella | -0.147 |
zin | -0.141 |
CFR | -0.141 |
RFC | -0.137 |
bish | -0.136 |
Token | ", |
Token ID | 1600 |
Feature activation | -9.69e-02 |
Pos logit contributions | |
desired | +0.337 |
intend | +0.326 |
ern | +0.313 |
baseman | +0.311 |
coat | +0.290 |
Neg logit contributions | |
arella | -0.374 |
zin | -0.357 |
CFR | -0.356 |
RFC | -0.349 |
bish | -0.342 |
Token | say |
Token ID | 910 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.017 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.020 |
zin | -0.019 |
CFR | -0.019 |
RFC | -0.019 |
bish | -0.018 |
Token | they |
Token ID | 484 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
desired | +0.016 |
intend | +0.015 |
ern | +0.015 |
baseman | +0.014 |
coat | +0.014 |
Neg logit contributions | |
arella | -0.017 |
zin | -0.016 |
CFR | -0.016 |
RFC | -0.015 |
bish | -0.015 |
Token | have |
Token ID | 423 |
Feature activation | -7.97e-03 |
Pos logit contributions | |
arella | +0.030 |
CFR | +0.029 |
zin | +0.029 |
RFC | +0.028 |
bish | +0.028 |
Neg logit contributions | |
desired | -0.027 |
intend | -0.026 |
ern | -0.025 |
baseman | -0.025 |
gang | -0.023 |
Token | never |
Token ID | 1239 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
desired | +0.044 |
intend | +0.043 |
ern | +0.041 |
baseman | +0.041 |
coat | +0.038 |
Neg logit contributions | |
arella | -0.049 |
zin | -0.047 |
CFR | -0.046 |
RFC | -0.045 |
bish | -0.045 |
Token | relationship |
Token ID | 2776 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.007 |
CFR | -0.007 |
RFC | -0.007 |
bish | -0.006 |
Token | turned |
Token ID | 2900 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
arella | +0.073 |
zin | +0.070 |
CFR | +0.069 |
RFC | +0.068 |
bish | +0.067 |
Neg logit contributions | |
desired | -0.058 |
intend | -0.056 |
ern | -0.054 |
baseman | -0.053 |
coat | -0.049 |
Token | sour |
Token ID | 11348 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
arella | +0.088 |
zin | +0.084 |
CFR | +0.083 |
RFC | +0.081 |
bish | +0.080 |
Neg logit contributions | |
desired | -0.079 |
intend | -0.076 |
ern | -0.074 |
baseman | -0.073 |
coat | -0.068 |
Token | Cat |
Token ID | 5181 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.003 |
ern | -0.003 |
baseman | -0.003 |
coat | -0.002 |
Token | Person |
Token ID | 7755 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
desired | +0.350 |
intend | +0.339 |
ern | +0.327 |
baseman | +0.323 |
coat | +0.303 |
Neg logit contributions | |
arella | -0.358 |
zin | -0.342 |
CFR | -0.342 |
RFC | -0.335 |
bish | -0.328 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-03 |
Pos logit contributions | |
desired | +0.039 |
intend | +0.038 |
ern | +0.036 |
baseman | +0.036 |
coat | +0.034 |
Neg logit contributions | |
arella | -0.041 |
zin | -0.040 |
CFR | -0.039 |
RFC | -0.038 |
bish | -0.038 |
Token | set |
Token ID | 900 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
desired | +0.000 |
intend | +0.000 |
ern | +0.000 |
baseman | +0.000 |
coat | +0.000 |
Neg logit contributions | |
arella | -0.000 |
zin | -0.000 |
CFR | -0.000 |
RFC | -0.000 |
bish | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
arella | +0.014 |
zin | +0.013 |
CFR | +0.013 |
RFC | +0.013 |
bish | +0.013 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.011 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.009 |
Token | internet |
Token ID | 5230 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.006 |
CFR | -0.006 |
zin | -0.006 |
RFC | -0.005 |
bish | -0.005 |
Token | V |
Token ID | 53 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.003 |
ern | -0.003 |
baseman | -0.003 |
coat | -0.003 |
Token | ac |
Token ID | 330 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.005 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | ation |
Token ID | 341 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.005 |
Token | Time |
Token ID | 3862 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
arella | +0.087 |
zin | +0.082 |
CFR | +0.082 |
RFC | +0.080 |
bish | +0.079 |
Neg logit contributions | |
desired | -0.091 |
intend | -0.088 |
ern | -0.085 |
baseman | -0.084 |
coat | -0.079 |
Token | – |
Token ID | 784 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
desired | +0.041 |
intend | +0.039 |
ern | +0.038 |
baseman | +0.038 |
coat | +0.035 |
Neg logit contributions | |
arella | -0.042 |
zin | -0.040 |
CFR | -0.040 |
RFC | -0.039 |
bish | -0.038 |
Token | Cat |
Token ID | 5181 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
desired | +0.023 |
intend | +0.022 |
ern | +0.021 |
baseman | +0.021 |
coat | +0.020 |
Neg logit contributions | |
arella | -0.026 |
zin | -0.025 |
CFR | -0.025 |
RFC | -0.025 |
bish | -0.024 |
Token | ast |
Token ID | 459 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
desired | +0.370 |
intend | +0.360 |
ern | +0.346 |
baseman | +0.343 |
coat | +0.323 |
Neg logit contributions | |
arella | -0.332 |
zin | -0.317 |
CFR | -0.314 |
RFC | -0.307 |
bish | -0.302 |
Token | rophic |
Token ID | 18191 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
arella | +0.055 |
zin | +0.053 |
CFR | +0.052 |
RFC | +0.051 |
bish | +0.051 |
Neg logit contributions | |
desired | -0.038 |
intend | -0.036 |
ern | -0.034 |
baseman | -0.034 |
gang | -0.031 |
Token | adjust |
Token ID | 4532 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
desired | +0.108 |
intend | +0.104 |
ern | +0.101 |
baseman | +0.100 |
coat | +0.095 |
Neg logit contributions | |
arella | -0.083 |
zin | -0.079 |
CFR | -0.078 |
RFC | -0.076 |
bish | -0.075 |
Token | ers |
Token ID | 364 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
arella | +0.089 |
zin | +0.086 |
CFR | +0.086 |
RFC | +0.084 |
bish | +0.083 |
Neg logit contributions | |
desired | -0.039 |
intend | -0.037 |
baseman | -0.034 |
ern | -0.033 |
gang | -0.030 |
Token | typically |
Token ID | 6032 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
desired | +0.141 |
intend | +0.137 |
ern | +0.131 |
baseman | +0.130 |
gang | +0.122 |
Neg logit contributions | |
arella | -0.156 |
CFR | -0.149 |
zin | -0.148 |
RFC | -0.144 |
bish | -0.142 |
Token | before |
Token ID | 878 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
desired | +0.051 |
intend | +0.049 |
ern | +0.047 |
baseman | +0.047 |
coat | +0.044 |
Neg logit contributions | |
arella | -0.056 |
zin | -0.053 |
CFR | -0.053 |
RFC | -0.052 |
bish | -0.051 |
Token | data |
Token ID | 1366 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
desired | +0.098 |
intend | +0.095 |
ern | +0.091 |
baseman | +0.091 |
coat | +0.085 |
Neg logit contributions | |
arella | -0.103 |
zin | -0.098 |
CFR | -0.098 |
RFC | -0.096 |
bish | -0.094 |
Token | is |
Token ID | 318 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
desired | +0.033 |
intend | +0.033 |
ern | +0.031 |
baseman | +0.031 |
gang | +0.029 |
Neg logit contributions | |
arella | -0.035 |
zin | -0.033 |
CFR | -0.033 |
RFC | -0.032 |
bish | -0.032 |
Token | lost |
Token ID | 2626 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.004 |
CFR | -0.004 |
RFC | -0.004 |
bish | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +6.64e-03 |
Pos logit contributions | |
arella | +0.059 |
zin | +0.057 |
CFR | +0.057 |
RFC | +0.055 |
bish | +0.055 |
Neg logit contributions | |
desired | -0.050 |
intend | -0.048 |
ern | -0.046 |
baseman | -0.046 |
coat | -0.042 |
Token | Cat |
Token ID | 5181 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | ches |
Token ID | 2052 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
desired | +0.381 |
intend | +0.370 |
ern | +0.359 |
baseman | +0.354 |
coat | +0.334 |
Neg logit contributions | |
arella | -0.317 |
CFR | -0.300 |
zin | -0.300 |
RFC | -0.292 |
bish | -0.288 |
Token | a |
Token ID | 257 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
desired | +0.034 |
intend | +0.033 |
ern | +0.032 |
baseman | +0.032 |
gang | +0.029 |
Neg logit contributions | |
arella | -0.037 |
zin | -0.036 |
CFR | -0.036 |
RFC | -0.035 |
bish | -0.034 |
Token | lot |
Token ID | 1256 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.008 |
ern | +0.008 |
baseman | +0.008 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
arella | +0.124 |
zin | +0.118 |
CFR | +0.117 |
RFC | +0.114 |
bish | +0.112 |
Neg logit contributions | |
desired | -0.128 |
intend | -0.124 |
ern | -0.119 |
baseman | -0.119 |
coat | -0.111 |
Token | problems |
Token ID | 2761 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.003 |
ern | -0.003 |
baseman | -0.003 |
coat | -0.003 |
Token | exposing |
Token ID | 21294 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
arella | +0.011 |
zin | +0.010 |
CFR | +0.010 |
RFC | +0.010 |
bish | +0.010 |
Neg logit contributions | |
desired | -0.010 |
intend | -0.010 |
ern | -0.010 |
baseman | -0.009 |
coat | -0.009 |
Token | their |
Token ID | 511 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | child |
Token ID | 1200 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.017 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.017 |
zin | -0.016 |
CFR | -0.016 |
RFC | -0.016 |
bish | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
desired | +0.104 |
intend | +0.101 |
ern | +0.097 |
baseman | +0.096 |
coat | +0.090 |
Neg logit contributions | |
arella | -0.105 |
zin | -0.100 |
CFR | -0.100 |
RFC | -0.098 |
bish | -0.096 |
Token | prof |
Token ID | 1534 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | anity |
Token ID | 19689 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.017 |
zin | -0.017 |
CFR | -0.017 |
RFC | -0.017 |
bish | -0.017 |
Token | ." |
Token ID | 526 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
desired | +0.317 |
intend | +0.302 |
ern | +0.291 |
baseman | +0.290 |
coat | +0.270 |
Neg logit contributions | |
arella | -0.361 |
CFR | -0.345 |
zin | -0.343 |
RFC | -0.338 |
bish | -0.330 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
arella | +0.034 |
zin | +0.032 |
CFR | +0.032 |
RFC | +0.031 |
bish | +0.030 |
Neg logit contributions | |
desired | -0.041 |
intend | -0.040 |
ern | -0.038 |
baseman | -0.038 |
coat | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
baseman | +0.002 |
ern | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | PHOTOS |
Token ID | 42709 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | : |
Token ID | 25 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
desired | +0.117 |
intend | +0.113 |
ern | +0.108 |
baseman | +0.108 |
coat | +0.101 |
Neg logit contributions | |
arella | -0.125 |
zin | -0.119 |
CFR | -0.119 |
RFC | -0.116 |
bish | -0.114 |
Token | more |
Token ID | 517 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
desired | +0.066 |
intend | +0.064 |
ern | +0.061 |
baseman | +0.061 |
coat | +0.057 |
Neg logit contributions | |
arella | -0.072 |
zin | -0.069 |
CFR | -0.068 |
RFC | -0.067 |
bish | -0.066 |
Token | prone |
Token ID | 17592 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.003 |
baseman | -0.003 |
coat | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
desired | +0.049 |
intend | +0.047 |
ern | +0.046 |
baseman | +0.045 |
coat | +0.042 |
Neg logit contributions | |
arella | -0.051 |
zin | -0.049 |
CFR | -0.049 |
RFC | -0.048 |
bish | -0.047 |
Token | use |
Token ID | 779 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | prof |
Token ID | 1534 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.016 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.016 |
zin | -0.016 |
CFR | -0.016 |
RFC | -0.015 |
bish | -0.015 |
Token | anity |
Token ID | 19689 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.016 |
zin | -0.016 |
CFR | -0.016 |
RFC | -0.016 |
bish | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -9.01e-05 |
Pos logit contributions | |
desired | +0.305 |
intend | +0.291 |
ern | +0.279 |
baseman | +0.278 |
coat | +0.258 |
Neg logit contributions | |
arella | -0.370 |
zin | -0.354 |
CFR | -0.354 |
RFC | -0.345 |
bish | -0.340 |
Token | party |
Token ID | 2151 |
Feature activation | +4.93e-03 |
Pos logit contributions | |
desired | +0.000 |
intend | +0.000 |
ern | +0.000 |
baseman | +0.000 |
coat | +0.000 |
Neg logit contributions | |
arella | -0.000 |
zin | -0.000 |
CFR | -0.000 |
RFC | -0.000 |
bish | -0.000 |
Token | than |
Token ID | 621 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
desired | +0.063 |
intend | +0.060 |
ern | +0.058 |
baseman | +0.058 |
coat | +0.054 |
Neg logit contributions | |
arella | -0.061 |
zin | -0.058 |
CFR | -0.058 |
RFC | -0.056 |
bish | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
desired | +0.014 |
intend | +0.013 |
ern | +0.013 |
baseman | +0.013 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.018 |
zin | -0.017 |
CFR | -0.017 |
RFC | -0.016 |
bish | -0.016 |
Token | this |
Token ID | 428 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
desired | +0.031 |
intend | +0.030 |
ern | +0.028 |
baseman | +0.028 |
coat | +0.026 |
Neg logit contributions | |
arella | -0.045 |
zin | -0.043 |
CFR | -0.043 |
RFC | -0.042 |
bish | -0.042 |
Token | month |
Token ID | 1227 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
desired | +0.031 |
intend | +0.030 |
ern | +0.029 |
baseman | +0.029 |
coat | +0.027 |
Neg logit contributions | |
arella | -0.028 |
zin | -0.027 |
CFR | -0.026 |
RFC | -0.026 |
bish | -0.025 |
Token | after |
Token ID | 706 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
arella | +0.013 |
zin | +0.013 |
CFR | +0.013 |
RFC | +0.012 |
bish | +0.012 |
Neg logit contributions | |
desired | -0.012 |
intend | -0.011 |
ern | -0.011 |
baseman | -0.011 |
coat | -0.010 |
Token | using |
Token ID | 1262 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | prof |
Token ID | 1534 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
arella | +0.072 |
zin | +0.069 |
CFR | +0.068 |
RFC | +0.067 |
bish | +0.066 |
Neg logit contributions | |
desired | -0.058 |
intend | -0.055 |
ern | -0.053 |
baseman | -0.053 |
coat | -0.049 |
Token | anity |
Token ID | 19689 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.016 |
zin | -0.015 |
CFR | -0.015 |
RFC | -0.015 |
bish | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
desired | +0.313 |
intend | +0.299 |
ern | +0.288 |
baseman | +0.287 |
coat | +0.266 |
Neg logit contributions | |
arella | -0.350 |
CFR | -0.334 |
zin | -0.333 |
RFC | -0.324 |
bish | -0.320 |
Token | describe |
Token ID | 6901 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.005 |
zin | -0.004 |
CFR | -0.004 |
RFC | -0.004 |
bish | -0.004 |
Token | President |
Token ID | 1992 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
arella | +0.068 |
zin | +0.065 |
CFR | +0.065 |
RFC | +0.063 |
bish | +0.062 |
Neg logit contributions | |
desired | -0.063 |
intend | -0.061 |
ern | -0.058 |
baseman | -0.058 |
coat | -0.054 |
Token | Donald |
Token ID | 3759 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
desired | +0.070 |
intend | +0.068 |
ern | +0.065 |
baseman | +0.065 |
coat | +0.061 |
Neg logit contributions | |
arella | -0.074 |
zin | -0.071 |
CFR | -0.070 |
RFC | -0.068 |
bish | -0.067 |
Token | Trump |
Token ID | 1301 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
desired | +0.055 |
intend | +0.053 |
ern | +0.051 |
baseman | +0.051 |
coat | +0.048 |
Neg logit contributions | |
arella | -0.052 |
zin | -0.050 |
CFR | -0.050 |
RFC | -0.048 |
bish | -0.048 |
Token | see |
Token ID | 766 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.017 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.019 |
zin | -0.018 |
CFR | -0.018 |
RFC | -0.018 |
bish | -0.017 |
Token | your |
Token ID | 534 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
arella | +0.069 |
zin | +0.066 |
CFR | +0.066 |
RFC | +0.064 |
bish | +0.064 |
Neg logit contributions | |
desired | -0.061 |
intend | -0.059 |
ern | -0.056 |
baseman | -0.056 |
coat | -0.053 |
Token | city |
Token ID | 1748 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
desired | +0.094 |
intend | +0.092 |
ern | +0.087 |
baseman | +0.087 |
coat | +0.081 |
Neg logit contributions | |
arella | -0.100 |
zin | -0.095 |
CFR | -0.095 |
RFC | -0.092 |
bish | -0.091 |
Token | � |
Token ID | 14519 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
desired | +0.026 |
intend | +0.025 |
ern | +0.024 |
baseman | +0.024 |
coat | +0.022 |
Neg logit contributions | |
arella | -0.027 |
zin | -0.026 |
CFR | -0.026 |
RFC | -0.025 |
bish | -0.025 |
Token | � |
Token ID | 244 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
arella | +0.016 |
zin | +0.016 |
CFR | +0.015 |
RFC | +0.015 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.015 |
intend | -0.014 |
ern | -0.014 |
baseman | -0.014 |
coat | -0.013 |
Token | ️ |
Token ID | 37929 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
desired | +0.052 |
intend | +0.050 |
ern | +0.047 |
baseman | +0.047 |
coat | +0.043 |
Neg logit contributions | |
arella | -0.082 |
zin | -0.079 |
CFR | -0.079 |
RFC | -0.077 |
bish | -0.076 |
Token | Be |
Token ID | 1355 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
desired | +0.331 |
intend | +0.320 |
ern | +0.308 |
baseman | +0.306 |
coat | +0.287 |
Neg logit contributions | |
arella | -0.311 |
zin | -0.296 |
CFR | -0.294 |
RFC | -0.287 |
bish | -0.283 |
Token | safe |
Token ID | 3338 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
arella | +0.041 |
zin | +0.039 |
CFR | +0.039 |
RFC | +0.038 |
bish | +0.038 |
Neg logit contributions | |
desired | -0.036 |
intend | -0.035 |
baseman | -0.033 |
ern | -0.033 |
coat | -0.031 |
Token | pic |
Token ID | 8301 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
arella | +0.016 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.015 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.015 |
intend | -0.014 |
ern | -0.014 |
baseman | -0.014 |
coat | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
desired | +0.110 |
intend | +0.106 |
baseman | +0.101 |
ern | +0.100 |
coat | +0.093 |
Neg logit contributions | |
arella | -0.137 |
zin | -0.131 |
CFR | -0.131 |
RFC | -0.128 |
bish | -0.125 |
Token | twitter |
Token ID | 6956 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
baseman | -0.002 |
ern | -0.002 |
ocked | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.007 |
baseman | +0.007 |
ern | +0.007 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.005 |
bish | -0.005 |
Token | G |
Token ID | 38 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | rim |
Token ID | 3036 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
desired | +0.040 |
intend | +0.038 |
ern | +0.037 |
baseman | +0.036 |
coat | +0.034 |
Neg logit contributions | |
arella | -0.040 |
zin | -0.038 |
CFR | -0.038 |
RFC | -0.037 |
bish | -0.036 |
Token | Lav |
Token ID | 21438 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
arella | +0.093 |
zin | +0.089 |
CFR | +0.088 |
RFC | +0.085 |
bish | +0.085 |
Neg logit contributions | |
desired | -0.088 |
intend | -0.085 |
baseman | -0.082 |
ern | -0.081 |
ocked | -0.075 |
Token | am |
Token ID | 321 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
arella | +0.034 |
zin | +0.032 |
CFR | +0.032 |
RFC | +0.031 |
bish | +0.031 |
Neg logit contributions | |
desired | -0.026 |
intend | -0.024 |
baseman | -0.023 |
ern | -0.023 |
coat | -0.021 |
Token | ancer |
Token ID | 8250 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
desired | +0.020 |
intend | +0.018 |
baseman | +0.015 |
ern | +0.015 |
gang | +0.011 |
Neg logit contributions | |
arella | -0.109 |
zin | -0.106 |
CFR | -0.106 |
RFC | -0.103 |
bish | -0.103 |
Token | vs |
Token ID | 3691 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
desired | +0.354 |
intend | +0.343 |
ern | +0.331 |
baseman | +0.330 |
coat | +0.311 |
Neg logit contributions | |
arella | -0.286 |
zin | -0.271 |
CFR | -0.269 |
RFC | -0.262 |
bish | -0.257 |
Token | Ragnar |
Token ID | 32797 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.007 |
CFR | -0.007 |
RFC | -0.007 |
bish | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
arella | +0.017 |
zin | +0.016 |
CFR | +0.016 |
RFC | +0.015 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.028 |
intend | -0.027 |
ern | -0.026 |
baseman | -0.026 |
coat | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
baseman | +0.005 |
ern | +0.005 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.004 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | Gen |
Token ID | 13746 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | including |
Token ID | 1390 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
arella | +0.042 |
zin | +0.040 |
CFR | +0.040 |
RFC | +0.039 |
bish | +0.038 |
Neg logit contributions | |
desired | -0.037 |
intend | -0.036 |
ern | -0.034 |
baseman | -0.034 |
coat | -0.032 |
Token | number |
Token ID | 1271 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
desired | +0.012 |
intend | +0.012 |
ern | +0.011 |
baseman | +0.011 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.011 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.010 |
bish | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.003 |
baseman | -0.003 |
coat | -0.003 |
Token | J |
Token ID | 449 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.012 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.014 |
CFR | -0.014 |
RFC | -0.014 |
bish | -0.013 |
Token | ansson |
Token ID | 44038 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.007 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.051 |
zin | -0.050 |
CFR | -0.049 |
RFC | -0.049 |
bish | -0.048 |
Token | herself |
Token ID | 5223 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
desired | +0.298 |
intend | +0.289 |
ern | +0.277 |
baseman | +0.275 |
coat | +0.256 |
Neg logit contributions | |
arella | -0.337 |
zin | -0.323 |
CFR | -0.321 |
RFC | -0.313 |
bish | -0.309 |
Token | was |
Token ID | 373 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
desired | +0.016 |
intend | +0.016 |
ern | +0.015 |
baseman | +0.015 |
gang | +0.014 |
Neg logit contributions | |
arella | -0.018 |
zin | -0.017 |
CFR | -0.017 |
RFC | -0.016 |
bish | -0.016 |
Token | involved |
Token ID | 2950 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
desired | +0.032 |
intend | +0.031 |
ern | +0.030 |
baseman | +0.029 |
coat | +0.027 |
Neg logit contributions | |
arella | -0.036 |
zin | -0.034 |
CFR | -0.034 |
RFC | -0.033 |
bish | -0.033 |
Token | in |
Token ID | 287 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
arella | +0.073 |
zin | +0.070 |
CFR | +0.070 |
RFC | +0.068 |
bish | +0.067 |
Neg logit contributions | |
desired | -0.069 |
intend | -0.066 |
ern | -0.064 |
baseman | -0.063 |
coat | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
arella | +0.003 |
zin | +0.003 |
CFR | +0.003 |
RFC | +0.003 |
bish | +0.003 |
Neg logit contributions | |
desired | -0.003 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | no |
Token ID | 645 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
desired | +0.039 |
intend | +0.038 |
ern | +0.037 |
baseman | +0.036 |
coat | +0.034 |
Neg logit contributions | |
arella | -0.040 |
zin | -0.038 |
CFR | -0.038 |
RFC | -0.037 |
bish | -0.037 |
Token | original |
Token ID | 2656 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
arella | +0.021 |
zin | +0.020 |
CFR | +0.020 |
RFC | +0.020 |
bish | +0.019 |
Neg logit contributions | |
desired | -0.023 |
intend | -0.023 |
ern | -0.022 |
baseman | -0.022 |
coat | -0.020 |
Token | lyrics |
Token ID | 15844 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
arella | +0.023 |
zin | +0.022 |
CFR | +0.022 |
RFC | +0.021 |
bish | +0.021 |
Neg logit contributions | |
desired | -0.025 |
intend | -0.024 |
ern | -0.023 |
baseman | -0.023 |
coat | -0.021 |
Token | by |
Token ID | 416 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
arella | +0.015 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.014 |
intend | -0.013 |
ern | -0.012 |
baseman | -0.012 |
coat | -0.012 |
Token | J |
Token ID | 449 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
arella | +0.007 |
zin | +0.007 |
CFR | +0.006 |
RFC | +0.006 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.006 |
ern | -0.006 |
baseman | -0.006 |
coat | -0.005 |
Token | ansson |
Token ID | 44038 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
desired | +0.012 |
intend | +0.010 |
baseman | +0.009 |
ern | +0.008 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.071 |
zin | -0.069 |
CFR | -0.068 |
RFC | -0.067 |
bish | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
desired | +0.295 |
intend | +0.283 |
ern | +0.271 |
baseman | +0.269 |
coat | +0.250 |
Neg logit contributions | |
arella | -0.342 |
zin | -0.327 |
CFR | -0.325 |
RFC | -0.320 |
bish | -0.314 |
Token | However |
Token ID | 2102 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.013 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
desired | +0.023 |
intend | +0.022 |
ern | +0.021 |
baseman | +0.021 |
coat | +0.020 |
Neg logit contributions | |
arella | -0.027 |
zin | -0.026 |
CFR | -0.026 |
RFC | -0.025 |
bish | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
arella | +0.018 |
zin | +0.017 |
CFR | +0.017 |
RFC | +0.017 |
bish | +0.017 |
Neg logit contributions | |
desired | -0.015 |
intend | -0.014 |
ern | -0.014 |
baseman | -0.014 |
coat | -0.013 |
Token | � |
Token ID | 250 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.008 |
Token | E |
Token ID | 36 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.009 |
baseman | +0.009 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.009 |
zin | -0.009 |
CFR | -0.009 |
RFC | -0.009 |
bish | -0.008 |
Token | scape |
Token ID | 6794 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
arella | +0.049 |
zin | +0.046 |
CFR | +0.046 |
RFC | +0.045 |
bish | +0.044 |
Neg logit contributions | |
desired | -0.044 |
intend | -0.043 |
ern | -0.041 |
baseman | -0.041 |
coat | -0.038 |
Token | from |
Token ID | 422 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
arella | +0.009 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.008 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.007 |
intend | -0.007 |
ern | -0.007 |
baseman | -0.006 |
coat | -0.006 |
Token | Al |
Token ID | 978 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
desired | +0.033 |
intend | +0.032 |
ern | +0.031 |
baseman | +0.031 |
coat | +0.029 |
Neg logit contributions | |
arella | -0.035 |
zin | -0.033 |
CFR | -0.033 |
RFC | -0.032 |
bish | -0.032 |
Token | cat |
Token ID | 9246 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
desired | +0.034 |
intend | +0.032 |
ern | +0.028 |
baseman | +0.028 |
coat | +0.023 |
Neg logit contributions | |
arella | -0.127 |
zin | -0.123 |
CFR | -0.123 |
RFC | -0.121 |
bish | -0.120 |
Token | raz |
Token ID | 3247 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
desired | +0.306 |
intend | +0.295 |
ern | +0.283 |
baseman | +0.282 |
coat | +0.263 |
Neg logit contributions | |
arella | -0.324 |
zin | -0.310 |
CFR | -0.308 |
RFC | -0.300 |
bish | -0.296 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
desired | +0.014 |
intend | +0.013 |
ern | +0.013 |
baseman | +0.013 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.016 |
zin | -0.016 |
CFR | -0.015 |
RFC | -0.015 |
bish | -0.015 |
Token | � |
Token ID | 447 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
desired | +0.009 |
intend | +0.009 |
ern | +0.009 |
baseman | +0.009 |
coat | +0.008 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.007 |
bish | -0.007 |
Token | � |
Token ID | 251 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.004 |
baseman | -0.003 |
coat | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.013 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.011 |
zin | -0.010 |
CFR | -0.010 |
RFC | -0.010 |
bish | -0.010 |
Token | have |
Token ID | 423 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
desired | +0.044 |
intend | +0.043 |
ern | +0.041 |
baseman | +0.041 |
coat | +0.038 |
Neg logit contributions | |
arella | -0.046 |
zin | -0.044 |
CFR | -0.044 |
RFC | -0.042 |
bish | -0.042 |
Token | been |
Token ID | 587 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.004 |
baseman | -0.003 |
coat | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.016 |
ern | +0.015 |
baseman | +0.015 |
coat | +0.014 |
Neg logit contributions | |
arella | -0.020 |
zin | -0.019 |
CFR | -0.019 |
RFC | -0.019 |
bish | -0.018 |
Token | from |
Token ID | 422 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
desired | +0.019 |
intend | +0.018 |
ern | +0.017 |
baseman | +0.017 |
coat | +0.016 |
Neg logit contributions | |
arella | -0.018 |
zin | -0.017 |
CFR | -0.017 |
RFC | -0.017 |
bish | -0.017 |
Token | J |
Token ID | 449 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
desired | +0.027 |
intend | +0.026 |
ern | +0.025 |
baseman | +0.025 |
coat | +0.023 |
Neg logit contributions | |
arella | -0.031 |
zin | -0.030 |
CFR | -0.030 |
RFC | -0.029 |
bish | -0.029 |
Token | ansson |
Token ID | 44038 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.007 |
ern | +0.006 |
baseman | +0.005 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.049 |
zin | -0.047 |
CFR | -0.047 |
RFC | -0.047 |
bish | -0.046 |
Token | 's |
Token ID | 338 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
desired | +0.327 |
intend | +0.316 |
ern | +0.305 |
baseman | +0.301 |
coat | +0.284 |
Neg logit contributions | |
arella | -0.302 |
zin | -0.287 |
CFR | -0.286 |
RFC | -0.279 |
bish | -0.274 |
Token | M |
Token ID | 337 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
arella | +0.029 |
zin | +0.027 |
CFR | +0.027 |
RFC | +0.027 |
bish | +0.026 |
Neg logit contributions | |
desired | -0.027 |
intend | -0.026 |
ern | -0.025 |
baseman | -0.025 |
coat | -0.023 |
Token | oom |
Token ID | 4207 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
desired | +0.041 |
intend | +0.040 |
ern | +0.039 |
baseman | +0.038 |
coat | +0.036 |
Neg logit contributions | |
arella | -0.031 |
zin | -0.029 |
CFR | -0.029 |
RFC | -0.028 |
bish | -0.027 |
Token | in |
Token ID | 259 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
arella | +0.128 |
zin | +0.123 |
CFR | +0.122 |
RFC | +0.120 |
bish | +0.118 |
Neg logit contributions | |
desired | -0.092 |
intend | -0.088 |
ern | -0.084 |
baseman | -0.083 |
coat | -0.077 |
Token | series |
Token ID | 2168 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
desired | +0.024 |
intend | +0.023 |
ern | +0.022 |
baseman | +0.022 |
coat | +0.021 |
Neg logit contributions | |
arella | -0.023 |
zin | -0.022 |
CFR | -0.022 |
RFC | -0.022 |
bish | -0.021 |
Token | early |
Token ID | 1903 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
desired | +0.012 |
intend | +0.011 |
ern | +0.011 |
baseman | +0.011 |
coat | +0.010 |
Neg logit contributions | |
arella | -0.014 |
zin | -0.013 |
CFR | -0.013 |
RFC | -0.013 |
bish | -0.012 |
Token | 1950 |
Token ID | 11445 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
desired | +0.076 |
intend | +0.073 |
ern | +0.070 |
baseman | +0.069 |
coat | +0.064 |
Neg logit contributions | |
arella | -0.093 |
zin | -0.089 |
CFR | -0.088 |
RFC | -0.087 |
bish | -0.085 |
Token | s |
Token ID | 82 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
desired | +0.043 |
intend | +0.042 |
ern | +0.040 |
baseman | +0.040 |
coat | +0.038 |
Neg logit contributions | |
arella | -0.038 |
zin | -0.036 |
CFR | -0.035 |
RFC | -0.035 |
bish | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -7.62e-03 |
Pos logit contributions | |
arella | +0.015 |
zin | +0.014 |
CFR | +0.014 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.013 |
intend | -0.013 |
ern | -0.012 |
baseman | -0.012 |
coat | -0.011 |
Token | J |
Token ID | 449 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | ansson |
Token ID | 44038 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
desired | +0.009 |
intend | +0.008 |
baseman | +0.007 |
ern | +0.007 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.058 |
zin | -0.056 |
CFR | -0.056 |
RFC | -0.055 |
bish | -0.055 |
Token | collaborated |
Token ID | 38261 |
Feature activation | -1.94e-04 |
Pos logit contributions | |
desired | +0.291 |
intend | +0.280 |
ern | +0.268 |
baseman | +0.266 |
coat | +0.248 |
Neg logit contributions | |
arella | -0.337 |
zin | -0.323 |
CFR | -0.321 |
RFC | -0.314 |
bish | -0.309 |
Token | on |
Token ID | 319 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
desired | +0.000 |
intend | +0.000 |
ern | +0.000 |
baseman | +0.000 |
coat | +0.000 |
Neg logit contributions | |
arella | -0.000 |
zin | -0.000 |
CFR | -0.000 |
RFC | -0.000 |
bish | -0.000 |
Token | M |
Token ID | 337 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | oom |
Token ID | 4207 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
desired | +0.034 |
intend | +0.033 |
ern | +0.032 |
baseman | +0.032 |
coat | +0.030 |
Neg logit contributions | |
arella | -0.027 |
CFR | -0.025 |
zin | -0.025 |
RFC | -0.024 |
bish | -0.024 |
Token | in |
Token ID | 259 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
arella | +0.122 |
zin | +0.117 |
CFR | +0.117 |
RFC | +0.114 |
bish | +0.113 |
Neg logit contributions | |
desired | -0.091 |
intend | -0.087 |
ern | -0.083 |
baseman | -0.083 |
coat | -0.076 |
Token | play |
Token ID | 711 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
desired | +0.028 |
intend | +0.027 |
ern | +0.026 |
baseman | +0.025 |
coat | +0.024 |
Neg logit contributions | |
arella | -0.029 |
zin | -0.027 |
CFR | -0.027 |
RFC | -0.026 |
bish | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
desired | +0.036 |
intend | +0.035 |
ern | +0.033 |
baseman | +0.033 |
coat | +0.031 |
Neg logit contributions | |
arella | -0.042 |
zin | -0.040 |
CFR | -0.040 |
RFC | -0.039 |
bish | -0.039 |
Token | lyrics |
Token ID | 15844 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
arella | +0.009 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.008 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | by |
Token ID | 416 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
arella | +0.023 |
zin | +0.022 |
CFR | +0.021 |
RFC | +0.021 |
bish | +0.021 |
Neg logit contributions | |
desired | -0.021 |
intend | -0.020 |
ern | -0.019 |
baseman | -0.019 |
coat | -0.018 |
Token | J |
Token ID | 449 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
arella | +0.019 |
zin | +0.018 |
CFR | +0.018 |
RFC | +0.018 |
bish | +0.017 |
Neg logit contributions | |
desired | -0.019 |
intend | -0.018 |
ern | -0.017 |
baseman | -0.017 |
coat | -0.016 |
Token | ansson |
Token ID | 44038 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.007 |
baseman | +0.006 |
ern | +0.006 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.050 |
zin | -0.048 |
CFR | -0.048 |
RFC | -0.047 |
bish | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
desired | +0.297 |
intend | +0.286 |
ern | +0.275 |
baseman | +0.273 |
coat | +0.254 |
Neg logit contributions | |
arella | -0.330 |
zin | -0.316 |
CFR | -0.314 |
RFC | -0.307 |
bish | -0.303 |
Token | music |
Token ID | 2647 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
arella | +0.011 |
zin | +0.011 |
CFR | +0.010 |
RFC | +0.010 |
bish | +0.010 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.010 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.009 |
Token | composed |
Token ID | 13160 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
arella | +0.080 |
zin | +0.076 |
CFR | +0.076 |
RFC | +0.074 |
bish | +0.073 |
Neg logit contributions | |
desired | -0.076 |
intend | -0.073 |
ern | -0.070 |
baseman | -0.070 |
coat | -0.065 |
Token | by |
Token ID | 416 |
Feature activation | +7.72e-02 |
Pos logit contributions | |
arella | +0.036 |
zin | +0.035 |
CFR | +0.035 |
RFC | +0.034 |
bish | +0.033 |
Neg logit contributions | |
desired | -0.036 |
intend | -0.035 |
ern | -0.033 |
baseman | -0.033 |
coat | -0.031 |
Token | Er |
Token ID | 5256 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
arella | +0.015 |
zin | +0.014 |
CFR | +0.014 |
RFC | +0.014 |
bish | +0.013 |
Neg logit contributions | |
desired | -0.015 |
intend | -0.014 |
ern | -0.014 |
baseman | -0.014 |
coat | -0.013 |
Token | M |
Token ID | 44 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
desired | +0.015 |
intend | +0.015 |
ern | +0.014 |
baseman | +0.014 |
coat | +0.013 |
Neg logit contributions | |
arella | -0.013 |
zin | -0.013 |
CFR | -0.013 |
RFC | -0.012 |
bish | -0.012 |
Token | urd |
Token ID | 2799 |
Feature activation | -9.00e-02 |
Pos logit contributions | |
desired | +0.040 |
intend | +0.039 |
ern | +0.037 |
baseman | +0.037 |
coat | +0.035 |
Neg logit contributions | |
arella | -0.044 |
zin | -0.042 |
CFR | -0.041 |
RFC | -0.040 |
bish | -0.040 |
Token | ers |
Token ID | 364 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
desired | +0.012 |
intend | +0.012 |
baseman | +0.011 |
ern | +0.011 |
gang | +0.010 |
Neg logit contributions | |
arella | -0.022 |
zin | -0.021 |
CFR | -0.021 |
RFC | -0.021 |
bish | -0.020 |
Token | on |
Token ID | 319 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
desired | +0.154 |
intend | +0.149 |
ern | +0.143 |
baseman | +0.143 |
coat | +0.133 |
Neg logit contributions | |
arella | -0.152 |
zin | -0.145 |
CFR | -0.144 |
RFC | -0.140 |
bish | -0.139 |
Token | Al |
Token ID | 978 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.005 |
CFR | -0.005 |
zin | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | cat |
Token ID | 9246 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
desired | +0.071 |
intend | +0.068 |
ern | +0.065 |
baseman | +0.065 |
coat | +0.060 |
Neg logit contributions | |
arella | -0.096 |
zin | -0.092 |
CFR | -0.092 |
RFC | -0.090 |
bish | -0.089 |
Token | raz |
Token ID | 3247 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
desired | +0.291 |
intend | +0.282 |
ern | +0.273 |
baseman | +0.268 |
gang | +0.250 |
Neg logit contributions | |
arella | -0.330 |
CFR | -0.317 |
zin | -0.315 |
RFC | -0.311 |
bish | -0.305 |
Token | . |
Token ID | 13 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
desired | +0.019 |
intend | +0.019 |
ern | +0.018 |
baseman | +0.018 |
coat | +0.017 |
Neg logit contributions | |
arella | -0.019 |
zin | -0.018 |
CFR | -0.018 |
RFC | -0.018 |
bish | -0.017 |
Token | � |
Token ID | 447 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.013 |
ern | +0.013 |
baseman | +0.012 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.010 |
Token | � |
Token ID | 251 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
desired | +0.014 |
intend | +0.013 |
ern | +0.013 |
baseman | +0.013 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.010 |
Token | oom |
Token ID | 4207 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
desired | +0.036 |
intend | +0.035 |
ern | +0.034 |
baseman | +0.034 |
coat | +0.032 |
Neg logit contributions | |
arella | -0.028 |
CFR | -0.026 |
zin | -0.026 |
RFC | -0.025 |
bish | -0.025 |
Token | in |
Token ID | 259 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
arella | +0.130 |
zin | +0.126 |
CFR | +0.125 |
RFC | +0.122 |
bish | +0.121 |
Neg logit contributions | |
desired | -0.075 |
intend | -0.072 |
ern | -0.068 |
baseman | -0.067 |
coat | -0.061 |
Token | novels |
Token ID | 16122 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
desired | +0.032 |
intend | +0.031 |
ern | +0.029 |
baseman | +0.029 |
coat | +0.027 |
Neg logit contributions | |
arella | -0.031 |
zin | -0.029 |
CFR | -0.029 |
RFC | -0.028 |
bish | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
arella | +0.048 |
zin | +0.046 |
CFR | +0.046 |
RFC | +0.045 |
bish | +0.044 |
Neg logit contributions | |
desired | -0.044 |
intend | -0.042 |
ern | -0.040 |
baseman | -0.040 |
coat | -0.037 |
Token | J |
Token ID | 449 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.005 |
Token | ansson |
Token ID | 44038 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
desired | +0.023 |
intend | +0.022 |
baseman | +0.021 |
ern | +0.021 |
coat | +0.019 |
Neg logit contributions | |
arella | -0.040 |
zin | -0.039 |
CFR | -0.038 |
RFC | -0.038 |
bish | -0.037 |
Token | 's |
Token ID | 338 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
desired | +0.332 |
intend | +0.322 |
ern | +0.310 |
baseman | +0.308 |
coat | +0.290 |
Neg logit contributions | |
arella | -0.292 |
zin | -0.278 |
CFR | -0.276 |
RFC | -0.269 |
bish | -0.265 |
Token | pict |
Token ID | 2862 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
arella | +0.028 |
zin | +0.027 |
CFR | +0.027 |
RFC | +0.026 |
bish | +0.026 |
Neg logit contributions | |
desired | -0.029 |
intend | -0.028 |
ern | -0.027 |
baseman | -0.027 |
coat | -0.025 |
Token | orial |
Token ID | 5132 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
desired | +0.060 |
intend | +0.058 |
baseman | +0.055 |
ern | +0.055 |
coat | +0.051 |
Neg logit contributions | |
arella | -0.072 |
zin | -0.069 |
CFR | -0.069 |
RFC | -0.067 |
bish | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.011 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.010 |
bish | -0.010 |
Token | descriptive |
Token ID | 35644 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.009 |
bish | +0.009 |
Neg logit contributions | |
desired | -0.009 |
intend | -0.009 |
ern | -0.009 |
baseman | -0.009 |
coat | -0.008 |
Token | Center |
Token ID | 3337 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
desired | +0.074 |
intend | +0.072 |
ern | +0.069 |
baseman | +0.068 |
coat | +0.064 |
Neg logit contributions | |
arella | -0.066 |
zin | -0.063 |
CFR | -0.063 |
RFC | -0.061 |
bish | -0.060 |
Token | Combat |
Token ID | 14487 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
arella | +0.009 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.009 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.010 |
intend | -0.010 |
ern | -0.009 |
baseman | -0.009 |
coat | -0.009 |
Token | ting |
Token ID | 889 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
arella | +0.023 |
zin | +0.022 |
CFR | +0.022 |
RFC | +0.022 |
bish | +0.021 |
Neg logit contributions | |
desired | -0.021 |
intend | -0.020 |
ern | -0.019 |
baseman | -0.019 |
coat | -0.018 |
Token | Extrem |
Token ID | 47871 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
arella | +0.024 |
zin | +0.023 |
CFR | +0.023 |
RFC | +0.022 |
bish | +0.022 |
Neg logit contributions | |
desired | -0.024 |
intend | -0.024 |
ern | -0.023 |
baseman | -0.023 |
coat | -0.021 |
Token | ism |
Token ID | 1042 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
desired | +0.169 |
intend | +0.165 |
ern | +0.162 |
baseman | +0.160 |
gang | +0.154 |
Neg logit contributions | |
arella | -0.043 |
zin | -0.039 |
CFR | -0.038 |
RFC | -0.037 |
bish | -0.033 |
Token | visited |
Token ID | 8672 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
arella | +0.223 |
zin | +0.213 |
CFR | +0.212 |
RFC | +0.207 |
bish | +0.204 |
Neg logit contributions | |
desired | -0.201 |
intend | -0.194 |
ern | -0.186 |
baseman | -0.185 |
coat | -0.172 |
Token | a |
Token ID | 257 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
desired | +0.050 |
intend | +0.049 |
ern | +0.047 |
baseman | +0.046 |
coat | +0.043 |
Neg logit contributions | |
arella | -0.052 |
zin | -0.050 |
CFR | -0.049 |
RFC | -0.048 |
bish | -0.048 |
Token | school |
Token ID | 1524 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
desired | +0.018 |
intend | +0.017 |
ern | +0.017 |
baseman | +0.017 |
coat | +0.016 |
Neg logit contributions | |
arella | -0.014 |
zin | -0.013 |
CFR | -0.013 |
RFC | -0.013 |
bish | -0.012 |
Token | pupil |
Token ID | 34047 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
arella | +0.087 |
zin | +0.084 |
CFR | +0.083 |
RFC | +0.081 |
bish | +0.080 |
Neg logit contributions | |
desired | -0.083 |
intend | -0.080 |
ern | -0.077 |
baseman | -0.076 |
coat | -0.071 |
Token | who |
Token ID | 508 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
arella | +0.107 |
zin | +0.102 |
CFR | +0.102 |
RFC | +0.099 |
bish | +0.098 |
Neg logit contributions | |
desired | -0.105 |
intend | -0.101 |
ern | -0.097 |
baseman | -0.097 |
coat | -0.091 |
Token | where |
Token ID | 810 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
arella | +0.017 |
zin | +0.016 |
CFR | +0.016 |
RFC | +0.015 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.016 |
intend | -0.015 |
ern | -0.015 |
baseman | -0.015 |
coat | -0.014 |
Token | peace |
Token ID | 4167 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
desired | +0.064 |
intend | +0.061 |
ern | +0.059 |
baseman | +0.058 |
coat | +0.055 |
Neg logit contributions | |
arella | -0.070 |
zin | -0.067 |
CFR | -0.066 |
RFC | -0.065 |
bish | -0.064 |
Token | reign |
Token ID | 13580 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
desired | +0.028 |
intend | +0.027 |
ern | +0.026 |
baseman | +0.026 |
coat | +0.024 |
Neg logit contributions | |
arella | -0.029 |
zin | -0.027 |
CFR | -0.027 |
RFC | -0.027 |
bish | -0.026 |
Token | s |
Token ID | 82 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.008 |
ern | +0.008 |
baseman | +0.008 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.007 |
CFR | -0.007 |
RFC | -0.006 |
bish | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
arella | +0.021 |
zin | +0.020 |
CFR | +0.020 |
RFC | +0.019 |
bish | +0.019 |
Neg logit contributions | |
desired | -0.018 |
intend | -0.017 |
ern | -0.017 |
baseman | -0.016 |
coat | -0.015 |
Token | Providence |
Token ID | 28319 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | similarly |
Token ID | 12470 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
arella | +0.232 |
zin | +0.221 |
CFR | +0.220 |
RFC | +0.215 |
bish | +0.212 |
Neg logit contributions | |
desired | -0.220 |
intend | -0.214 |
ern | -0.205 |
baseman | -0.204 |
coat | -0.190 |
Token | ends |
Token ID | 5645 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
arella | +0.168 |
zin | +0.160 |
CFR | +0.160 |
RFC | +0.156 |
bish | +0.153 |
Neg logit contributions | |
desired | -0.160 |
intend | -0.156 |
ern | -0.149 |
baseman | -0.149 |
gang | -0.139 |
Token | with |
Token ID | 351 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
desired | +0.105 |
intend | +0.102 |
ern | +0.097 |
baseman | +0.096 |
coat | +0.090 |
Neg logit contributions | |
arella | -0.123 |
zin | -0.118 |
CFR | -0.117 |
RFC | -0.115 |
bish | -0.113 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.010 |
CFR | +0.010 |
RFC | +0.010 |
bish | +0.010 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | arrival |
Token ID | 10325 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
arella | +0.002 |
zin | +0.002 |
CFR | +0.002 |
RFC | +0.002 |
bish | +0.002 |
Neg logit contributions | |
desired | -0.002 |
intend | -0.002 |
ern | -0.002 |
baseman | -0.002 |
coat | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
desired | +0.042 |
intend | +0.041 |
ern | +0.039 |
baseman | +0.039 |
coat | +0.036 |
Neg logit contributions | |
arella | -0.053 |
zin | -0.050 |
CFR | -0.050 |
RFC | -0.049 |
bish | -0.048 |
Token | Caribbean |
Token ID | 18020 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.006 |
CFR | -0.006 |
zin | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | oil |
Token ID | 3056 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
desired | +0.078 |
intend | +0.075 |
ern | +0.072 |
baseman | +0.072 |
coat | +0.067 |
Neg logit contributions | |
arella | -0.080 |
CFR | -0.076 |
zin | -0.076 |
RFC | -0.073 |
bish | -0.072 |
Token | alliance |
Token ID | 12801 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.009 |
bish | +0.009 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
arella | +0.119 |
zin | +0.114 |
CFR | +0.114 |
RFC | +0.111 |
bish | +0.109 |
Neg logit contributions | |
desired | -0.106 |
intend | -0.102 |
ern | -0.098 |
baseman | -0.097 |
coat | -0.091 |
Token | Petro |
Token ID | 36863 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | car |
Token ID | 7718 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
arella | +0.240 |
zin | +0.230 |
CFR | +0.229 |
RFC | +0.224 |
bish | +0.220 |
Neg logit contributions | |
desired | -0.209 |
intend | -0.202 |
ern | -0.193 |
baseman | -0.192 |
coat | -0.179 |
Token | ibe |
Token ID | 32438 |
Feature activation | +7.45e-02 |
Pos logit contributions | |
desired | +0.076 |
intend | +0.073 |
baseman | +0.070 |
ern | +0.070 |
gang | +0.065 |
Neg logit contributions | |
arella | -0.088 |
zin | -0.085 |
CFR | -0.083 |
RFC | -0.081 |
bish | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
arella | +0.015 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.013 |
intend | -0.013 |
ern | -0.012 |
baseman | -0.012 |
coat | -0.011 |
Token | which |
Token ID | 543 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.005 |
zin | -0.004 |
CFR | -0.004 |
RFC | -0.004 |
bish | -0.004 |
Token | allowed |
Token ID | 3142 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
desired | +0.042 |
intend | +0.040 |
ern | +0.039 |
baseman | +0.039 |
coat | +0.036 |
Neg logit contributions | |
arella | -0.046 |
zin | -0.043 |
CFR | -0.043 |
RFC | -0.042 |
bish | -0.042 |
Token | thought |
Token ID | 1807 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
desired | +0.027 |
intend | +0.027 |
ern | +0.026 |
baseman | +0.026 |
gang | +0.024 |
Neg logit contributions | |
arella | -0.031 |
zin | -0.030 |
CFR | -0.030 |
RFC | -0.029 |
bish | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
gang | +0.007 |
Neg logit contributions | |
arella | -0.010 |
zin | -0.009 |
CFR | -0.009 |
RFC | -0.009 |
bish | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.012 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.015 |
CFR | -0.015 |
RFC | -0.014 |
bish | -0.014 |
Token | ion |
Token ID | 22088 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | engine |
Token ID | 3113 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | exhaust |
Token ID | 12142 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
arella | +0.009 |
zin | +0.008 |
CFR | +0.008 |
RFC | +0.008 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.008 |
baseman | -0.008 |
coat | -0.007 |
Token | might |
Token ID | 1244 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
arella | +0.235 |
zin | +0.225 |
CFR | +0.224 |
RFC | +0.218 |
bish | +0.215 |
Neg logit contributions | |
desired | -0.229 |
intend | -0.224 |
ern | -0.214 |
baseman | -0.213 |
gang | -0.198 |
Token | interfere |
Token ID | 18135 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
arella | +0.018 |
zin | +0.017 |
CFR | +0.017 |
RFC | +0.016 |
bish | +0.016 |
Neg logit contributions | |
desired | -0.018 |
intend | -0.017 |
ern | -0.016 |
baseman | -0.016 |
coat | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
arella | +0.104 |
zin | +0.100 |
CFR | +0.099 |
RFC | +0.097 |
bish | +0.096 |
Neg logit contributions | |
desired | -0.093 |
intend | -0.088 |
ern | -0.086 |
baseman | -0.085 |
coat | -0.079 |
Token | other |
Token ID | 584 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
arella | +0.013 |
zin | +0.012 |
CFR | +0.012 |
RFC | +0.012 |
bish | +0.012 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.011 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.009 |
Token | spacecraft |
Token ID | 16807 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
arella | +0.035 |
CFR | +0.034 |
zin | +0.033 |
RFC | +0.032 |
bish | +0.032 |
Neg logit contributions | |
desired | -0.037 |
intend | -0.036 |
ern | -0.035 |
baseman | -0.035 |
coat | -0.032 |
Token | Hitch |
Token ID | 36456 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
arella | +0.047 |
zin | +0.045 |
CFR | +0.044 |
RFC | +0.043 |
bish | +0.043 |
Neg logit contributions | |
desired | -0.042 |
intend | -0.040 |
ern | -0.038 |
baseman | -0.038 |
coat | -0.036 |
Token | 's |
Token ID | 338 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
arella | +0.064 |
zin | +0.061 |
CFR | +0.061 |
RFC | +0.060 |
bish | +0.059 |
Neg logit contributions | |
desired | -0.050 |
intend | -0.048 |
ern | -0.046 |
baseman | -0.046 |
coat | -0.042 |
Token | long |
Token ID | 890 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
arella | +0.024 |
zin | +0.023 |
CFR | +0.023 |
RFC | +0.022 |
bish | +0.022 |
Neg logit contributions | |
desired | -0.025 |
intend | -0.024 |
ern | -0.023 |
baseman | -0.023 |
coat | -0.022 |
Token | - |
Token ID | 12 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
arella | +0.056 |
zin | +0.053 |
CFR | +0.053 |
RFC | +0.052 |
bish | +0.051 |
Neg logit contributions | |
desired | -0.047 |
intend | -0.045 |
ern | -0.043 |
baseman | -0.043 |
gang | -0.040 |
Token | time |
Token ID | 2435 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
desired | +0.012 |
intend | +0.012 |
ern | +0.011 |
baseman | +0.011 |
coat | +0.010 |
Neg logit contributions | |
arella | -0.014 |
zin | -0.014 |
CFR | -0.014 |
RFC | -0.013 |
bish | -0.013 |
Token | associate |
Token ID | 11602 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
desired | +0.037 |
intend | +0.036 |
ern | +0.035 |
baseman | +0.034 |
coat | +0.032 |
Neg logit contributions | |
arella | -0.031 |
zin | -0.030 |
CFR | -0.030 |
RFC | -0.029 |
bish | -0.028 |
Token | producer |
Token ID | 9920 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
arella | +0.207 |
zin | +0.198 |
CFR | +0.197 |
RFC | +0.192 |
bish | +0.190 |
Neg logit contributions | |
desired | -0.184 |
intend | -0.177 |
ern | -0.170 |
baseman | -0.169 |
coat | -0.157 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
arella | +0.119 |
zin | +0.114 |
CFR | +0.113 |
RFC | +0.110 |
bish | +0.109 |
Neg logit contributions | |
desired | -0.103 |
intend | -0.100 |
ern | -0.096 |
baseman | -0.095 |
coat | -0.088 |
Token | Joan |
Token ID | 26640 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
desired | +0.006 |
intend | +0.006 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.005 |
Neg logit contributions | |
arella | -0.007 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | Harrison |
Token ID | 17281 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.010 |
zin | -0.010 |
CFR | -0.010 |
RFC | -0.009 |
bish | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
desired | +0.011 |
intend | +0.011 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.011 |
Token | not |
Token ID | 407 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.016 |
ern | +0.015 |
baseman | +0.015 |
coat | +0.014 |
Neg logit contributions | |
arella | -0.021 |
zin | -0.020 |
CFR | -0.020 |
RFC | -0.020 |
bish | -0.019 |
Token | by |
Token ID | 416 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
desired | +0.026 |
intend | +0.025 |
ern | +0.024 |
baseman | +0.024 |
coat | +0.022 |
Neg logit contributions | |
arella | -0.030 |
zin | -0.029 |
CFR | -0.029 |
RFC | -0.028 |
bish | -0.028 |
Token | our |
Token ID | 674 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
arella | +0.012 |
zin | +0.012 |
CFR | +0.012 |
RFC | +0.011 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.011 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.010 |
Token | souls |
Token ID | 15625 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
arella | +0.025 |
zin | +0.024 |
CFR | +0.024 |
RFC | +0.023 |
bish | +0.023 |
Neg logit contributions | |
desired | -0.026 |
intend | -0.025 |
ern | -0.025 |
baseman | -0.024 |
coat | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
desired | +0.103 |
intend | +0.099 |
ern | +0.095 |
baseman | +0.095 |
coat | +0.088 |
Neg logit contributions | |
arella | -0.114 |
zin | -0.109 |
CFR | -0.108 |
RFC | -0.106 |
bish | -0.104 |
Token | it |
Token ID | 340 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
arella | +0.024 |
zin | +0.023 |
CFR | +0.023 |
RFC | +0.022 |
bish | +0.022 |
Neg logit contributions | |
desired | -0.021 |
intend | -0.021 |
ern | -0.020 |
baseman | -0.020 |
coat | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
desired | +0.025 |
intend | +0.024 |
ern | +0.023 |
baseman | +0.023 |
coat | +0.021 |
Neg logit contributions | |
arella | -0.029 |
zin | -0.028 |
CFR | -0.028 |
RFC | -0.027 |
bish | -0.027 |
Token | Every |
Token ID | 3887 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
desired | +0.014 |
intend | +0.013 |
ern | +0.013 |
baseman | +0.013 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.012 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.011 |
bish | -0.011 |
Token | single |
Token ID | 2060 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
desired | +0.022 |
intend | +0.022 |
ern | +0.020 |
baseman | +0.020 |
coat | +0.019 |
Neg logit contributions | |
arella | -0.034 |
zin | -0.033 |
CFR | -0.033 |
RFC | -0.032 |
bish | -0.032 |
Token | time |
Token ID | 640 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
desired | +0.066 |
intend | +0.063 |
ern | +0.060 |
baseman | +0.060 |
coat | +0.055 |
Neg logit contributions | |
arella | -0.093 |
zin | -0.090 |
CFR | -0.089 |
RFC | -0.087 |
bish | -0.086 |
Token | � |
Token ID | 447 |
Feature activation | +8.47e-02 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.004 |
Token | � |
Token ID | 247 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
arella | +0.017 |
zin | +0.016 |
CFR | +0.016 |
RFC | +0.016 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.016 |
intend | -0.015 |
ern | -0.014 |
baseman | -0.014 |
coat | -0.013 |
Token | s |
Token ID | 82 |
Feature activation | +8.96e-02 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
baseman | -0.007 |
ern | -0.007 |
gang | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
arella | +0.019 |
zin | +0.018 |
CFR | +0.018 |
RFC | +0.017 |
bish | +0.017 |
Neg logit contributions | |
desired | -0.016 |
intend | -0.015 |
ern | -0.015 |
baseman | -0.014 |
coat | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
desired | +0.011 |
intend | +0.011 |
ern | +0.010 |
baseman | +0.010 |
coat | +0.010 |
Neg logit contributions | |
arella | -0.013 |
zin | -0.012 |
CFR | -0.012 |
RFC | -0.012 |
bish | -0.012 |
Token | TV |
Token ID | 3195 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.005 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
arella | +0.057 |
zin | +0.055 |
CFR | +0.055 |
RFC | +0.053 |
bish | +0.052 |
Neg logit contributions | |
desired | -0.055 |
intend | -0.053 |
ern | -0.051 |
baseman | -0.051 |
coat | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | -2.41e-04 |
Pos logit contributions | |
desired | +0.000 |
intend | +0.000 |
ern | +0.000 |
baseman | +0.000 |
coat | +0.000 |
Neg logit contributions | |
arella | -0.000 |
zin | -0.000 |
CFR | -0.000 |
RFC | -0.000 |
bish | -0.000 |
Token | feminist |
Token ID | 14314 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
desired | +0.000 |
intend | +0.000 |
ern | +0.000 |
baseman | +0.000 |
coat | +0.000 |
Neg logit contributions | |
arella | -0.000 |
CFR | -0.000 |
zin | -0.000 |
RFC | -0.000 |
bish | -0.000 |
Token | ut |
Token ID | 3384 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
arella | +0.059 |
zin | +0.056 |
CFR | +0.056 |
RFC | +0.055 |
bish | +0.054 |
Neg logit contributions | |
desired | -0.057 |
intend | -0.054 |
ern | -0.052 |
baseman | -0.052 |
gang | -0.049 |
Token | opia |
Token ID | 24464 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
arella | +0.031 |
zin | +0.029 |
CFR | +0.028 |
RFC | +0.027 |
bish | +0.027 |
Neg logit contributions | |
desired | -0.053 |
intend | -0.052 |
ern | -0.050 |
baseman | -0.050 |
coat | -0.048 |
Token | screenshots |
Token ID | 23322 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
arella | +0.020 |
zin | +0.019 |
CFR | +0.019 |
RFC | +0.018 |
bish | +0.018 |
Neg logit contributions | |
desired | -0.020 |
intend | -0.020 |
ern | -0.019 |
baseman | -0.019 |
coat | -0.018 |
Token | introduce |
Token ID | 10400 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
desired | +0.034 |
intend | +0.033 |
ern | +0.032 |
baseman | +0.032 |
coat | +0.030 |
Neg logit contributions | |
arella | -0.034 |
zin | -0.032 |
CFR | -0.032 |
RFC | -0.031 |
bish | -0.031 |
Token | Event |
Token ID | 8558 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
desired | +0.076 |
intend | +0.073 |
ern | +0.070 |
baseman | +0.070 |
coat | +0.065 |
Neg logit contributions | |
arella | -0.078 |
zin | -0.074 |
CFR | -0.073 |
RFC | -0.072 |
bish | -0.070 |
Token | Qu |
Token ID | 2264 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
arella | +0.029 |
zin | +0.028 |
CFR | +0.028 |
RFC | +0.027 |
bish | +0.026 |
Neg logit contributions | |
desired | -0.030 |
intend | -0.029 |
ern | -0.028 |
baseman | -0.028 |
coat | -0.026 |
Token | ests |
Token ID | 3558 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
arella | +0.142 |
zin | +0.137 |
CFR | +0.136 |
RFC | +0.134 |
bish | +0.132 |
Neg logit contributions | |
desired | -0.088 |
intend | -0.084 |
baseman | -0.079 |
ern | -0.079 |
coat | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
desired | +0.156 |
intend | +0.151 |
ern | +0.145 |
baseman | +0.144 |
coat | +0.135 |
Neg logit contributions | |
arella | -0.147 |
zin | -0.140 |
CFR | -0.140 |
RFC | -0.136 |
bish | -0.134 |
Token | Special |
Token ID | 6093 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | Concert |
Token ID | 39220 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.006 |
CFR | +0.006 |
RFC | +0.006 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.007 |
intend | -0.007 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | s |
Token ID | 82 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
arella | +0.029 |
zin | +0.027 |
CFR | +0.027 |
RFC | +0.026 |
bish | +0.026 |
Neg logit contributions | |
desired | -0.033 |
intend | -0.032 |
ern | -0.031 |
baseman | -0.031 |
coat | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
arella | +0.008 |
zin | +0.008 |
CFR | +0.008 |
RFC | +0.008 |
bish | +0.007 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.007 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | new |
Token ID | 649 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | did |
Token ID | 750 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | recommend |
Token ID | 4313 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
desired | +0.016 |
intend | +0.015 |
ern | +0.015 |
baseman | +0.014 |
gang | +0.014 |
Neg logit contributions | |
arella | -0.017 |
CFR | -0.016 |
zin | -0.016 |
RFC | -0.016 |
bish | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
desired | +0.034 |
intend | +0.033 |
ern | +0.032 |
baseman | +0.031 |
coat | +0.030 |
Neg logit contributions | |
arella | -0.036 |
CFR | -0.035 |
zin | -0.035 |
RFC | -0.034 |
bish | -0.033 |
Token | new |
Token ID | 649 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.005 |
CFR | -0.005 |
zin | -0.005 |
RFC | -0.005 |
bish | -0.004 |
Token | level |
Token ID | 1241 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
arella | +0.065 |
CFR | +0.062 |
zin | +0.062 |
RFC | +0.060 |
bish | +0.060 |
Neg logit contributions | |
desired | -0.063 |
intend | -0.061 |
ern | -0.059 |
baseman | -0.058 |
coat | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
arella | +0.144 |
zin | +0.137 |
CFR | +0.137 |
RFC | +0.133 |
bish | +0.131 |
Neg logit contributions | |
desired | -0.142 |
intend | -0.138 |
ern | -0.132 |
baseman | -0.131 |
coat | -0.123 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
gang | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.006 |
CFR | +0.006 |
RFC | +0.006 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | ST |
Token ID | 2257 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.004 |
Token | ORY |
Token ID | 15513 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
desired | +0.059 |
intend | +0.057 |
ern | +0.055 |
baseman | +0.055 |
coat | +0.051 |
Neg logit contributions | |
arella | -0.060 |
zin | -0.057 |
CFR | -0.057 |
RFC | -0.055 |
bish | -0.055 |
Token | 's |
Token ID | 338 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.004 |
CFR | -0.004 |
RFC | -0.004 |
bish | -0.004 |
Token | no |
Token ID | 645 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
arella | +0.040 |
zin | +0.039 |
CFR | +0.038 |
RFC | +0.037 |
bish | +0.037 |
Neg logit contributions | |
desired | -0.036 |
intend | -0.035 |
ern | -0.033 |
baseman | -0.033 |
gang | -0.031 |
Token | good |
Token ID | 922 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
arella | +0.039 |
zin | +0.038 |
CFR | +0.038 |
RFC | +0.037 |
bish | +0.036 |
Neg logit contributions | |
desired | -0.032 |
intend | -0.031 |
ern | -0.030 |
baseman | -0.030 |
coat | -0.027 |
Token | ! |
Token ID | 0 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
arella | +0.026 |
zin | +0.025 |
CFR | +0.025 |
RFC | +0.024 |
bish | +0.024 |
Neg logit contributions | |
desired | -0.021 |
intend | -0.021 |
ern | -0.020 |
baseman | -0.020 |
coat | -0.018 |
Token | The |
Token ID | 383 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.006 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.005 |
Token | stack |
Token ID | 8931 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
arella | +0.020 |
zin | +0.019 |
CFR | +0.019 |
RFC | +0.019 |
bish | +0.019 |
Neg logit contributions | |
desired | -0.019 |
intend | -0.018 |
ern | -0.017 |
baseman | -0.017 |
coat | -0.016 |
Token | pointer |
Token ID | 17562 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
arella | +0.029 |
zin | +0.027 |
CFR | +0.027 |
RFC | +0.027 |
bish | +0.026 |
Neg logit contributions | |
desired | -0.023 |
intend | -0.022 |
ern | -0.021 |
baseman | -0.021 |
coat | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
desired | +0.035 |
intend | +0.033 |
ern | +0.032 |
baseman | +0.032 |
coat | +0.030 |
Neg logit contributions | |
arella | -0.037 |
zin | -0.035 |
CFR | -0.035 |
RFC | -0.034 |
bish | -0.033 |
Token | pointing |
Token ID | 10609 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
desired | +0.022 |
intend | +0.021 |
ern | +0.020 |
baseman | +0.020 |
coat | +0.019 |
Neg logit contributions | |
arella | -0.023 |
zin | -0.022 |
CFR | -0.022 |
RFC | -0.021 |
bish | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.69e-03 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.006 |
CFR | +0.006 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.004 |
Token | feet |
Token ID | 3625 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
desired | +0.102 |
intend | +0.100 |
ern | +0.096 |
baseman | +0.095 |
coat | +0.090 |
Neg logit contributions | |
arella | -0.100 |
CFR | -0.095 |
zin | -0.095 |
RFC | -0.092 |
bish | -0.091 |
Token | for |
Token ID | 329 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
arella | +0.042 |
zin | +0.040 |
CFR | +0.039 |
RFC | +0.038 |
bish | +0.038 |
Neg logit contributions | |
desired | -0.039 |
intend | -0.038 |
ern | -0.036 |
baseman | -0.036 |
gang | -0.034 |
Token | hours |
Token ID | 2250 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
arella | +0.016 |
CFR | +0.015 |
zin | +0.015 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.013 |
intend | -0.013 |
baseman | -0.012 |
ern | -0.012 |
gang | -0.011 |
Token | every |
Token ID | 790 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
arella | +0.047 |
zin | +0.045 |
CFR | +0.045 |
RFC | +0.044 |
bish | +0.043 |
Neg logit contributions | |
desired | -0.043 |
intend | -0.041 |
ern | -0.040 |
baseman | -0.039 |
gang | -0.037 |
Token | day |
Token ID | 1110 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
arella | +0.012 |
zin | +0.011 |
CFR | +0.011 |
RFC | +0.011 |
bish | +0.011 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.007 |
baseman | -0.007 |
gang | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
desired | +0.072 |
intend | +0.070 |
ern | +0.067 |
baseman | +0.066 |
gang | +0.062 |
Neg logit contributions | |
arella | -0.083 |
zin | -0.079 |
CFR | -0.079 |
RFC | -0.077 |
bish | -0.076 |
Token | you |
Token ID | 345 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.009 |
baseman | +0.009 |
gang | +0.009 |
Neg logit contributions | |
arella | -0.013 |
CFR | -0.012 |
zin | -0.012 |
RFC | -0.012 |
bish | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
desired | +0.016 |
intend | +0.015 |
ern | +0.015 |
baseman | +0.015 |
gang | +0.014 |
Neg logit contributions | |
arella | -0.017 |
zin | -0.017 |
CFR | -0.017 |
RFC | -0.016 |
bish | -0.016 |
Token | at |
Token ID | 379 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
desired | +0.014 |
intend | +0.014 |
ern | +0.013 |
baseman | +0.013 |
gang | +0.012 |
Neg logit contributions | |
arella | -0.015 |
CFR | -0.014 |
zin | -0.014 |
RFC | -0.014 |
bish | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
arella | +0.014 |
CFR | +0.014 |
zin | +0.014 |
RFC | +0.013 |
bish | +0.013 |
Neg logit contributions | |
desired | -0.013 |
intend | -0.013 |
ern | -0.012 |
baseman | -0.012 |
coat | -0.011 |
Token | convention |
Token ID | 9831 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | 41 |
Token ID | 6073 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
arella | +0.013 |
zin | +0.013 |
CFR | +0.013 |
RFC | +0.012 |
bish | +0.012 |
Neg logit contributions | |
desired | -0.015 |
intend | -0.015 |
ern | -0.015 |
baseman | -0.015 |
coat | -0.014 |
Token | minutes |
Token ID | 2431 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
arella | +0.141 |
zin | +0.135 |
CFR | +0.134 |
RFC | +0.131 |
bish | +0.129 |
Neg logit contributions | |
desired | -0.116 |
intend | -0.112 |
ern | -0.107 |
baseman | -0.106 |
coat | -0.099 |
Token | after |
Token ID | 706 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
desired | +0.025 |
intend | +0.024 |
ern | +0.023 |
baseman | +0.022 |
coat | +0.021 |
Neg logit contributions | |
arella | -0.032 |
zin | -0.030 |
CFR | -0.030 |
RFC | -0.030 |
bish | -0.029 |
Token | launch |
Token ID | 4219 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.010 |
CFR | +0.010 |
RFC | +0.010 |
bish | +0.009 |
Neg logit contributions | |
desired | -0.009 |
intend | -0.009 |
ern | -0.009 |
baseman | -0.009 |
coat | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
arella | +0.016 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.015 |
bish | +0.015 |
Neg logit contributions | |
desired | -0.012 |
intend | -0.012 |
ern | -0.011 |
baseman | -0.011 |
coat | -0.010 |
Token | This |
Token ID | 770 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | 41 |
Token ID | 6073 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
desired | +0.028 |
intend | +0.028 |
ern | +0.026 |
baseman | +0.026 |
coat | +0.025 |
Neg logit contributions | |
arella | -0.030 |
CFR | -0.029 |
zin | -0.029 |
RFC | -0.028 |
bish | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
arella | +0.146 |
zin | +0.139 |
CFR | +0.138 |
RFC | +0.136 |
bish | +0.134 |
Neg logit contributions | |
desired | -0.114 |
intend | -0.109 |
ern | -0.105 |
baseman | -0.104 |
coat | -0.096 |
Token | 2 |
Token ID | 17 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.007 |
intend | -0.006 |
ern | -0.006 |
baseman | -0.006 |
coat | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.007 |
ern | +0.007 |
baseman | +0.007 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.008 |
Token | meter |
Token ID | 27231 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | they |
Token ID | 484 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
desired | +0.056 |
intend | +0.053 |
ern | +0.052 |
baseman | +0.051 |
coat | +0.048 |
Neg logit contributions | |
arella | -0.053 |
zin | -0.051 |
CFR | -0.050 |
RFC | -0.049 |
bish | -0.048 |
Token | should |
Token ID | 815 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
arella | +0.033 |
zin | +0.032 |
CFR | +0.032 |
RFC | +0.031 |
bish | +0.030 |
Neg logit contributions | |
desired | -0.028 |
intend | -0.027 |
ern | -0.026 |
baseman | -0.026 |
coat | -0.024 |
Token | ask |
Token ID | 1265 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
desired | +0.046 |
intend | +0.044 |
ern | +0.042 |
baseman | +0.042 |
coat | +0.039 |
Neg logit contributions | |
arella | -0.051 |
zin | -0.049 |
CFR | -0.048 |
RFC | -0.047 |
bish | -0.047 |
Token | me |
Token ID | 502 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
arella | +0.033 |
zin | +0.031 |
CFR | +0.031 |
RFC | +0.030 |
bish | +0.030 |
Neg logit contributions | |
desired | -0.033 |
intend | -0.031 |
ern | -0.030 |
baseman | -0.030 |
coat | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
arella | +0.049 |
zin | +0.047 |
CFR | +0.047 |
RFC | +0.045 |
bish | +0.045 |
Neg logit contributions | |
desired | -0.045 |
intend | -0.044 |
ern | -0.042 |
baseman | -0.042 |
coat | -0.039 |
Token | I |
Token ID | 314 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
desired | +0.010 |
intend | +0.010 |
ern | +0.009 |
baseman | +0.009 |
coat | +0.009 |
Neg logit contributions | |
arella | -0.009 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
desired | +0.009 |
intend | +0.008 |
ern | +0.008 |
baseman | +0.008 |
coat | +0.008 |
Neg logit contributions | |
arella | -0.010 |
zin | -0.009 |
CFR | -0.009 |
RFC | -0.009 |
bish | -0.009 |
Token | � |
Token ID | 564 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
desired | +0.013 |
intend | +0.012 |
ern | +0.012 |
baseman | +0.012 |
coat | +0.011 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.014 |
CFR | -0.014 |
RFC | -0.014 |
bish | -0.013 |
Token | � |
Token ID | 250 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
baseman | +0.007 |
ern | +0.007 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.006 |
CFR | -0.006 |
RFC | -0.006 |
bish | -0.006 |
Token | Of |
Token ID | 5189 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
desired | +0.015 |
intend | +0.015 |
baseman | +0.014 |
ern | +0.014 |
coat | +0.013 |
Neg logit contributions | |
arella | -0.016 |
zin | -0.015 |
CFR | -0.015 |
RFC | -0.015 |
bish | -0.015 |
Token | course |
Token ID | 1781 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
desired | +0.001 |
intend | +0.001 |
ern | +0.001 |
baseman | +0.001 |
coat | +0.001 |
Neg logit contributions | |
arella | -0.001 |
zin | -0.001 |
CFR | -0.001 |
RFC | -0.001 |
bish | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
arella | +0.030 |
zin | +0.029 |
CFR | +0.029 |
RFC | +0.028 |
bish | +0.028 |
Neg logit contributions | |
desired | -0.024 |
intend | -0.023 |
ern | -0.022 |
baseman | -0.022 |
coat | -0.020 |
Token | The |
Token ID | 383 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | New |
Token ID | 968 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
arella | +0.007 |
zin | +0.007 |
CFR | +0.007 |
RFC | +0.006 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.007 |
ern | -0.007 |
baseman | -0.007 |
coat | -0.007 |
Token | York |
Token ID | 1971 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
arella | +0.035 |
zin | +0.033 |
CFR | +0.033 |
RFC | +0.032 |
bish | +0.031 |
Neg logit contributions | |
desired | -0.049 |
intend | -0.048 |
ern | -0.047 |
baseman | -0.046 |
coat | -0.044 |
Token | Times |
Token ID | 3782 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
arella | +0.093 |
CFR | +0.089 |
zin | +0.089 |
RFC | +0.086 |
bish | +0.085 |
Neg logit contributions | |
desired | -0.068 |
intend | -0.065 |
ern | -0.062 |
baseman | -0.061 |
coat | -0.057 |
Token | published |
Token ID | 3199 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
desired | +0.060 |
intend | +0.058 |
ern | +0.056 |
baseman | +0.055 |
ocked | +0.052 |
Neg logit contributions | |
arella | -0.059 |
zin | -0.056 |
CFR | -0.056 |
RFC | -0.055 |
bish | -0.054 |
Token | an |
Token ID | 281 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
desired | +0.064 |
intend | +0.061 |
ern | +0.057 |
baseman | +0.057 |
coat | +0.052 |
Neg logit contributions | |
arella | -0.107 |
zin | -0.103 |
CFR | -0.103 |
RFC | -0.101 |
bish | -0.100 |
Token | investigation |
Token ID | 3645 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
desired | +0.054 |
intend | +0.052 |
ern | +0.049 |
baseman | +0.048 |
coat | +0.044 |
Neg logit contributions | |
arella | -0.100 |
zin | -0.097 |
CFR | -0.096 |
RFC | -0.094 |
bish | -0.093 |
Token | showing |
Token ID | 4478 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
desired | +0.051 |
intend | +0.049 |
ern | +0.047 |
baseman | +0.047 |
coat | +0.043 |
Neg logit contributions | |
arella | -0.062 |
zin | -0.059 |
CFR | -0.059 |
RFC | -0.058 |
bish | -0.057 |
Token | that |
Token ID | 326 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
desired | +0.020 |
intend | +0.019 |
ern | +0.018 |
baseman | +0.018 |
coat | +0.017 |
Neg logit contributions | |
arella | -0.023 |
zin | -0.022 |
CFR | -0.022 |
RFC | -0.022 |
bish | -0.022 |
Token | letters |
Token ID | 7475 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.017 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.017 |
zin | -0.016 |
CFR | -0.015 |
RFC | -0.015 |
bish | -0.015 |
Token | ugh |
Token ID | 6724 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
desired | +0.026 |
intend | +0.026 |
ern | +0.025 |
baseman | +0.024 |
coat | +0.023 |
Neg logit contributions | |
arella | -0.026 |
zin | -0.025 |
CFR | -0.025 |
RFC | -0.024 |
bish | -0.024 |
Token | [ |
Token ID | 685 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
desired | +0.020 |
intend | +0.019 |
ern | +0.018 |
baseman | +0.018 |
coat | +0.017 |
Neg logit contributions | |
arella | -0.021 |
zin | -0.020 |
CFR | -0.020 |
RFC | -0.020 |
bish | -0.019 |
Token | who |
Token ID | 8727 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
arella | +0.041 |
zin | +0.039 |
CFR | +0.038 |
RFC | +0.037 |
bish | +0.037 |
Neg logit contributions | |
desired | -0.040 |
intend | -0.039 |
ern | -0.037 |
baseman | -0.037 |
coat | -0.034 |
Token | died |
Token ID | 3724 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
desired | +0.050 |
intend | +0.048 |
ern | +0.046 |
baseman | +0.046 |
coat | +0.043 |
Neg logit contributions | |
arella | -0.056 |
zin | -0.053 |
CFR | -0.053 |
RFC | -0.052 |
bish | -0.051 |
Token | last |
Token ID | 938 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
desired | +0.047 |
intend | +0.045 |
ern | +0.043 |
baseman | +0.043 |
coat | +0.040 |
Neg logit contributions | |
arella | -0.049 |
zin | -0.047 |
CFR | -0.047 |
RFC | -0.046 |
bish | -0.045 |
Token | week |
Token ID | 1285 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.017 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.014 |
zin | -0.014 |
CFR | -0.014 |
RFC | -0.013 |
bish | -0.013 |
Token | at |
Token ID | 379 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
desired | +0.042 |
intend | +0.041 |
ern | +0.040 |
baseman | +0.039 |
coat | +0.037 |
Neg logit contributions | |
arella | -0.037 |
zin | -0.035 |
CFR | -0.035 |
RFC | -0.034 |
bish | -0.034 |
Token | 70 |
Token ID | 4317 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
arella | +0.016 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.015 |
intend | -0.015 |
ern | -0.014 |
baseman | -0.014 |
coat | -0.013 |
Token | ]. |
Token ID | 4083 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.007 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.005 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token | Whenever |
Token ID | 21326 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
arella | +0.031 |
zin | +0.030 |
CFR | +0.030 |
RFC | +0.029 |
bish | +0.029 |
Neg logit contributions | |
desired | -0.034 |
intend | -0.033 |
ern | -0.032 |
baseman | -0.032 |
coat | -0.030 |
Token | she |
Token ID | 673 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
arella | +0.035 |
zin | +0.033 |
CFR | +0.033 |
RFC | +0.032 |
bish | +0.032 |
Neg logit contributions | |
desired | -0.037 |
intend | -0.036 |
ern | -0.034 |
baseman | -0.034 |
coat | -0.032 |
Token | came |
Token ID | 1625 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
desired | +0.089 |
intend | +0.086 |
ern | +0.083 |
baseman | +0.082 |
coat | +0.077 |
Neg logit contributions | |
arella | -0.090 |
zin | -0.086 |
CFR | -0.085 |
RFC | -0.083 |
bish | -0.082 |
Token | from |
Token ID | 422 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
arella | +0.039 |
zin | +0.038 |
CFR | +0.038 |
RFC | +0.037 |
bish | +0.036 |
Neg logit contributions | |
desired | -0.029 |
intend | -0.028 |
ern | -0.026 |
baseman | -0.026 |
coat | -0.024 |
Token | this |
Token ID | 428 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
desired | +0.025 |
intend | +0.024 |
ern | +0.023 |
baseman | +0.022 |
coat | +0.021 |
Neg logit contributions | |
arella | -0.030 |
zin | -0.029 |
CFR | -0.028 |
RFC | -0.028 |
bish | -0.027 |
Token | election |
Token ID | 3071 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
desired | +0.025 |
intend | +0.024 |
ern | +0.023 |
baseman | +0.023 |
coat | +0.021 |
Neg logit contributions | |
arella | -0.027 |
zin | -0.026 |
CFR | -0.026 |
RFC | -0.025 |
bish | -0.025 |
Token | leaf |
Token ID | 12835 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
desired | +0.055 |
intend | +0.053 |
ern | +0.051 |
baseman | +0.050 |
coat | +0.047 |
Neg logit contributions | |
arella | -0.055 |
zin | -0.052 |
CFR | -0.052 |
RFC | -0.051 |
bish | -0.050 |
Token | let |
Token ID | 1616 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
desired | +0.021 |
intend | +0.019 |
ern | +0.017 |
baseman | +0.017 |
coat | +0.014 |
Neg logit contributions | |
arella | -0.083 |
zin | -0.080 |
CFR | -0.080 |
RFC | -0.079 |
bish | -0.078 |
Token | Julian |
Token ID | 18322 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
desired | +0.202 |
intend | +0.194 |
ern | +0.186 |
baseman | +0.185 |
coat | +0.173 |
Neg logit contributions | |
arella | -0.228 |
zin | -0.217 |
CFR | -0.216 |
RFC | -0.211 |
bish | -0.208 |
Token | found |
Token ID | 1043 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
desired | +0.037 |
intend | +0.036 |
ern | +0.035 |
baseman | +0.035 |
coat | +0.032 |
Neg logit contributions | |
arella | -0.036 |
zin | -0.034 |
CFR | -0.034 |
RFC | -0.033 |
bish | -0.032 |
Token | in |
Token ID | 287 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
arella | +0.139 |
zin | +0.133 |
CFR | +0.132 |
RFC | +0.129 |
bish | +0.127 |
Neg logit contributions | |
desired | -0.125 |
intend | -0.121 |
ern | -0.116 |
baseman | -0.116 |
coat | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
arella | +0.014 |
zin | +0.013 |
CFR | +0.013 |
RFC | +0.013 |
bish | +0.012 |
Neg logit contributions | |
desired | -0.011 |
intend | -0.011 |
ern | -0.010 |
baseman | -0.010 |
coat | -0.009 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | Chennai |
Token ID | 47678 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.005 |
CFR | +0.005 |
RFC | +0.005 |
bish | +0.005 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
arella | +0.016 |
zin | +0.015 |
CFR | +0.015 |
RFC | +0.014 |
bish | +0.014 |
Neg logit contributions | |
desired | -0.012 |
intend | -0.012 |
ern | -0.011 |
baseman | -0.011 |
coat | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
ern | +0.004 |
baseman | +0.004 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.005 |
ern | -0.005 |
baseman | -0.005 |
coat | -0.005 |
Token | AP |
Token ID | 2969 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.005 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.004 |
Token | Photo |
Token ID | 5555 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
arella | +0.118 |
zin | +0.114 |
CFR | +0.113 |
RFC | +0.111 |
bish | +0.110 |
Neg logit contributions | |
desired | -0.064 |
intend | -0.061 |
ern | -0.058 |
baseman | -0.057 |
coat | -0.052 |
Token | Rescue |
Token ID | 17285 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
desired | +0.206 |
intend | +0.199 |
ern | +0.193 |
baseman | +0.191 |
coat | +0.181 |
Neg logit contributions | |
arella | -0.166 |
zin | -0.157 |
CFR | -0.155 |
RFC | -0.152 |
bish | -0.149 |
Token | workers |
Token ID | 3259 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
desired | +0.016 |
intend | +0.016 |
ern | +0.015 |
baseman | +0.015 |
coat | +0.014 |
Neg logit contributions | |
arella | -0.015 |
zin | -0.014 |
CFR | -0.014 |
RFC | -0.013 |
bish | -0.013 |
Token | carry |
Token ID | 3283 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
arella | +0.081 |
zin | +0.078 |
CFR | +0.078 |
RFC | +0.075 |
bish | +0.075 |
Neg logit contributions | |
desired | -0.073 |
intend | -0.071 |
ern | -0.068 |
baseman | -0.067 |
gang | -0.063 |
Token | food |
Token ID | 2057 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
desired | +0.031 |
intend | +0.030 |
ern | +0.029 |
baseman | +0.029 |
coat | +0.027 |
Neg logit contributions | |
arella | -0.037 |
zin | -0.035 |
CFR | -0.035 |
RFC | -0.034 |
bish | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
arella | +0.058 |
zin | +0.055 |
CFR | +0.055 |
RFC | +0.053 |
bish | +0.053 |
Neg logit contributions | |
desired | -0.054 |
intend | -0.052 |
ern | -0.050 |
baseman | -0.050 |
coat | -0.047 |
Token | showcasing |
Token ID | 40318 |
Feature activation | +6.10e-03 |
Pos logit contributions | |
arella | +0.021 |
zin | +0.020 |
CFR | +0.020 |
RFC | +0.019 |
bish | +0.019 |
Neg logit contributions | |
desired | -0.019 |
intend | -0.018 |
ern | -0.017 |
baseman | -0.017 |
coat | -0.016 |
Token | prolific |
Token ID | 28892 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
arella | +0.001 |
zin | +0.001 |
CFR | +0.001 |
RFC | +0.001 |
bish | +0.001 |
Neg logit contributions | |
desired | -0.001 |
intend | -0.001 |
ern | -0.001 |
baseman | -0.001 |
coat | -0.001 |
Token | � |
Token ID | 564 |
Feature activation | +8.94e-04 |
Pos logit contributions | |
desired | +0.045 |
intend | +0.044 |
ern | +0.042 |
baseman | +0.042 |
coat | +0.039 |
Neg logit contributions | |
arella | -0.044 |
zin | -0.042 |
CFR | -0.042 |
RFC | -0.041 |
bish | -0.040 |
Token | � |
Token ID | 250 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
arella | +0.000 |
zin | +0.000 |
CFR | +0.000 |
RFC | +0.000 |
bish | +0.000 |
Neg logit contributions | |
desired | -0.000 |
intend | -0.000 |
ern | -0.000 |
baseman | -0.000 |
coat | -0.000 |
Token | N |
Token ID | 45 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
desired | +0.008 |
intend | +0.008 |
ern | +0.008 |
baseman | +0.008 |
coat | +0.007 |
Neg logit contributions | |
arella | -0.008 |
zin | -0.008 |
CFR | -0.008 |
RFC | -0.008 |
bish | -0.008 |
Token | ind |
Token ID | 521 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.003 |
ern | +0.003 |
baseman | +0.003 |
coat | +0.003 |
Neg logit contributions | |
arella | -0.013 |
zin | -0.013 |
CFR | -0.013 |
RFC | -0.012 |
bish | -0.012 |
Token | ies |
Token ID | 444 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
desired | +0.260 |
intend | +0.254 |
ern | +0.245 |
baseman | +0.241 |
coat | +0.227 |
Neg logit contributions | |
arella | -0.252 |
CFR | -0.239 |
zin | -0.239 |
RFC | -0.233 |
bish | -0.228 |
Token | � |
Token ID | 447 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.006 |
CFR | +0.006 |
RFC | +0.006 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.006 |
intend | -0.006 |
ern | -0.006 |
baseman | -0.006 |
coat | -0.006 |
Token | � |
Token ID | 251 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
arella | +0.010 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.009 |
bish | +0.009 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.008 |
baseman | -0.008 |
coat | -0.007 |
Token | as |
Token ID | 355 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
desired | +0.002 |
intend | +0.002 |
ern | +0.002 |
baseman | +0.002 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | well |
Token ID | 880 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
desired | +0.015 |
intend | +0.014 |
ern | +0.014 |
baseman | +0.013 |
coat | +0.012 |
Neg logit contributions | |
arella | -0.018 |
zin | -0.017 |
CFR | -0.017 |
RFC | -0.017 |
bish | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
desired | +0.017 |
intend | +0.017 |
ern | +0.016 |
baseman | +0.016 |
coat | +0.015 |
Neg logit contributions | |
arella | -0.022 |
zin | -0.021 |
CFR | -0.021 |
RFC | -0.020 |
bish | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
desired | +0.007 |
intend | +0.006 |
ern | +0.006 |
baseman | +0.006 |
coat | +0.006 |
Neg logit contributions | |
arella | -0.006 |
zin | -0.005 |
CFR | -0.005 |
RFC | -0.005 |
bish | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
desired | +0.003 |
intend | +0.003 |
baseman | +0.003 |
ern | +0.003 |
coat | +0.002 |
Neg logit contributions | |
arella | -0.002 |
zin | -0.002 |
CFR | -0.002 |
RFC | -0.002 |
bish | -0.002 |
Token | If |
Token ID | 1532 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
desired | +0.005 |
intend | +0.005 |
ern | +0.005 |
baseman | +0.005 |
coat | +0.004 |
Neg logit contributions | |
arella | -0.004 |
zin | -0.004 |
CFR | -0.004 |
RFC | -0.004 |
bish | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
arella | +0.022 |
zin | +0.021 |
CFR | +0.021 |
RFC | +0.021 |
bish | +0.021 |
Neg logit contributions | |
desired | -0.017 |
intend | -0.017 |
ern | -0.016 |
baseman | -0.016 |
coat | -0.015 |
Token | homeowner |
Token ID | 40130 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
desired | +0.012 |
intend | +0.011 |
ern | +0.011 |
baseman | +0.011 |
coat | +0.010 |
Neg logit contributions | |
arella | -0.011 |
zin | -0.011 |
CFR | -0.011 |
RFC | -0.010 |
bish | -0.010 |
Token | � |
Token ID | 447 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
desired | +0.214 |
intend | +0.209 |
ern | +0.199 |
baseman | +0.198 |
gang | +0.186 |
Neg logit contributions | |
arella | -0.224 |
zin | -0.214 |
CFR | -0.214 |
RFC | -0.208 |
bish | -0.205 |
Token | � |
Token ID | 247 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
arella | +0.008 |
zin | +0.007 |
CFR | +0.007 |
RFC | +0.007 |
bish | +0.007 |
Neg logit contributions | |
desired | -0.007 |
intend | -0.007 |
baseman | -0.006 |
ern | -0.006 |
coat | -0.006 |
Token | s |
Token ID | 82 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
desired | +0.004 |
intend | +0.004 |
baseman | +0.004 |
ern | +0.004 |
gang | +0.004 |
Neg logit contributions | |
arella | -0.003 |
zin | -0.003 |
CFR | -0.003 |
RFC | -0.003 |
bish | -0.003 |
Token | curb |
Token ID | 20799 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
arella | +0.004 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.004 |
intend | -0.004 |
ern | -0.004 |
baseman | -0.004 |
coat | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
arella | +0.075 |
zin | +0.071 |
CFR | +0.071 |
RFC | +0.069 |
bish | +0.068 |
Neg logit contributions | |
desired | -0.068 |
intend | -0.065 |
ern | -0.062 |
baseman | -0.062 |
gang | -0.058 |
Token | ub |
Token ID | 549 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
desired | +0.088 |
intend | +0.085 |
baseman | +0.081 |
ern | +0.081 |
coat | +0.076 |
Neg logit contributions | |
arella | -0.087 |
zin | -0.083 |
CFR | -0.082 |
RFC | -0.080 |
bish | -0.078 |
Token | ges |
Token ID | 3212 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
arella | +0.005 |
zin | +0.004 |
CFR | +0.004 |
RFC | +0.004 |
bish | +0.004 |
Neg logit contributions | |
desired | -0.005 |
intend | -0.004 |
baseman | -0.004 |
ern | -0.004 |
coat | -0.004 |
Token | hig |
Token ID | 25196 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
desired | +0.028 |
intend | +0.027 |
baseman | +0.026 |
ern | +0.026 |
coat | +0.025 |
Neg logit contributions | |
arella | -0.017 |
zin | -0.016 |
CFR | -0.016 |
RFC | -0.015 |
bish | -0.015 |
Token | Rice |
Token ID | 13823 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
arella | +0.142 |
CFR | +0.138 |
zin | +0.137 |
RFC | +0.134 |
bish | +0.131 |
Neg logit contributions | |
desired | -0.072 |
intend | -0.069 |
baseman | -0.065 |
ern | -0.065 |
coat | -0.058 |
Token | / |
Token ID | 14 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
desired | +0.142 |
intend | +0.137 |
baseman | +0.131 |
ern | +0.130 |
coat | +0.120 |
Neg logit contributions | |
arella | -0.172 |
CFR | -0.165 |
zin | -0.165 |
RFC | -0.161 |
bish | -0.157 |
Token | CBC |
Token ID | 29208 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
desired | +0.020 |
intend | +0.019 |
baseman | +0.018 |
ern | +0.018 |
coat | +0.016 |
Neg logit contributions | |
arella | -0.041 |
zin | -0.040 |
CFR | -0.040 |
RFC | -0.039 |
bish | -0.039 |
Token | ) |
Token ID | 8 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
desired | +0.175 |
intend | +0.168 |
ern | +0.160 |
baseman | +0.159 |
coat | +0.147 |
Neg logit contributions | |
arella | -0.241 |
zin | -0.231 |
CFR | -0.230 |
RFC | -0.226 |
bish | -0.223 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
desired | +0.021 |
intend | +0.020 |
ern | +0.020 |
baseman | +0.019 |
coat | +0.018 |
Neg logit contributions | |
arella | -0.018 |
zin | -0.017 |
CFR | -0.017 |
RFC | -0.017 |
bish | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
arella | +0.006 |
zin | +0.006 |
CFR | +0.006 |
RFC | +0.006 |
bish | +0.006 |
Neg logit contributions | |
desired | -0.008 |
intend | -0.008 |
ern | -0.008 |
baseman | -0.008 |
coat | -0.007 |
Token | Insp |
Token ID | 41502 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
arella | +0.009 |
zin | +0.009 |
CFR | +0.009 |
RFC | +0.009 |
bish | +0.008 |
Neg logit contributions | |
desired | -0.009 |
intend | -0.009 |
ern | -0.009 |
baseman | -0.009 |
coat | -0.008 |
Token | ired |
Token ID | 1202 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
desired | +0.105 |
intend | +0.101 |
ern | +0.096 |
baseman | +0.096 |
coat | +0.088 |
Neg logit contributions | |
arella | -0.148 |
zin | -0.142 |
CFR | -0.141 |
RFC | -0.138 |
bish | -0.137 |