Token | They |
Token ID | 1119 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.007 |
Nem | +0.007 |
le | +0.006 |
Twe | +0.006 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
rum | -0.005 |
Token | burst |
Token ID | 11173 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Twe | +0.022 |
ot | +0.022 |
Nem | +0.020 |
le | +0.020 |
Twe | +0.020 |
Neg logit contributions | |
outage | -0.032 |
ouncing | -0.031 |
hole | -0.031 |
ying | -0.030 |
ma | -0.029 |
Token | open |
Token ID | 1280 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
outage | +0.012 |
hole | +0.012 |
ouncing | +0.011 |
lessly | +0.011 |
ying | +0.011 |
Neg logit contributions | |
Twe | -0.015 |
Twe | -0.015 |
ot | -0.014 |
le | -0.014 |
Nem | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
ying | +0.005 |
hole | +0.005 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
Nem | -0.006 |
le | -0.005 |
Twe | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.003 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
le | -0.004 |
Twe | -0.004 |
Token | million |
Token ID | 1510 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
ouncing | +0.015 |
outage | +0.015 |
ying | +0.014 |
hole | +0.014 |
rum | +0.014 |
Neg logit contributions | |
Twe | -0.011 |
ot | -0.011 |
le | -0.010 |
Nem | -0.010 |
Twe | -0.010 |
Token | different |
Token ID | 1180 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
outage | +0.133 |
hole | +0.128 |
ying | +0.120 |
ouncing | +0.119 |
lessly | +0.119 |
Neg logit contributions | |
Twe | -0.161 |
Twe | -0.153 |
ot | -0.152 |
Nem | -0.148 |
le | -0.143 |
Token | colours |
Token ID | 18915 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
outage | +0.023 |
hole | +0.022 |
ouncing | +0.022 |
ying | +0.022 |
ma | +0.021 |
Neg logit contributions | |
Twe | -0.024 |
ot | -0.022 |
Twe | -0.022 |
Nem | -0.022 |
le | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
le | +0.002 |
Nem | +0.002 |
Twe | +0.001 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
hole | -0.002 |
ying | -0.002 |
ma | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Twe | +0.024 |
ot | +0.023 |
Twe | +0.022 |
Nem | +0.022 |
le | +0.021 |
Neg logit contributions | |
outage | -0.029 |
ouncing | -0.028 |
hole | -0.028 |
ying | -0.027 |
ma | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
Twe | +0.015 |
Twe | +0.014 |
ot | +0.014 |
Nem | +0.014 |
jew | +0.013 |
Neg logit contributions | |
outage | -0.017 |
hole | -0.016 |
ouncing | -0.016 |
lessly | -0.015 |
ows | -0.015 |
Token | v |
Token ID | 410 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Twe | +0.003 |
Nem | +0.003 |
Twe | +0.003 |
ot | +0.003 |
Bub | +0.003 |
Neg logit contributions | |
outage | -0.004 |
ma | -0.004 |
hole | -0.004 |
click | -0.004 |
ouncing | -0.004 |
Token | ase |
Token ID | 589 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Nem | +0.056 |
ot | +0.055 |
Twe | +0.055 |
jew | +0.051 |
Bub | +0.051 |
Neg logit contributions | |
ouncing | -0.031 |
outage | -0.028 |
ying | -0.027 |
ows | -0.026 |
hole | -0.025 |
Token | broke |
Token ID | 6265 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
outage | +0.008 |
ouncing | +0.008 |
hole | +0.008 |
ying | +0.008 |
ma | +0.008 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
Nem | -0.005 |
Twe | -0.004 |
le | -0.004 |
Token | into |
Token ID | 656 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
outage | +0.012 |
ouncing | +0.011 |
hole | +0.011 |
ying | +0.011 |
lessly | +0.010 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.015 |
Nem | -0.015 |
Twe | -0.015 |
le | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
outage | +0.001 |
hole | +0.001 |
ouncing | +0.001 |
ying | +0.001 |
ma | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Nem | -0.001 |
Twe | -0.001 |
le | -0.001 |
Token | million |
Token ID | 1510 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
ouncing | +0.019 |
ying | +0.019 |
outage | +0.017 |
ows | +0.017 |
hole | +0.017 |
Neg logit contributions | |
Twe | -0.026 |
ot | -0.026 |
le | -0.025 |
jew | -0.024 |
Twe | -0.024 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
hole | +0.111 |
outage | +0.106 |
rum | +0.096 |
instant | +0.096 |
lessly | +0.094 |
Neg logit contributions | |
Twe | -0.166 |
Twe | -0.163 |
Nem | -0.161 |
ot | -0.161 |
Bub | -0.149 |
Token | and |
Token ID | 290 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
ouncing | +0.062 |
Deal | +0.061 |
outage | +0.061 |
Today | +0.059 |
ma | +0.058 |
Neg logit contributions | |
Twe | -0.042 |
ot | -0.041 |
le | -0.039 |
Nem | -0.038 |
se | -0.037 |
Token | they |
Token ID | 484 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ot | +0.006 |
Twe | +0.006 |
Twe | +0.006 |
Nem | +0.006 |
le | +0.006 |
Neg logit contributions | |
outage | -0.007 |
hole | -0.007 |
ouncing | -0.007 |
ma | -0.006 |
lessly | -0.006 |
Token | were |
Token ID | 547 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Nem | +0.011 |
Twe | +0.011 |
le | +0.010 |
Neg logit contributions | |
outage | -0.014 |
hole | -0.014 |
ouncing | -0.014 |
ying | -0.013 |
lessly | -0.013 |
Token | very |
Token ID | 845 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
ying | +0.009 |
hole | +0.009 |
Today | +0.008 |
Neg logit contributions | |
Twe | -0.011 |
ot | -0.010 |
le | -0.010 |
Nem | -0.009 |
Twe | -0.009 |
Token | pocket |
Token ID | 10000 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
outage | +0.023 |
hole | +0.022 |
ouncing | +0.021 |
ying | +0.020 |
ma | +0.020 |
Neg logit contributions | |
Twe | -0.041 |
ot | -0.039 |
Twe | -0.038 |
Nem | -0.038 |
le | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
outage | +0.015 |
ouncing | +0.014 |
hole | +0.014 |
ying | +0.014 |
ma | +0.013 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.012 |
Nem | -0.012 |
le | -0.012 |
Twe | -0.011 |
Token | broke |
Token ID | 6265 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
Twe | +0.000 |
Twe | +0.000 |
ot | +0.000 |
le | +0.000 |
Nem | +0.000 |
Neg logit contributions | |
outage | -0.000 |
hole | -0.000 |
ma | -0.000 |
ouncing | -0.000 |
click | -0.000 |
Token | into |
Token ID | 656 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
hole | +0.005 |
outage | +0.005 |
ying | +0.005 |
rum | +0.005 |
ouncing | +0.004 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.005 |
Twe | -0.005 |
le | -0.005 |
jew | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.003 |
hole | -0.003 |
rum | -0.003 |
ouncing | -0.003 |
lessly | -0.003 |
Token | million |
Token ID | 1510 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
ouncing | +0.012 |
ying | +0.012 |
outage | +0.011 |
ows | +0.011 |
hole | +0.011 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.013 |
le | -0.013 |
jew | -0.013 |
Nem | -0.012 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
hole | +0.108 |
outage | +0.104 |
rum | +0.099 |
ying | +0.096 |
lessly | +0.095 |
Neg logit contributions | |
Twe | -0.165 |
Twe | -0.159 |
ot | -0.156 |
Nem | -0.151 |
le | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
outage | +0.049 |
ouncing | +0.049 |
hole | +0.047 |
ying | +0.047 |
ma | +0.047 |
Neg logit contributions | |
Twe | -0.028 |
ot | -0.027 |
Nem | -0.025 |
le | -0.025 |
Twe | -0.024 |
Token | Tim |
Token ID | 5045 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Today | +0.013 |
ouncing | +0.013 |
outage | +0.013 |
ma | +0.013 |
about | +0.013 |
Neg logit contributions | |
ot | -0.011 |
jew | -0.011 |
se | -0.011 |
le | -0.010 |
Twe | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
outage | +0.020 |
ying | +0.018 |
ouncing | +0.017 |
ma | +0.017 |
Today | +0.017 |
Neg logit contributions | |
Twe | -0.020 |
ot | -0.020 |
le | -0.019 |
Nem | -0.019 |
Twe | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
outage | +0.025 |
ouncing | +0.024 |
hole | +0.024 |
ying | +0.024 |
ma | +0.023 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.013 |
Nem | -0.012 |
le | -0.012 |
Twe | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
outage | +0.007 |
ouncing | +0.007 |
ying | +0.007 |
hole | +0.007 |
ma | +0.007 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.003 |
le | -0.003 |
Twe | -0.003 |
Token | It |
Token ID | 632 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Twe | +0.008 |
ot | +0.008 |
Nem | +0.007 |
le | +0.007 |
Twe | +0.007 |
Neg logit contributions | |
outage | -0.007 |
ouncing | -0.006 |
hole | -0.006 |
ying | -0.006 |
ma | -0.006 |
Token | broke |
Token ID | 6265 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ot | +0.039 |
Twe | +0.039 |
Nem | +0.038 |
Twe | +0.038 |
jew | +0.037 |
Neg logit contributions | |
outage | -0.046 |
hole | -0.044 |
lessly | -0.042 |
ouncing | -0.042 |
click | -0.041 |
Token | into |
Token ID | 656 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
outage | +0.004 |
hole | +0.004 |
ouncing | +0.004 |
ying | +0.004 |
lessly | +0.004 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Twe | -0.004 |
Nem | -0.004 |
le | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
Twe | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
hole | -0.004 |
ying | -0.004 |
ma | -0.004 |
Token | million |
Token ID | 1510 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
ouncing | +0.021 |
ying | +0.021 |
ows | +0.019 |
outage | +0.018 |
ems | +0.018 |
Neg logit contributions | |
le | -0.022 |
Twe | -0.022 |
ot | -0.021 |
se | -0.021 |
jew | -0.020 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
outage | +0.123 |
hole | +0.121 |
ouncing | +0.115 |
ying | +0.115 |
rum | +0.113 |
Neg logit contributions | |
Twe | -0.144 |
ot | -0.139 |
Twe | -0.137 |
Nem | -0.134 |
le | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Deal | +0.070 |
ouncing | +0.070 |
ma | +0.068 |
outage | +0.068 |
Today | +0.068 |
Neg logit contributions | |
Twe | -0.026 |
ot | -0.025 |
le | -0.025 |
se | -0.023 |
Nem | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Nem | +0.003 |
Twe | +0.003 |
le | +0.003 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
Twe | +0.000 |
le | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ying | -0.000 |
ma | -0.000 |
Token | Tim |
Token ID | 14967 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
le | +0.000 |
jew | +0.000 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
hole | -0.001 |
ying | -0.001 |
rum | -0.001 |
Token | v |
Token ID | 410 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Nem | +0.001 |
Twe | +0.001 |
Twe | +0.001 |
ot | +0.001 |
Bub | +0.001 |
Neg logit contributions | |
outage | -0.001 |
ma | -0.001 |
hole | -0.001 |
click | -0.001 |
ouncing | -0.001 |
Token | ase |
Token ID | 589 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
Nem | +0.052 |
ot | +0.051 |
Twe | +0.051 |
Bub | +0.048 |
le | +0.046 |
Neg logit contributions | |
ouncing | -0.029 |
outage | -0.026 |
ying | -0.025 |
ows | -0.024 |
apping | -0.024 |
Token | shattered |
Token ID | 23273 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
outage | +0.010 |
ouncing | +0.010 |
hole | +0.010 |
ying | +0.010 |
ma | +0.010 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
Nem | -0.006 |
Twe | -0.006 |
le | -0.005 |
Token | into |
Token ID | 656 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
outage | +0.029 |
hole | +0.029 |
ouncing | +0.028 |
ying | +0.028 |
lessly | +0.027 |
Neg logit contributions | |
Twe | -0.034 |
ot | -0.033 |
Twe | -0.032 |
Nem | -0.032 |
le | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.011 |
Nem | +0.011 |
Twe | +0.010 |
le | +0.010 |
Neg logit contributions | |
outage | -0.012 |
hole | -0.012 |
ouncing | -0.012 |
ma | -0.011 |
ying | -0.011 |
Token | million |
Token ID | 1510 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
ouncing | +0.011 |
ying | +0.011 |
outage | +0.010 |
ows | +0.009 |
hole | +0.009 |
Neg logit contributions | |
le | -0.014 |
ot | -0.014 |
Twe | -0.014 |
se | -0.013 |
jew | -0.013 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
hole | +0.112 |
outage | +0.110 |
lessly | +0.101 |
instant | +0.099 |
rum | +0.098 |
Neg logit contributions | |
Twe | -0.151 |
Twe | -0.144 |
ot | -0.144 |
Nem | -0.142 |
le | -0.130 |
Token | and |
Token ID | 290 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
Deal | +0.048 |
ouncing | +0.048 |
outage | +0.047 |
ma | +0.046 |
Today | +0.046 |
Neg logit contributions | |
Twe | -0.037 |
ot | -0.036 |
le | -0.036 |
se | -0.034 |
Nem | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
ot | +0.004 |
Twe | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.005 |
ma | -0.004 |
hole | -0.004 |
ouncing | -0.004 |
lessly | -0.004 |
Token | elderly |
Token ID | 13830 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Twe | +0.021 |
Nem | +0.021 |
Twe | +0.020 |
ot | +0.020 |
Bub | +0.018 |
Neg logit contributions | |
ma | -0.022 |
hole | -0.021 |
outage | -0.021 |
click | -0.021 |
ouncing | -0.020 |
Token | lady |
Token ID | 10846 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
Nem | +0.070 |
ot | +0.068 |
Twe | +0.068 |
Twe | +0.067 |
Bub | +0.067 |
Neg logit contributions | |
ma | -0.042 |
ouncing | -0.040 |
outage | -0.039 |
ying | -0.037 |
about | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
outage | +0.029 |
ouncing | +0.028 |
ying | +0.027 |
ma | +0.027 |
rum | +0.027 |
Neg logit contributions | |
Twe | -0.032 |
ot | -0.031 |
le | -0.030 |
Nem | -0.028 |
Twe | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Twe | +0.005 |
Nem | +0.005 |
le | +0.005 |
Neg logit contributions | |
outage | -0.006 |
ouncing | -0.006 |
hole | -0.006 |
ma | -0.006 |
ying | -0.006 |
Token | broke |
Token ID | 6265 |
Feature activation | -2.77e-03 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
jew | +0.004 |
Neg logit contributions | |
outage | -0.003 |
hole | -0.003 |
ouncing | -0.003 |
lessly | -0.003 |
ows | -0.003 |
Token | into |
Token ID | 656 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
ot | +0.000 |
Twe | +0.000 |
Twe | +0.000 |
Nem | +0.000 |
le | +0.000 |
Neg logit contributions | |
hole | -0.000 |
outage | -0.000 |
ouncing | -0.000 |
ying | -0.000 |
lessly | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.009 |
Nem | +0.008 |
Twe | +0.008 |
le | +0.008 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.009 |
hole | -0.008 |
ying | -0.008 |
ma | -0.008 |
Token | million |
Token ID | 1510 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
ying | +0.014 |
ouncing | +0.014 |
ows | +0.012 |
outage | +0.012 |
ems | +0.012 |
Neg logit contributions | |
Twe | -0.014 |
ot | -0.014 |
le | -0.014 |
se | -0.014 |
jew | -0.013 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
hole | +0.102 |
outage | +0.101 |
rum | +0.094 |
lessly | +0.091 |
ying | +0.089 |
Neg logit contributions | |
Twe | -0.158 |
Twe | -0.153 |
ot | -0.150 |
Nem | -0.147 |
le | -0.140 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
ouncing | +0.053 |
outage | +0.052 |
ma | +0.051 |
Deal | +0.051 |
Today | +0.051 |
Neg logit contributions | |
Twe | -0.021 |
ot | -0.021 |
le | -0.019 |
Nem | -0.018 |
se | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
hole | +0.004 |
ying | +0.003 |
rum | +0.003 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.002 |
le | -0.002 |
Twe | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
outage | +0.002 |
hole | +0.002 |
ouncing | +0.002 |
ying | +0.002 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.002 |
Twe | -0.002 |
Nem | -0.002 |
ot | -0.002 |
le | -0.002 |
Token | L |
Token ID | 43 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
outage | +0.004 |
hole | +0.004 |
ouncing | +0.004 |
ying | +0.004 |
ows | +0.004 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.001 |
Twe | -0.001 |
le | -0.001 |
Nem | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
Twe | +0.000 |
le | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ying | -0.000 |
ma | -0.000 |
Token | ornament |
Token ID | 45618 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
outage | +0.007 |
ouncing | +0.007 |
ying | +0.006 |
hole | +0.006 |
ows | +0.006 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
le | -0.005 |
Nem | -0.005 |
Twe | -0.005 |
Token | broke |
Token ID | 6265 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
outage | +0.018 |
hole | +0.018 |
ouncing | +0.017 |
ying | +0.017 |
lessly | +0.016 |
Neg logit contributions | |
Twe | -0.015 |
ot | -0.015 |
Nem | -0.015 |
Twe | -0.015 |
jew | -0.014 |
Token | into |
Token ID | 656 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
outage | +0.008 |
ouncing | +0.008 |
hole | +0.008 |
ying | +0.008 |
ma | +0.007 |
Neg logit contributions | |
Twe | -0.010 |
ot | -0.010 |
Nem | -0.009 |
Twe | -0.009 |
le | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Nem | +0.002 |
Twe | +0.002 |
le | +0.002 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
hole | -0.002 |
ying | -0.002 |
ma | -0.002 |
Token | million |
Token ID | 1510 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
ouncing | +0.025 |
ying | +0.024 |
ows | +0.022 |
ems | +0.022 |
outage | +0.022 |
Neg logit contributions | |
Twe | -0.025 |
le | -0.025 |
ot | -0.025 |
se | -0.024 |
jew | -0.024 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
outage | +0.116 |
hole | +0.115 |
ouncing | +0.109 |
ying | +0.108 |
rum | +0.107 |
Neg logit contributions | |
Twe | -0.140 |
ot | -0.137 |
Twe | -0.132 |
Nem | -0.131 |
le | -0.127 |
Token | and |
Token ID | 290 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
Deal | +0.055 |
ouncing | +0.055 |
outage | +0.054 |
ma | +0.053 |
Today | +0.053 |
Neg logit contributions | |
Twe | -0.039 |
ot | -0.038 |
le | -0.038 |
se | -0.036 |
Nem | -0.035 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Twe | +0.002 |
Nem | +0.002 |
jew | +0.002 |
Neg logit contributions | |
outage | -0.002 |
hole | -0.002 |
ouncing | -0.002 |
ma | -0.002 |
lessly | -0.002 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.005 |
Nem | +0.005 |
le | +0.005 |
Twe | +0.005 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.008 |
ma | -0.008 |
Token | really |
Token ID | 1107 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.010 |
Twe | +0.010 |
Nem | +0.009 |
le | +0.009 |
Neg logit contributions | |
outage | -0.005 |
lessly | -0.004 |
about | -0.004 |
hole | -0.004 |
ying | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ouncing | +0.023 |
Deal | +0.023 |
outage | +0.022 |
ma | +0.022 |
ying | +0.022 |
Neg logit contributions | |
Twe | -0.018 |
le | -0.018 |
ot | -0.017 |
se | -0.017 |
pl | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ot | +0.009 |
Twe | +0.009 |
Twe | +0.008 |
Nem | +0.008 |
le | +0.008 |
Neg logit contributions | |
outage | -0.007 |
hole | -0.007 |
ma | -0.007 |
click | -0.007 |
ouncing | -0.007 |
Token | broke |
Token ID | 6265 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
ot | +0.010 |
Twe | +0.010 |
Twe | +0.010 |
Nem | +0.010 |
jew | +0.010 |
Neg logit contributions | |
outage | -0.009 |
hole | -0.008 |
ouncing | -0.008 |
lessly | -0.008 |
ows | -0.008 |
Token | into |
Token ID | 656 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ot | +0.003 |
Twe | +0.003 |
Twe | +0.003 |
Nem | +0.003 |
le | +0.003 |
Neg logit contributions | |
hole | -0.002 |
outage | -0.002 |
lessly | -0.002 |
ouncing | -0.002 |
ying | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Nem | +0.011 |
Twe | +0.011 |
le | +0.011 |
Neg logit contributions | |
outage | -0.011 |
hole | -0.010 |
ouncing | -0.010 |
ying | -0.010 |
ma | -0.010 |
Token | million |
Token ID | 1510 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ouncing | +0.009 |
ying | +0.008 |
outage | +0.008 |
ows | +0.007 |
hole | +0.007 |
Neg logit contributions | |
Twe | -0.012 |
ot | -0.012 |
le | -0.012 |
jew | -0.012 |
se | -0.012 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
outage | +0.101 |
hole | +0.100 |
rum | +0.093 |
lessly | +0.091 |
instant | +0.090 |
Neg logit contributions | |
Twe | -0.156 |
Twe | -0.152 |
ot | -0.149 |
Nem | -0.146 |
le | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
ouncing | +0.050 |
outage | +0.049 |
ma | +0.048 |
Deal | +0.048 |
Today | +0.048 |
Neg logit contributions | |
Twe | -0.020 |
ot | -0.020 |
le | -0.019 |
Nem | -0.018 |
se | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.002 |
ying | +0.002 |
ma | +0.002 |
Neg logit contributions | |
ot | -0.003 |
Twe | -0.003 |
Nem | -0.003 |
le | -0.003 |
Twe | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
Twe | +0.000 |
le | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ying | -0.000 |
ma | -0.000 |
Token | L |
Token ID | 43 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
outage | +0.002 |
ouncing | +0.002 |
hole | +0.002 |
ying | +0.002 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Nem | -0.001 |
le | -0.001 |
Twe | -0.001 |
Token | tooth |
Token ID | 16162 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
le | +0.003 |
jew | +0.003 |
Nem | +0.003 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
ying | -0.004 |
hole | -0.004 |
rum | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
Twe | +0.020 |
ot | +0.020 |
le | +0.019 |
se | +0.018 |
Nem | +0.018 |
Neg logit contributions | |
outage | -0.031 |
ouncing | -0.031 |
ying | -0.030 |
Today | -0.030 |
hole | -0.030 |
Token | broken |
Token ID | 5445 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
outage | +0.005 |
hole | +0.005 |
ma | +0.005 |
about | +0.005 |
lessly | +0.005 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
Twe | -0.005 |
Nem | -0.004 |
le | -0.004 |
Token | into |
Token ID | 656 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
outage | +0.019 |
ouncing | +0.018 |
hole | +0.018 |
ying | +0.017 |
ma | +0.017 |
Neg logit contributions | |
Twe | -0.017 |
ot | -0.017 |
Nem | -0.016 |
Twe | -0.016 |
le | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.013 |
Twe | +0.012 |
Nem | +0.012 |
le | +0.012 |
Neg logit contributions | |
outage | -0.015 |
hole | -0.015 |
ouncing | -0.014 |
ying | -0.014 |
rum | -0.014 |
Token | million |
Token ID | 1510 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ying | +0.010 |
ouncing | +0.010 |
ows | +0.009 |
outage | +0.009 |
rum | +0.009 |
Neg logit contributions | |
Twe | -0.008 |
ot | -0.008 |
le | -0.008 |
se | -0.007 |
jew | -0.007 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
hole | +0.108 |
outage | +0.108 |
rum | +0.099 |
lessly | +0.097 |
ouncing | +0.097 |
Neg logit contributions | |
Twe | -0.141 |
ot | -0.135 |
Twe | -0.135 |
Nem | -0.132 |
le | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
ouncing | +0.046 |
Deal | +0.045 |
outage | +0.045 |
ma | +0.045 |
Today | +0.044 |
Neg logit contributions | |
ot | -0.029 |
Twe | -0.028 |
le | -0.027 |
Nem | -0.026 |
se | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
le | +0.011 |
Nem | +0.010 |
se | +0.010 |
Neg logit contributions | |
outage | -0.010 |
ying | -0.010 |
ouncing | -0.010 |
rum | -0.009 |
Today | -0.009 |
Token | each |
Token ID | 1123 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
outage | +0.021 |
ouncing | +0.021 |
hole | +0.020 |
ying | +0.020 |
rum | +0.019 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.015 |
Nem | -0.014 |
le | -0.014 |
Twe | -0.014 |
Token | piece |
Token ID | 3704 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
Twe | +0.025 |
ot | +0.024 |
le | +0.023 |
Nem | +0.023 |
Twe | +0.022 |
Neg logit contributions | |
ouncing | -0.033 |
outage | -0.032 |
ying | -0.031 |
hole | -0.031 |
ma | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
ouncing | +0.020 |
outage | +0.020 |
Deal | +0.020 |
ma | +0.019 |
ying | +0.019 |
Neg logit contributions | |
Twe | -0.016 |
le | -0.015 |
ot | -0.015 |
se | -0.014 |
Twe | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ot | +0.007 |
Twe | +0.007 |
Twe | +0.006 |
jew | +0.006 |
Nem | +0.006 |
Neg logit contributions | |
outage | -0.006 |
ma | -0.006 |
click | -0.006 |
ouncing | -0.005 |
lessly | -0.005 |
Token | shattered |
Token ID | 23273 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ot | +0.007 |
Nem | +0.007 |
Twe | +0.007 |
Twe | +0.007 |
jew | +0.007 |
Neg logit contributions | |
hole | -0.005 |
outage | -0.005 |
ouncing | -0.005 |
lessly | -0.005 |
click | -0.005 |
Token | into |
Token ID | 656 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
hole | +0.013 |
outage | +0.012 |
lessly | +0.012 |
ouncing | +0.012 |
ying | +0.011 |
Neg logit contributions | |
Twe | -0.018 |
Twe | -0.017 |
ot | -0.017 |
Nem | -0.017 |
jew | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Twe | +0.024 |
ot | +0.023 |
Twe | +0.022 |
Nem | +0.022 |
le | +0.021 |
Neg logit contributions | |
outage | -0.026 |
hole | -0.025 |
ouncing | -0.024 |
ma | -0.024 |
rum | -0.024 |
Token | million |
Token ID | 1510 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ouncing | +0.006 |
ying | +0.006 |
outage | +0.005 |
ows | +0.005 |
ems | +0.005 |
Neg logit contributions | |
Twe | -0.008 |
le | -0.008 |
ot | -0.008 |
se | -0.008 |
jew | -0.008 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
hole | +0.094 |
outage | +0.094 |
rum | +0.087 |
instant | +0.084 |
lessly | +0.082 |
Neg logit contributions | |
Twe | -0.148 |
Twe | -0.146 |
Nem | -0.144 |
ot | -0.143 |
Bub | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
ouncing | +0.043 |
outage | +0.042 |
ma | +0.042 |
Deal | +0.042 |
Today | +0.041 |
Neg logit contributions | |
Twe | -0.019 |
ot | -0.019 |
le | -0.018 |
Nem | -0.017 |
se | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
le | +0.000 |
Twe | +0.000 |
Neg logit contributions | |
outage | -0.001 |
hole | -0.001 |
ouncing | -0.001 |
ying | -0.000 |
rum | -0.000 |
Token | 's |
Token ID | 338 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
outage | +0.016 |
ying | +0.015 |
ouncing | +0.015 |
hole | +0.015 |
Today | +0.014 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
le | -0.007 |
Twe | -0.006 |
Nem | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ouncing | +0.049 |
outage | +0.049 |
hole | +0.048 |
ma | +0.046 |
ows | +0.046 |
Neg logit contributions | |
Nem | -0.061 |
Twe | -0.060 |
Twe | -0.057 |
ot | -0.057 |
jew | -0.055 |
Token | he |
Token ID | 339 |
Feature activation | -7.49e-03 |
Pos logit contributions | |
outage | +0.007 |
hole | +0.006 |
ying | +0.006 |
ouncing | +0.006 |
Today | +0.006 |
Neg logit contributions | |
Twe | -0.009 |
Twe | -0.009 |
ot | -0.009 |
le | -0.009 |
jew | -0.009 |
Token | found |
Token ID | 1043 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Twe | +0.000 |
Nem | +0.000 |
jew | +0.000 |
Neg logit contributions | |
hole | -0.000 |
ouncing | -0.000 |
ma | -0.000 |
outage | -0.000 |
about | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Twe | +0.012 |
Twe | +0.011 |
ot | +0.010 |
arom | +0.010 |
Nem | +0.010 |
Neg logit contributions | |
about | -0.011 |
hole | -0.011 |
lessly | -0.010 |
ying | -0.010 |
outage | -0.010 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
ouncing | +0.007 |
outage | +0.006 |
ying | +0.006 |
hole | +0.006 |
rum | +0.006 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
le | -0.004 |
Nem | -0.004 |
Twe | -0.004 |
Token | qu |
Token ID | 627 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
outage | +0.024 |
ouncing | +0.023 |
hole | +0.023 |
ying | +0.022 |
ma | +0.021 |
Neg logit contributions | |
Twe | -0.024 |
ot | -0.023 |
Nem | -0.022 |
Twe | -0.022 |
le | -0.022 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.009 |
Nem | +0.009 |
le | +0.009 |
Twe | +0.008 |
Neg logit contributions | |
ouncing | -0.005 |
outage | -0.005 |
hole | -0.004 |
ying | -0.004 |
lessly | -0.004 |
Token | lling |
Token ID | 2680 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ouncing | +0.119 |
ma | +0.118 |
Deal | +0.118 |
outage | +0.118 |
Today | +0.117 |
Neg logit contributions | |
ot | -0.124 |
Twe | -0.118 |
Nem | -0.112 |
le | -0.112 |
se | -0.111 |
Token | with |
Token ID | 351 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
outage | +0.036 |
ouncing | +0.035 |
hole | +0.034 |
ying | +0.034 |
ma | +0.033 |
Neg logit contributions | |
Twe | -0.034 |
ot | -0.034 |
Nem | -0.032 |
le | -0.032 |
Twe | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Twe | +0.038 |
Twe | +0.034 |
ot | +0.034 |
pre | +0.033 |
host | +0.031 |
Neg logit contributions | |
about | -0.030 |
click | -0.030 |
lessly | -0.029 |
grin | -0.029 |
instant | -0.029 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.012 |
le | +0.011 |
Nem | +0.011 |
Twe | +0.010 |
Neg logit contributions | |
ying | -0.016 |
ouncing | -0.015 |
outage | -0.015 |
hole | -0.015 |
rum | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
outage | +0.014 |
ouncing | +0.014 |
hole | +0.014 |
ying | +0.013 |
rum | +0.013 |
Neg logit contributions | |
Twe | -0.012 |
ot | -0.011 |
Nem | -0.011 |
Twe | -0.011 |
jew | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ot | +0.016 |
Twe | +0.015 |
le | +0.015 |
se | +0.015 |
Nem | +0.015 |
Neg logit contributions | |
ouncing | -0.016 |
outage | -0.015 |
Today | -0.014 |
ma | -0.014 |
rum | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ot | +0.008 |
Twe | +0.007 |
Twe | +0.007 |
Nem | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.007 |
hole | -0.007 |
ouncing | -0.007 |
ma | -0.007 |
ying | -0.007 |
Token | broke |
Token ID | 6265 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Twe | +0.006 |
Twe | +0.006 |
ot | +0.006 |
Nem | +0.006 |
jew | +0.006 |
Neg logit contributions | |
outage | -0.005 |
hole | -0.005 |
ouncing | -0.005 |
lessly | -0.004 |
ying | -0.004 |
Token | into |
Token ID | 656 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
ot | +0.004 |
Twe | +0.004 |
Twe | +0.004 |
Nem | +0.003 |
le | +0.003 |
Neg logit contributions | |
hole | -0.003 |
outage | -0.003 |
lessly | -0.003 |
ouncing | -0.003 |
ying | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Nem | +0.011 |
Twe | +0.011 |
le | +0.010 |
Neg logit contributions | |
outage | -0.012 |
ouncing | -0.011 |
hole | -0.011 |
ying | -0.011 |
ma | -0.011 |
Token | million |
Token ID | 1510 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
ouncing | +0.011 |
ying | +0.011 |
outage | +0.010 |
hole | +0.010 |
ows | +0.010 |
Neg logit contributions | |
ot | -0.014 |
Twe | -0.013 |
le | -0.013 |
se | -0.013 |
Nem | -0.013 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
outage | +0.097 |
hole | +0.094 |
rum | +0.091 |
lessly | +0.090 |
ying | +0.090 |
Neg logit contributions | |
Twe | -0.147 |
Twe | -0.144 |
ot | -0.136 |
Nem | -0.130 |
le | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ouncing | +0.046 |
outage | +0.045 |
ma | +0.044 |
Deal | +0.044 |
Today | +0.044 |
Neg logit contributions | |
Twe | -0.020 |
ot | -0.020 |
le | -0.019 |
Nem | -0.018 |
se | -0.017 |
Token | Her |
Token ID | 2332 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.003 |
Neg logit contributions | |
ot | -0.005 |
Twe | -0.005 |
Nem | -0.004 |
Twe | -0.004 |
le | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.25e-03 |
Pos logit contributions | |
outage | +0.017 |
ouncing | +0.016 |
ma | +0.016 |
hole | +0.015 |
ying | +0.015 |
Neg logit contributions | |
Twe | -0.020 |
Twe | -0.020 |
ot | -0.018 |
Nem | -0.018 |
Bub | -0.017 |
Token | my |
Token ID | 1820 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
outage | +0.000 |
Today | +0.000 |
ying | +0.000 |
ma | +0.000 |
ouncing | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
ot | -0.000 |
le | -0.000 |
se | -0.000 |
Twe | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
outage | +0.032 |
hole | +0.032 |
ying | +0.030 |
ma | +0.030 |
ouncing | +0.029 |
Neg logit contributions | |
ot | -0.038 |
Twe | -0.037 |
Twe | -0.037 |
Nem | -0.035 |
le | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
outage | +0.006 |
ouncing | +0.006 |
hole | +0.005 |
ying | +0.005 |
ma | +0.005 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
Nem | -0.004 |
le | -0.004 |
Twe | -0.004 |
Token | broke |
Token ID | 6265 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
outage | +0.005 |
hole | +0.005 |
ouncing | +0.005 |
ows | +0.005 |
lessly | +0.005 |
Neg logit contributions | |
ot | -0.006 |
Twe | -0.005 |
Nem | -0.005 |
Twe | -0.005 |
jew | -0.005 |
Token | into |
Token ID | 656 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ot | +0.002 |
Twe | +0.002 |
Twe | +0.002 |
Nem | +0.002 |
le | +0.002 |
Neg logit contributions | |
hole | -0.002 |
outage | -0.002 |
ouncing | -0.002 |
lessly | -0.002 |
ying | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.012 |
Nem | +0.012 |
Twe | +0.012 |
le | +0.011 |
Neg logit contributions | |
outage | -0.012 |
hole | -0.012 |
ouncing | -0.012 |
ying | -0.011 |
ma | -0.011 |
Token | million |
Token ID | 1510 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
ouncing | +0.013 |
ying | +0.012 |
ows | +0.011 |
ems | +0.011 |
outage | +0.010 |
Neg logit contributions | |
Twe | -0.017 |
ot | -0.017 |
le | -0.017 |
se | -0.016 |
jew | -0.016 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
outage | +0.109 |
hole | +0.105 |
ouncing | +0.099 |
ying | +0.099 |
rum | +0.098 |
Neg logit contributions | |
Twe | -0.135 |
ot | -0.131 |
Twe | -0.129 |
Nem | -0.127 |
le | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
ouncing | +0.048 |
outage | +0.047 |
ma | +0.046 |
Today | +0.046 |
Deal | +0.045 |
Neg logit contributions | |
Twe | -0.022 |
ot | -0.021 |
le | -0.020 |
Nem | -0.019 |
se | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
hole | +0.004 |
ying | +0.004 |
rum | +0.004 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
Twe | -0.004 |
le | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
outage | +0.019 |
ying | +0.019 |
ouncing | +0.019 |
Today | +0.018 |
hole | +0.018 |
Neg logit contributions | |
Twe | -0.008 |
ot | -0.007 |
le | -0.007 |
Nem | -0.006 |
Twe | -0.006 |
Token | very |
Token ID | 845 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
ouncing | +0.026 |
ems | +0.025 |
outage | +0.025 |
ying | +0.024 |
Today | +0.024 |
Neg logit contributions | |
Twe | -0.023 |
ot | -0.021 |
le | -0.021 |
Nem | -0.020 |
se | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
hole | +0.008 |
ying | +0.008 |
ma | +0.008 |
Neg logit contributions | |
Twe | -0.008 |
ot | -0.008 |
Nem | -0.008 |
le | -0.007 |
Twe | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Nem | +0.002 |
Twe | +0.002 |
le | +0.002 |
Neg logit contributions | |
outage | -0.003 |
ouncing | -0.003 |
hole | -0.003 |
ying | -0.003 |
ma | -0.003 |
Token | broke |
Token ID | 6265 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
Twe | +0.015 |
Twe | +0.015 |
ot | +0.015 |
Nem | +0.014 |
jew | +0.014 |
Neg logit contributions | |
outage | -0.015 |
hole | -0.015 |
ouncing | -0.015 |
about | -0.014 |
ows | -0.014 |
Token | into |
Token ID | 656 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
ot | +0.000 |
Twe | +0.000 |
Twe | +0.000 |
Nem | +0.000 |
le | +0.000 |
Neg logit contributions | |
hole | -0.000 |
outage | -0.000 |
lessly | -0.000 |
rum | -0.000 |
ouncing | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.010 |
Nem | +0.009 |
Twe | +0.009 |
le | +0.009 |
Neg logit contributions | |
outage | -0.009 |
hole | -0.009 |
ouncing | -0.008 |
rum | -0.008 |
ying | -0.008 |
Token | million |
Token ID | 1510 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ouncing | +0.009 |
ying | +0.009 |
outage | +0.008 |
ows | +0.008 |
hole | +0.008 |
Neg logit contributions | |
Twe | -0.010 |
ot | -0.010 |
le | -0.010 |
jew | -0.010 |
Twe | -0.010 |
Token | pieces |
Token ID | 5207 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
hole | +0.094 |
outage | +0.088 |
instant | +0.084 |
rum | +0.084 |
lessly | +0.081 |
Neg logit contributions | |
Twe | -0.145 |
Twe | -0.140 |
ot | -0.139 |
Nem | -0.136 |
Bub | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
outage | +0.041 |
ouncing | +0.041 |
ying | +0.040 |
hole | +0.039 |
ma | +0.039 |
Neg logit contributions | |
Twe | -0.022 |
ot | -0.022 |
Nem | -0.020 |
le | -0.020 |
Twe | -0.019 |
Token | His |
Token ID | 2399 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ouncing | +0.006 |
Today | +0.005 |
outage | +0.005 |
ma | +0.005 |
hole | +0.005 |
Neg logit contributions | |
ot | -0.007 |
Twe | -0.006 |
le | -0.006 |
jew | -0.006 |
Twe | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
ouncing | +0.005 |
outage | +0.005 |
ma | +0.005 |
hole | +0.005 |
grin | +0.005 |
Neg logit contributions | |
Twe | -0.005 |
Twe | -0.005 |
ot | -0.005 |
Nem | -0.005 |
le | -0.005 |
Token | my |
Token ID | 1820 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
le | +0.003 |
Twe | +0.003 |
se | +0.003 |
Neg logit contributions | |
outage | -0.002 |
ying | -0.002 |
Today | -0.002 |
ouncing | -0.002 |
ma | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.005 |
Nem | +0.005 |
le | +0.005 |
Twe | +0.005 |
Neg logit contributions | |
outage | -0.003 |
hole | -0.003 |
ying | -0.003 |
ouncing | -0.002 |
rum | -0.002 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Twe | +0.014 |
ot | +0.014 |
Twe | +0.013 |
Nem | +0.013 |
jew | +0.012 |
Neg logit contributions | |
ouncing | -0.014 |
hole | -0.014 |
outage | -0.014 |
ma | -0.014 |
ying | -0.013 |
Token | onto |
Token ID | 4291 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
hole | +0.005 |
onwards | +0.005 |
about | +0.005 |
ying | +0.005 |
click | +0.005 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
Twe | -0.005 |
Nem | -0.005 |
jew | -0.004 |
Token | its |
Token ID | 663 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
click | +0.012 |
hole | +0.011 |
about | +0.011 |
ma | +0.011 |
Today | +0.011 |
Neg logit contributions | |
ot | -0.017 |
Twe | -0.017 |
Nem | -0.016 |
jew | -0.015 |
mer | -0.015 |
Token | handle |
Token ID | 5412 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.012 |
Nem | +0.012 |
le | +0.012 |
Twe | +0.012 |
Neg logit contributions | |
outage | -0.012 |
ouncing | -0.012 |
hole | -0.011 |
ying | -0.011 |
ma | -0.011 |
Token | bars |
Token ID | 34046 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
outage | +0.037 |
Deal | +0.037 |
rum | +0.036 |
ouncing | +0.035 |
Promise | +0.035 |
Neg logit contributions | |
Twe | -0.034 |
le | -0.032 |
ot | -0.032 |
se | -0.030 |
Nem | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
outage | +0.121 |
Deal | +0.116 |
ouncing | +0.115 |
ying | +0.114 |
ma | +0.114 |
Neg logit contributions | |
Twe | -0.114 |
ot | -0.103 |
le | -0.101 |
Twe | -0.097 |
se | -0.095 |
Token | put |
Token ID | 1234 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Twe | +0.005 |
Nem | +0.005 |
le | +0.005 |
Neg logit contributions | |
outage | -0.008 |
hole | -0.008 |
ouncing | -0.008 |
ying | -0.007 |
ma | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ot | +0.002 |
Twe | +0.002 |
Twe | +0.002 |
Nem | +0.002 |
le | +0.002 |
Neg logit contributions | |
hole | -0.001 |
outage | -0.001 |
ouncing | -0.001 |
ying | -0.001 |
lessly | -0.001 |
Token | feet |
Token ID | 3625 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
le | +0.004 |
Twe | +0.003 |
Neg logit contributions | |
outage | -0.003 |
ouncing | -0.003 |
ying | -0.003 |
hole | -0.003 |
ma | -0.003 |
Token | onto |
Token ID | 4291 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
Twe | +0.022 |
ot | +0.021 |
Nem | +0.021 |
le | +0.021 |
Twe | +0.020 |
Neg logit contributions | |
outage | -0.012 |
ouncing | -0.012 |
ying | -0.011 |
hole | -0.011 |
ma | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ouncing | +0.044 |
outage | +0.043 |
ma | +0.042 |
ying | +0.042 |
Deal | +0.041 |
Neg logit contributions | |
Twe | -0.024 |
ot | -0.024 |
le | -0.023 |
Nem | -0.021 |
se | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Twe | +0.005 |
Nem | +0.005 |
le | +0.005 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token | broke |
Token ID | 6265 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ot | +0.001 |
Twe | +0.001 |
Twe | +0.001 |
Nem | +0.001 |
jew | +0.001 |
Neg logit contributions | |
hole | -0.001 |
outage | -0.001 |
lessly | -0.001 |
falls | -0.001 |
ouncing | -0.001 |
Token | into |
Token ID | 656 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
ot | +0.004 |
Twe | +0.004 |
Twe | +0.004 |
Nem | +0.003 |
jew | +0.003 |
Neg logit contributions | |
hole | -0.004 |
outage | -0.003 |
lessly | -0.003 |
rum | -0.003 |
ouncing | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Twe | +0.014 |
ot | +0.014 |
Twe | +0.014 |
Nem | +0.013 |
le | +0.013 |
Neg logit contributions | |
outage | -0.012 |
hole | -0.012 |
rum | -0.012 |
ouncing | -0.012 |
ma | -0.011 |
Token | million |
Token ID | 1510 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
ouncing | +0.011 |
ying | +0.010 |
ows | +0.009 |
outage | +0.009 |
ems | +0.009 |
Neg logit contributions | |
Twe | -0.014 |
le | -0.014 |
ot | -0.014 |
se | -0.014 |
jew | -0.013 |
Token | pieces |
Token ID | 5207 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
outage | +0.095 |
hole | +0.094 |
rum | +0.089 |
ying | +0.086 |
lessly | +0.085 |
Neg logit contributions | |
Twe | -0.139 |
Twe | -0.135 |
ot | -0.134 |
Nem | -0.130 |
le | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
ouncing | +0.040 |
outage | +0.039 |
ma | +0.038 |
Today | +0.038 |
ying | +0.038 |
Neg logit contributions | |
Twe | -0.017 |
ot | -0.017 |
le | -0.016 |
Nem | -0.015 |
Twe | -0.014 |
Token | Tim |
Token ID | 5045 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
ot | +0.001 |
Twe | +0.001 |
jew | +0.001 |
le | +0.001 |
Twe | +0.001 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
Today | -0.001 |
hole | -0.001 |
ma | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | +5.49e-01 |
Pos logit contributions | |
outage | +0.020 |
ma | +0.018 |
ying | +0.018 |
click | +0.018 |
onwards | +0.018 |
Neg logit contributions | |
Twe | -0.015 |
ot | -0.015 |
le | -0.014 |
B | -0.014 |
Nem | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
outage | +0.025 |
ouncing | +0.024 |
ying | +0.024 |
hole | +0.024 |
Today | +0.023 |
Neg logit contributions | |
Twe | -0.011 |
ot | -0.010 |
le | -0.010 |
Nem | -0.009 |
Twe | -0.009 |
Token | hive |
Token ID | 35881 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
outage | +0.015 |
ouncing | +0.015 |
hole | +0.014 |
ying | +0.014 |
ma | +0.013 |
Neg logit contributions | |
Twe | -0.020 |
ot | -0.019 |
Nem | -0.018 |
le | -0.018 |
Twe | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
outage | +0.052 |
ouncing | +0.052 |
ying | +0.050 |
hole | +0.050 |
rum | +0.049 |
Neg logit contributions | |
Twe | -0.022 |
ot | -0.021 |
le | -0.020 |
Nem | -0.019 |
jew | -0.018 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
le | +0.004 |
Twe | +0.004 |
Neg logit contributions | |
outage | -0.005 |
hole | -0.004 |
ouncing | -0.004 |
ying | -0.004 |
rum | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
ying | +0.004 |
hole | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
Twe | -0.005 |
Nem | -0.005 |
le | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
outage | +0.003 |
ying | +0.003 |
ouncing | +0.003 |
ma | +0.003 |
hole | +0.003 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Twe | -0.004 |
le | -0.003 |
Nem | -0.003 |
Token | swarm |
Token ID | 30077 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.005 |
le | +0.005 |
Nem | +0.005 |
Twe | +0.005 |
Neg logit contributions | |
outage | -0.007 |
ouncing | -0.007 |
hole | -0.007 |
ying | -0.007 |
rum | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
ouncing | +0.114 |
outage | +0.113 |
hole | +0.106 |
ma | +0.104 |
rum | +0.103 |
Neg logit contributions | |
ot | -0.122 |
Twe | -0.116 |
le | -0.115 |
Nem | -0.110 |
se | -0.109 |
Token | bees |
Token ID | 17002 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Twe | +0.028 |
ot | +0.026 |
Nem | +0.026 |
Twe | +0.025 |
le | +0.025 |
Neg logit contributions | |
outage | -0.024 |
ouncing | -0.023 |
ying | -0.022 |
hole | -0.022 |
ma | -0.021 |
Token | flew |
Token ID | 13112 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
outage | +0.037 |
ouncing | +0.036 |
hole | +0.035 |
ying | +0.035 |
ma | +0.034 |
Neg logit contributions | |
Twe | -0.027 |
ot | -0.026 |
Nem | -0.024 |
le | -0.024 |
Twe | -0.024 |
Token | out |
Token ID | 503 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
outage | +0.019 |
ouncing | +0.019 |
hole | +0.018 |
ying | +0.018 |
lessly | +0.017 |
Neg logit contributions | |
Twe | -0.031 |
ot | -0.030 |
Nem | -0.030 |
Twe | -0.030 |
jew | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.006 |
le | +0.005 |
Nem | +0.005 |
se | +0.005 |
Neg logit contributions | |
ouncing | -0.005 |
outage | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
outage | +0.026 |
ouncing | +0.026 |
ying | +0.025 |
hole | +0.025 |
ma | +0.025 |
Neg logit contributions | |
Twe | -0.015 |
ot | -0.014 |
le | -0.013 |
Nem | -0.013 |
Twe | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
Nem | +0.010 |
Twe | +0.010 |
ot | +0.010 |
le | +0.009 |
Bub | +0.009 |
Neg logit contributions | |
outage | -0.009 |
hole | -0.009 |
ouncing | -0.009 |
ying | -0.008 |
rum | -0.008 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Twe | +0.016 |
ot | +0.016 |
Twe | +0.014 |
Nem | +0.014 |
le | +0.014 |
Neg logit contributions | |
outage | -0.021 |
ouncing | -0.021 |
hole | -0.021 |
ying | -0.020 |
ma | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
outage | +0.010 |
hole | +0.009 |
ouncing | +0.009 |
ying | +0.009 |
ma | +0.009 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
Twe | -0.007 |
Nem | -0.007 |
le | -0.006 |
Token | handle |
Token ID | 5412 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
outage | +0.030 |
ouncing | +0.030 |
ying | +0.029 |
rum | +0.027 |
ows | +0.027 |
Neg logit contributions | |
Twe | -0.042 |
ot | -0.041 |
le | -0.040 |
Nem | -0.038 |
jew | -0.038 |
Token | bars |
Token ID | 34046 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
outage | +0.023 |
Deal | +0.023 |
ouncing | +0.022 |
rum | +0.022 |
ems | +0.022 |
Neg logit contributions | |
Twe | -0.026 |
ot | -0.025 |
le | -0.025 |
se | -0.023 |
Nem | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
outage | +0.114 |
ouncing | +0.109 |
ying | +0.107 |
Deal | +0.107 |
ma | +0.105 |
Neg logit contributions | |
Twe | -0.119 |
ot | -0.113 |
le | -0.111 |
Nem | -0.105 |
se | -0.104 |
Token | he |
Token ID | 339 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
Twe | +0.004 |
le | +0.003 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token | quickly |
Token ID | 2952 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.011 |
Twe | +0.010 |
Nem | +0.010 |
le | +0.010 |
Neg logit contributions | |
hole | -0.012 |
outage | -0.012 |
ouncing | -0.012 |
ying | -0.011 |
ma | -0.011 |
Token | pushed |
Token ID | 7121 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
Twe | +0.016 |
ot | +0.015 |
Twe | +0.015 |
Nem | +0.015 |
le | +0.014 |
Neg logit contributions | |
hole | -0.016 |
outage | -0.016 |
ouncing | -0.016 |
ma | -0.015 |
lessly | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Twe | -0.002 |
Token | walked |
Token ID | 6807 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
outage | +0.015 |
ouncing | +0.015 |
ying | +0.015 |
hole | +0.015 |
ma | +0.014 |
Neg logit contributions | |
Twe | -0.012 |
ot | -0.012 |
Nem | -0.011 |
le | -0.011 |
Twe | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Nem | +0.001 |
le | +0.001 |
Twe | +0.001 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
hole | -0.001 |
ying | -0.001 |
ma | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
Twe | +0.016 |
ot | +0.014 |
le | +0.014 |
Nem | +0.014 |
jew | +0.013 |
Neg logit contributions | |
ouncing | -0.034 |
ying | -0.032 |
outage | -0.030 |
itates | -0.030 |
ows | -0.030 |
Token | us |
Token ID | 514 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
outage | +0.034 |
hole | +0.033 |
ouncing | +0.032 |
ma | +0.032 |
ying | +0.032 |
Neg logit contributions | |
Twe | -0.025 |
ot | -0.024 |
Twe | -0.023 |
Nem | -0.023 |
le | -0.022 |
Token | qu |
Token ID | 627 |
Feature activation | -9.10e-02 |
Pos logit contributions | |
ouncing | +0.004 |
outage | +0.004 |
ying | +0.004 |
ma | +0.003 |
irk | +0.003 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Bub | -0.001 |
Token | arre |
Token ID | 9624 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Nem | +0.005 |
le | +0.005 |
Twe | +0.004 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
hole | -0.001 |
ying | -0.001 |
ma | -0.001 |
Token | ling |
Token ID | 1359 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
Today | +0.123 |
outage | +0.120 |
ma | +0.119 |
ouncing | +0.119 |
Deal | +0.118 |
Neg logit contributions | |
ot | -0.102 |
Twe | -0.093 |
Nem | -0.092 |
se | -0.091 |
le | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
outage | +0.030 |
ouncing | +0.029 |
hole | +0.028 |
ying | +0.028 |
ma | +0.027 |
Neg logit contributions | |
Twe | -0.025 |
ot | -0.024 |
Nem | -0.023 |
le | -0.023 |
Twe | -0.022 |
Token | heard |
Token ID | 2982 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Twe | +0.017 |
ot | +0.017 |
Nem | +0.016 |
le | +0.016 |
Twe | +0.015 |
Neg logit contributions | |
outage | -0.017 |
hole | -0.017 |
ouncing | -0.017 |
ying | -0.017 |
ows | -0.016 |
Token | us |
Token ID | 514 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
ying | +0.005 |
hole | +0.005 |
ma | +0.005 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Twe | -0.004 |
Nem | -0.004 |
le | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -5.87e-02 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Nem | +0.004 |
le | +0.004 |
Twe | +0.004 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.008 |
ma | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
outage | +0.063 |
ouncing | +0.062 |
rum | +0.060 |
ying | +0.059 |
Today | +0.058 |
Neg logit contributions | |
Twe | -0.055 |
ot | -0.051 |
le | -0.050 |
Nem | -0.049 |
Twe | -0.047 |
Token | it |
Token ID | 340 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Twe | +0.000 |
Nem | +0.000 |
le | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ying | -0.000 |
ma | -0.000 |
Token | shattered |
Token ID | 23273 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
ot | +0.001 |
Twe | +0.001 |
Twe | +0.001 |
Nem | +0.001 |
jew | +0.001 |
Neg logit contributions | |
outage | -0.001 |
hole | -0.001 |
ouncing | -0.001 |
lessly | -0.001 |
ying | -0.001 |
Token | into |
Token ID | 656 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
outage | +0.014 |
hole | +0.014 |
ouncing | +0.013 |
ying | +0.013 |
lessly | +0.013 |
Neg logit contributions | |
Twe | -0.015 |
ot | -0.015 |
Twe | -0.015 |
Nem | -0.015 |
le | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Twe | +0.022 |
ot | +0.021 |
Twe | +0.021 |
Nem | +0.020 |
le | +0.019 |
Neg logit contributions | |
outage | -0.023 |
hole | -0.022 |
ma | -0.021 |
lessly | -0.021 |
ouncing | -0.021 |
Token | million |
Token ID | 1510 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ouncing | +0.006 |
ying | +0.006 |
outage | +0.006 |
hole | +0.006 |
ows | +0.005 |
Neg logit contributions | |
Twe | -0.010 |
ot | -0.010 |
le | -0.009 |
jew | -0.009 |
se | -0.009 |
Token | pieces |
Token ID | 5207 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
outage | +0.091 |
hole | +0.090 |
lessly | +0.084 |
instant | +0.082 |
rum | +0.081 |
Neg logit contributions | |
Twe | -0.137 |
Twe | -0.132 |
ot | -0.132 |
Nem | -0.127 |
le | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
ouncing | +0.035 |
outage | +0.034 |
Today | +0.033 |
ma | +0.033 |
Deal | +0.033 |
Neg logit contributions | |
Twe | -0.019 |
ot | -0.018 |
le | -0.017 |
Nem | -0.017 |
se | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
Twe | -0.003 |
le | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
outage | +0.014 |
ying | +0.014 |
ouncing | +0.014 |
Today | +0.014 |
hole | +0.014 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
le | -0.005 |
Nem | -0.005 |
se | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ouncing | +0.020 |
outage | +0.020 |
ying | +0.019 |
hole | +0.019 |
ems | +0.019 |
Neg logit contributions | |
Twe | -0.023 |
ot | -0.022 |
le | -0.021 |
Nem | -0.021 |
se | -0.020 |
Token | much |
Token ID | 881 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
outage | +0.021 |
hole | +0.020 |
ouncing | +0.020 |
ying | +0.020 |
ma | +0.019 |
Neg logit contributions | |
Twe | -0.025 |
ot | -0.024 |
le | -0.023 |
Nem | -0.023 |
Twe | -0.022 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
outage | +0.035 |
ouncing | +0.034 |
hole | +0.033 |
ying | +0.033 |
ma | +0.032 |
Neg logit contributions | |
Twe | -0.031 |
ot | -0.030 |
Nem | -0.028 |
Twe | -0.028 |
le | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Nem | +0.003 |
le | +0.003 |
Twe | +0.003 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
Twe | +0.008 |
Nem | +0.007 |
ot | +0.007 |
Twe | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.006 |
ying | -0.006 |
ouncing | -0.006 |
hole | -0.006 |
rum | -0.005 |
Token | Whe |
Token ID | 10842 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.012 |
Nem | +0.011 |
le | +0.011 |
Twe | +0.011 |
Neg logit contributions | |
outage | -0.013 |
ouncing | -0.012 |
hole | -0.012 |
ying | -0.012 |
ma | -0.012 |
Token | e |
Token ID | 68 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Nem | +0.011 |
le | +0.011 |
Twe | +0.010 |
Neg logit contributions | |
outage | -0.014 |
ouncing | -0.014 |
hole | -0.014 |
ying | -0.013 |
ma | -0.013 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
Twe | +0.170 |
ot | +0.169 |
Nem | +0.162 |
Twe | +0.160 |
le | +0.158 |
Neg logit contributions | |
ouncing | -0.113 |
outage | -0.112 |
hole | -0.108 |
ying | -0.104 |
ma | -0.103 |
Token | he |
Token ID | 339 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
Twe | +0.014 |
ot | +0.013 |
Nem | +0.013 |
le | +0.012 |
Twe | +0.012 |
Neg logit contributions | |
outage | -0.014 |
ouncing | -0.013 |
hole | -0.013 |
ying | -0.013 |
ma | -0.012 |
Token | shouted |
Token ID | 17293 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
outage | +0.011 |
ouncing | +0.011 |
hole | +0.011 |
ying | +0.011 |
ma | +0.010 |
Neg logit contributions | |
Twe | -0.011 |
ot | -0.011 |
Nem | -0.010 |
Twe | -0.010 |
le | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
ot | +0.008 |
Twe | +0.008 |
Twe | +0.008 |
le | +0.008 |
Nem | +0.008 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.009 |
about | -0.008 |
hole | -0.008 |
lessly | -0.008 |
Token | From |
Token ID | 3574 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
le | +0.000 |
Twe | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ying | -0.000 |
ma | -0.000 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
outage | +0.018 |
hole | +0.017 |
ouncing | +0.017 |
ying | +0.016 |
Today | +0.016 |
Neg logit contributions | |
Twe | -0.026 |
ot | -0.025 |
le | -0.024 |
Nem | -0.024 |
Twe | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
outage | +0.009 |
hole | +0.009 |
ouncing | +0.009 |
ying | +0.009 |
rum | +0.008 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
le | -0.007 |
Nem | -0.006 |
jew | -0.006 |
Token | shouts |
Token ID | 34757 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Twe | +0.015 |
ot | +0.014 |
le | +0.014 |
Nem | +0.014 |
Twe | +0.013 |
Neg logit contributions | |
outage | -0.013 |
hole | -0.012 |
ying | -0.012 |
ouncing | -0.012 |
rum | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Nem | +0.005 |
Twe | +0.005 |
le | +0.005 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token | Whe |
Token ID | 10842 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Twe | +0.034 |
ot | +0.034 |
Nem | +0.032 |
le | +0.031 |
Twe | +0.031 |
Neg logit contributions | |
outage | -0.036 |
ouncing | -0.035 |
hole | -0.035 |
ying | -0.033 |
ma | -0.033 |
Token | e |
Token ID | 68 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Nem | +0.003 |
le | +0.003 |
Twe | +0.003 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Twe | +0.163 |
ot | +0.160 |
Nem | +0.154 |
Twe | +0.152 |
le | +0.149 |
Neg logit contributions | |
ouncing | -0.119 |
outage | -0.118 |
hole | -0.113 |
ying | -0.111 |
ma | -0.110 |
Token | Uncle |
Token ID | 23169 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Twe | +0.012 |
le | +0.011 |
Nem | +0.010 |
Twe | +0.010 |
ot | +0.010 |
Neg logit contributions | |
outage | -0.019 |
ying | -0.018 |
rum | -0.017 |
hole | -0.017 |
ouncing | -0.016 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.009 |
le | +0.009 |
Nem | +0.009 |
Twe | +0.008 |
Neg logit contributions | |
outage | -0.007 |
hole | -0.007 |
ouncing | -0.006 |
ying | -0.006 |
lessly | -0.006 |
Token | laughs |
Token ID | 22051 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
outage | +0.013 |
hole | +0.012 |
ying | +0.012 |
ouncing | +0.012 |
lessly | +0.011 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.016 |
le | -0.016 |
Nem | -0.015 |
Bub | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
outage | +0.003 |
hole | +0.003 |
ouncing | +0.003 |
ying | +0.003 |
rum | +0.002 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
se | -0.002 |
Token | as |
Token ID | 355 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
outage | +0.016 |
ouncing | +0.016 |
ying | +0.016 |
hole | +0.016 |
lessly | +0.016 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.016 |
Twe | -0.015 |
le | -0.015 |
Nem | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Twe | +0.005 |
le | +0.005 |
Nem | +0.005 |
Neg logit contributions | |
ma | -0.006 |
ying | -0.006 |
outage | -0.006 |
lessly | -0.005 |
ouncing | -0.005 |
Token | best |
Token ID | 1266 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
Twe | +0.069 |
Twe | +0.063 |
Nem | +0.062 |
ot | +0.061 |
jew | +0.057 |
Neg logit contributions | |
ma | -0.048 |
outage | -0.047 |
ouncing | -0.045 |
click | -0.044 |
hole | -0.044 |
Token | joke |
Token ID | 9707 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
outage | +0.002 |
ouncing | +0.002 |
ying | +0.002 |
hole | +0.002 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.002 |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Token | - |
Token ID | 12 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Twe | +0.043 |
ot | +0.042 |
Nem | +0.040 |
Twe | +0.039 |
le | +0.039 |
Neg logit contributions | |
outage | -0.048 |
ouncing | -0.047 |
hole | -0.046 |
ying | -0.045 |
ma | -0.043 |
Token | te |
Token ID | 660 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
ot | +0.116 |
Twe | +0.114 |
Nem | +0.111 |
jew | +0.111 |
Twe | +0.106 |
Neg logit contributions | |
ouncing | -0.119 |
outage | -0.115 |
ying | -0.114 |
lessly | -0.111 |
rum | -0.105 |
Token | ller |
Token ID | 6051 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
jew | +0.172 |
ot | +0.168 |
Twe | +0.167 |
Twe | +0.164 |
Nem | +0.162 |
Neg logit contributions | |
ouncing | -0.110 |
outage | -0.097 |
ying | -0.093 |
rum | -0.091 |
hole | -0.089 |
Token | around |
Token ID | 1088 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Twe | +0.025 |
ot | +0.024 |
Twe | +0.023 |
Nem | +0.023 |
le | +0.022 |
Neg logit contributions | |
outage | -0.030 |
ouncing | -0.029 |
hole | -0.028 |
ying | -0.028 |
ma | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
outage | +0.020 |
ying | +0.020 |
hole | +0.020 |
ouncing | +0.019 |
lessly | +0.019 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.012 |
Twe | -0.012 |
le | -0.011 |
Nem | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.006 |
Nem | +0.006 |
Twe | +0.006 |
le | +0.006 |
Neg logit contributions | |
outage | -0.004 |
hole | -0.004 |
ouncing | -0.004 |
ying | -0.004 |
ows | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.008 |
hole | +0.008 |
ying | +0.008 |
ma | +0.008 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
Nem | -0.007 |
Twe | -0.007 |
le | -0.006 |
Token | then |
Token ID | 788 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Twe | +0.008 |
Twe | +0.008 |
ot | +0.008 |
Nem | +0.008 |
le | +0.008 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.007 |
ma | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -9.81e-02 |
Pos logit contributions | |
Twe | +0.037 |
ot | +0.036 |
Nem | +0.034 |
le | +0.033 |
Twe | +0.033 |
Neg logit contributions | |
outage | -0.043 |
ouncing | -0.042 |
hole | -0.041 |
ying | -0.041 |
rum | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Nem | +0.003 |
Twe | +0.003 |
le | +0.003 |
Neg logit contributions | |
outage | -0.003 |
ouncing | -0.003 |
hole | -0.003 |
ying | -0.003 |
ma | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
outage | +0.010 |
hole | +0.009 |
ouncing | +0.009 |
ying | +0.009 |
rum | +0.009 |
Neg logit contributions | |
Twe | -0.012 |
ot | -0.011 |
Nem | -0.011 |
le | -0.011 |
Twe | -0.010 |
Token | Whe |
Token ID | 10842 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
Twe | +0.023 |
ot | +0.022 |
Nem | +0.021 |
le | +0.021 |
Twe | +0.021 |
Neg logit contributions | |
outage | -0.025 |
ouncing | -0.025 |
hole | -0.024 |
ying | -0.024 |
ma | -0.023 |
Token | e |
Token ID | 68 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.001 |
Nem | +0.001 |
le | +0.001 |
Twe | +0.001 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
hole | -0.002 |
ying | -0.002 |
ma | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
Twe | +0.159 |
ot | +0.158 |
Nem | +0.152 |
Twe | +0.150 |
jew | +0.146 |
Neg logit contributions | |
ouncing | -0.119 |
outage | -0.114 |
hole | -0.109 |
ma | -0.109 |
ows | -0.109 |
Token | Tim |
Token ID | 5045 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
Twe | +0.020 |
ot | +0.019 |
Nem | +0.019 |
le | +0.018 |
Twe | +0.018 |
Neg logit contributions | |
outage | -0.019 |
hole | -0.018 |
ouncing | -0.018 |
ying | -0.018 |
ma | -0.017 |
Token | my |
Token ID | 1820 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
le | +0.002 |
Nem | +0.002 |
Twe | +0.002 |
Neg logit contributions | |
outage | -0.002 |
ying | -0.002 |
otion | -0.002 |
ouncing | -0.002 |
lessly | -0.002 |
Token | slid |
Token ID | 27803 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Nem | +0.001 |
le | +0.001 |
Twe | +0.001 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
ying | -0.002 |
hole | -0.002 |
ma | -0.002 |
Token | down |
Token ID | 866 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
outage | +0.001 |
Promise | +0.001 |
rum | +0.001 |
ouncing | +0.001 |
ems | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
le | -0.001 |
ot | -0.001 |
Nem | -0.001 |
Bub | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
le | +0.001 |
Nem | +0.001 |
Bub | +0.001 |
Neg logit contributions | |
outage | -0.001 |
hole | -0.001 |
ying | -0.001 |
ouncing | -0.001 |
ma | -0.001 |
Token | shouts |
Token ID | 34757 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
outage | +0.004 |
ying | +0.004 |
hole | +0.004 |
ouncing | +0.003 |
rum | +0.003 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.004 |
le | -0.004 |
Nem | -0.004 |
Bub | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Twe | +0.001 |
Nem | +0.001 |
le | +0.001 |
Neg logit contributions | |
ouncing | -0.001 |
outage | -0.001 |
ying | -0.001 |
hole | -0.001 |
ma | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
outage | +0.022 |
ouncing | +0.022 |
hole | +0.021 |
ying | +0.021 |
rum | +0.020 |
Neg logit contributions | |
Twe | -0.025 |
ot | -0.024 |
Nem | -0.023 |
le | -0.022 |
Twe | -0.022 |
Token | Whe |
Token ID | 10842 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Twe | +0.001 |
Nem | +0.001 |
le | +0.001 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
ying | -0.001 |
hole | -0.001 |
ows | -0.001 |
Token | e |
Token ID | 68 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
outage | +0.013 |
ouncing | +0.012 |
hole | +0.012 |
ying | +0.012 |
ma | +0.012 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
le | -0.006 |
Nem | -0.005 |
Twe | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Twe | +0.162 |
ot | +0.159 |
Nem | +0.153 |
Twe | +0.151 |
le | +0.149 |
Neg logit contributions | |
outage | -0.117 |
ouncing | -0.115 |
hole | -0.110 |
ying | -0.108 |
ma | -0.105 |
Token | This |
Token ID | 770 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Twe | +0.008 |
ot | +0.008 |
Nem | +0.008 |
le | +0.007 |
Twe | +0.007 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
hole | -0.004 |
ying | -0.004 |
lessly | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.012 |
le | +0.012 |
Nem | +0.011 |
Twe | +0.011 |
Neg logit contributions | |
outage | -0.012 |
ouncing | -0.011 |
ying | -0.011 |
hole | -0.011 |
rum | -0.011 |
Token | fun |
Token ID | 1257 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
outage | +0.026 |
ouncing | +0.026 |
hole | +0.025 |
ying | +0.025 |
rum | +0.024 |
Neg logit contributions | |
Twe | -0.024 |
ot | -0.023 |
Nem | -0.022 |
le | -0.021 |
Twe | -0.021 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
ouncing | +0.026 |
outage | +0.026 |
hole | +0.025 |
ying | +0.025 |
ma | +0.024 |
Neg logit contributions | |
Twe | -0.021 |
ot | -0.020 |
le | -0.020 |
Nem | -0.019 |
Twe | -0.017 |
Token | down |
Token ID | 866 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Twe | +0.023 |
le | +0.021 |
ot | +0.021 |
Nem | +0.020 |
Bub | +0.019 |
Neg logit contributions | |
outage | -0.014 |
ying | -0.012 |
ouncing | -0.012 |
rum | -0.011 |
Promise | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
outage | +0.017 |
hole | +0.017 |
ouncing | +0.017 |
lessly | +0.017 |
ying | +0.016 |
Neg logit contributions | |
ot | -0.016 |
Twe | -0.015 |
Twe | -0.015 |
Nem | -0.015 |
jew | -0.014 |
Token | slide |
Token ID | 10649 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Twe | +0.018 |
le | +0.017 |
ot | +0.016 |
Twe | +0.016 |
Nem | +0.015 |
Neg logit contributions | |
outage | -0.017 |
ems | -0.016 |
rum | -0.016 |
ouncing | -0.016 |
Deal | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Nem | +0.002 |
Twe | +0.002 |
le | +0.002 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
hole | -0.004 |
ying | -0.004 |
lessly | -0.004 |
Token | Whe |
Token ID | 5792 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.006 |
le | +0.006 |
Nem | +0.006 |
Twe | +0.006 |
Neg logit contributions | |
outage | -0.006 |
ying | -0.006 |
hole | -0.006 |
ouncing | -0.005 |
rum | -0.005 |
Token | e |
Token ID | 68 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
outage | +0.011 |
ouncing | +0.011 |
hole | +0.010 |
ying | +0.010 |
ma | +0.010 |
Neg logit contributions | |
Twe | -0.009 |
ot | -0.009 |
Nem | -0.008 |
le | -0.008 |
Twe | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
ot | +0.145 |
Nem | +0.139 |
Twe | +0.135 |
jew | +0.132 |
Twe | +0.132 |
Neg logit contributions | |
ouncing | -0.140 |
ows | -0.128 |
hole | -0.120 |
ma | -0.120 |
outage | -0.118 |
Token | It |
Token ID | 632 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Twe | +0.017 |
ot | +0.016 |
Nem | +0.015 |
Twe | +0.015 |
le | +0.015 |
Neg logit contributions | |
outage | -0.014 |
ouncing | -0.013 |
hole | -0.013 |
ying | -0.013 |
rum | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
Twe | +0.031 |
ot | +0.030 |
Nem | +0.028 |
Twe | +0.027 |
le | +0.027 |
Neg logit contributions | |
outage | -0.069 |
ouncing | -0.067 |
hole | -0.066 |
ying | -0.066 |
ma | -0.064 |
Token | so |
Token ID | 523 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
outage | +0.007 |
ouncing | +0.007 |
ying | +0.007 |
hole | +0.007 |
rum | +0.007 |
Neg logit contributions | |
Twe | -0.007 |
le | -0.006 |
ot | -0.006 |
Nem | -0.006 |
Twe | -0.006 |
Token | much |
Token ID | 881 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
outage | +0.023 |
hole | +0.022 |
rum | +0.021 |
ying | +0.020 |
ouncing | +0.020 |
Neg logit contributions | |
Twe | -0.024 |
ot | -0.021 |
le | -0.021 |
Nem | -0.021 |
Twe | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
outage | +0.006 |
ouncing | +0.005 |
hole | +0.005 |
ying | +0.005 |
rum | +0.005 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
Nem | -0.006 |
le | -0.006 |
Bub | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | +6.74e-04 |
Pos logit contributions | |
outage | +0.008 |
ying | +0.007 |
hole | +0.007 |
ouncing | +0.007 |
rum | +0.007 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.005 |
Nem | -0.005 |
le | -0.005 |
Twe | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
outage | +0.000 |
hole | +0.000 |
ouncing | +0.000 |
ying | +0.000 |
rum | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
ot | -0.000 |
Nem | -0.000 |
le | -0.000 |
Bub | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
outage | +0.016 |
hole | +0.015 |
ying | +0.014 |
rum | +0.014 |
ouncing | +0.014 |
Neg logit contributions | |
Twe | -0.012 |
le | -0.011 |
Nem | -0.011 |
ot | -0.011 |
Bub | -0.011 |
Token | Whe |
Token ID | 10842 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
Twe | +0.018 |
ot | +0.017 |
Nem | +0.017 |
Twe | +0.016 |
le | +0.016 |
Neg logit contributions | |
outage | -0.016 |
ouncing | -0.015 |
hole | -0.015 |
ying | -0.015 |
ma | -0.014 |
Token | e |
Token ID | 68 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
hole | +0.005 |
ying | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
le | -0.003 |
Twe | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
ot | +0.157 |
Twe | +0.156 |
Nem | +0.151 |
Twe | +0.149 |
jew | +0.146 |
Neg logit contributions | |
ouncing | -0.117 |
outage | -0.109 |
ma | -0.106 |
hole | -0.105 |
ows | -0.105 |
Token | This |
Token ID | 770 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Twe | +0.008 |
ot | +0.007 |
Nem | +0.007 |
Twe | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.005 |
ying | -0.005 |
hole | -0.005 |
ouncing | -0.004 |
lessly | -0.004 |
Token | is |
Token ID | 318 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.012 |
le | +0.012 |
Nem | +0.012 |
Twe | +0.011 |
Neg logit contributions | |
outage | -0.012 |
ouncing | -0.011 |
ying | -0.011 |
hole | -0.011 |
rum | -0.011 |
Token | fun |
Token ID | 1257 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
outage | +0.027 |
ouncing | +0.027 |
ying | +0.026 |
hole | +0.026 |
rum | +0.025 |
Neg logit contributions | |
Twe | -0.026 |
ot | -0.024 |
Nem | -0.024 |
le | -0.023 |
Twe | -0.023 |
Token | ! |
Token ID | 0 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
ouncing | +0.020 |
outage | +0.020 |
hole | +0.020 |
ying | +0.020 |
Deal | +0.019 |
Neg logit contributions | |
Twe | -0.017 |
ot | -0.016 |
le | -0.016 |
Nem | -0.015 |
se | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
outage | +0.037 |
rum | +0.030 |
hole | +0.030 |
ouncing | +0.029 |
lessly | +0.029 |
Neg logit contributions | |
Twe | -0.021 |
le | -0.019 |
Nem | -0.018 |
sp | -0.018 |
- | -0.018 |
Token | slide |
Token ID | 10649 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.009 |
le | +0.009 |
Nem | +0.009 |
Twe | +0.009 |
Neg logit contributions | |
outage | -0.011 |
ouncing | -0.010 |
ying | -0.010 |
hole | -0.010 |
rum | -0.010 |
Token | down |
Token ID | 866 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Twe | +0.010 |
le | +0.009 |
Nem | +0.009 |
ot | +0.009 |
Twe | +0.008 |
Neg logit contributions | |
outage | -0.010 |
ouncing | -0.009 |
Promise | -0.009 |
rum | -0.008 |
ying | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.008 |
hole | +0.008 |
ying | +0.008 |
rum | +0.008 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
le | -0.007 |
Nem | -0.007 |
Twe | -0.006 |
Token | Whe |
Token ID | 5792 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
ying | +0.007 |
outage | +0.007 |
ouncing | +0.006 |
hole | +0.006 |
lessly | +0.006 |
Neg logit contributions | |
Twe | -0.009 |
ot | -0.008 |
Nem | -0.008 |
Twe | -0.008 |
Bub | -0.008 |
Token | e |
Token ID | 68 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
le | +0.000 |
Nem | +0.000 |
Twe | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ma | -0.000 |
lessly | -0.000 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Twe | +0.170 |
ot | +0.169 |
Nem | +0.162 |
Twe | +0.162 |
jew | +0.158 |
Neg logit contributions | |
ouncing | -0.104 |
outage | -0.101 |
ows | -0.097 |
hole | -0.096 |
ying | -0.095 |
Token |
|
Token ID | 198 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.007 |
Twe | +0.007 |
Nem | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.013 |
ying | -0.013 |
ouncing | -0.012 |
hole | -0.012 |
rum | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
outage | +0.000 |
ouncing | +0.000 |
hole | +0.000 |
ying | +0.000 |
ma | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
ot | -0.000 |
Twe | -0.000 |
Nem | -0.000 |
le | -0.000 |
Token | Tim |
Token ID | 14967 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
outage | +0.004 |
ying | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ows | +0.003 |
Neg logit contributions | |
Twe | -0.004 |
Twe | -0.004 |
ot | -0.004 |
le | -0.003 |
Nem | -0.003 |
Token | slid |
Token ID | 27803 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Twe | +0.020 |
ot | +0.019 |
Nem | +0.018 |
le | +0.018 |
Twe | +0.018 |
Neg logit contributions | |
outage | -0.027 |
ouncing | -0.026 |
hole | -0.025 |
ying | -0.025 |
ma | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
ot | +0.037 |
jew | +0.036 |
Twe | +0.036 |
Twe | +0.036 |
Nem | +0.034 |
Neg logit contributions | |
ouncing | -0.031 |
does | -0.028 |
falls | -0.027 |
ows | -0.027 |
about | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Twe | +0.003 |
Nem | +0.003 |
jew | +0.003 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
hole | -0.002 |
ying | -0.002 |
about | -0.002 |
Token | get |
Token ID | 651 |
Feature activation | -7.85e-02 |
Pos logit contributions | |
Twe | +0.025 |
ot | +0.024 |
Twe | +0.023 |
Nem | +0.023 |
le | +0.022 |
Neg logit contributions | |
outage | -0.029 |
hole | -0.027 |
ouncing | -0.027 |
ma | -0.027 |
ying | -0.027 |
Token | more |
Token ID | 517 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
jew | +0.003 |
ho | +0.003 |
io | +0.003 |
Neg logit contributions | |
forth | -0.001 |
down | -0.001 |
onwards | -0.001 |
OK | -0.001 |
on | -0.001 |
Token | ice |
Token ID | 4771 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
Twe | +0.007 |
Twe | +0.007 |
ot | +0.007 |
Nem | +0.006 |
Bub | +0.006 |
Neg logit contributions | |
outage | -0.010 |
hole | -0.009 |
ying | -0.009 |
ouncing | -0.009 |
rum | -0.009 |
Token | - |
Token ID | 12 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
Twe | +0.049 |
ot | +0.048 |
Twe | +0.048 |
Nem | +0.046 |
Bub | +0.045 |
Neg logit contributions | |
ying | -0.079 |
outage | -0.079 |
hole | -0.077 |
ouncing | -0.076 |
ows | -0.075 |
Token | cream |
Token ID | 36277 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ot | +0.133 |
jew | +0.129 |
Nem | +0.125 |
Bub | +0.120 |
Twe | +0.116 |
Neg logit contributions | |
aking | -0.130 |
ying | -0.126 |
ouncing | -0.124 |
hole | -0.123 |
lessly | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Twe | +0.055 |
ot | +0.053 |
Twe | +0.050 |
Nem | +0.050 |
le | +0.048 |
Neg logit contributions | |
outage | -0.084 |
ouncing | -0.081 |
hole | -0.081 |
ying | -0.080 |
ma | -0.077 |
Token | Spot |
Token ID | 15899 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ot | +0.005 |
Twe | +0.005 |
Twe | +0.005 |
jew | +0.005 |
Nem | +0.005 |
Neg logit contributions | |
ouncing | -0.005 |
outage | -0.005 |
Today | -0.005 |
ma | -0.005 |
hole | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
ouncing | +0.008 |
outage | +0.007 |
ma | +0.007 |
hole | +0.007 |
ying | +0.007 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
Twe | -0.007 |
jew | -0.007 |
Nem | -0.007 |
Token | worried |
Token ID | 7960 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
outage | +0.010 |
hole | +0.010 |
ying | +0.010 |
ouncing | +0.010 |
ems | +0.010 |
Neg logit contributions | |
Twe | -0.012 |
le | -0.011 |
ot | -0.011 |
Nem | -0.010 |
Twe | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Twe | +0.026 |
ot | +0.025 |
Twe | +0.024 |
Nem | +0.023 |
le | +0.022 |
Neg logit contributions | |
outage | -0.033 |
ouncing | -0.033 |
hole | -0.032 |
ying | -0.032 |
lessly | -0.031 |
Token | now |
Token ID | 783 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Twe | +0.016 |
ot | +0.016 |
Twe | +0.015 |
Nem | +0.015 |
le | +0.015 |
Neg logit contributions | |
outage | -0.010 |
ouncing | -0.010 |
ying | -0.010 |
hole | -0.009 |
ma | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Twe | +0.043 |
ot | +0.041 |
Nem | +0.040 |
le | +0.039 |
Twe | +0.038 |
Neg logit contributions | |
outage | -0.039 |
ouncing | -0.038 |
hole | -0.038 |
ying | -0.037 |
ma | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -7.93e-01 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.007 |
Nem | +0.006 |
le | +0.006 |
jew | +0.006 |
Neg logit contributions | |
outage | -0.010 |
hole | -0.010 |
ouncing | -0.010 |
ying | -0.010 |
rum | -0.009 |
Token | well |
Token ID | 880 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
Twe | +0.027 |
ot | +0.026 |
Nem | +0.025 |
le | +0.024 |
Twe | +0.024 |
Neg logit contributions | |
outage | -0.024 |
ouncing | -0.023 |
hole | -0.023 |
ying | -0.022 |
ma | -0.021 |
Token | - |
Token ID | 12 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
Twe | +0.053 |
ot | +0.051 |
Twe | +0.050 |
Nem | +0.047 |
le | +0.046 |
Neg logit contributions | |
outage | -0.070 |
ouncing | -0.069 |
ying | -0.068 |
hole | -0.067 |
lessly | -0.066 |
Token | fed |
Token ID | 19082 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ot | +0.132 |
jew | +0.121 |
Nem | +0.118 |
Twe | +0.117 |
se | +0.117 |
Neg logit contributions | |
ouncing | -0.152 |
ying | -0.140 |
aking | -0.136 |
lessly | -0.131 |
ows | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.006 |
ouncing | -0.006 |
hole | -0.006 |
ying | -0.006 |
ma | -0.006 |
Token | From |
Token ID | 3574 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Nem | +0.002 |
le | +0.002 |
Twe | +0.002 |
Neg logit contributions | |
outage | -0.001 |
hole | -0.001 |
ying | -0.001 |
ouncing | -0.001 |
ows | -0.001 |
Token | then |
Token ID | 788 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
outage | +0.021 |
ouncing | +0.020 |
hole | +0.020 |
ying | +0.020 |
ma | +0.019 |
Neg logit contributions | |
Twe | -0.021 |
ot | -0.020 |
Nem | -0.019 |
le | -0.019 |
Twe | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
le | +0.009 |
Twe | +0.009 |
B | +0.008 |
ot | +0.008 |
B | +0.008 |
Neg logit contributions | |
outage | -0.012 |
ows | -0.011 |
hole | -0.010 |
fuss | -0.010 |
ouncing | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
outage | +0.014 |
ying | +0.013 |
hole | +0.013 |
rum | +0.013 |
ouncing | +0.013 |
Neg logit contributions | |
Twe | -0.015 |
ot | -0.013 |
Twe | -0.013 |
le | -0.013 |
Nem | -0.013 |
Token | shouts |
Token ID | 34757 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
hole | +0.008 |
ying | +0.008 |
rum | +0.008 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.016 |
le | -0.015 |
Nem | -0.015 |
Twe | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.002 |
ying | +0.002 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
Twe | -0.003 |
le | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
outage | +0.008 |
hole | +0.008 |
ying | +0.008 |
rum | +0.008 |
instant | +0.007 |
Neg logit contributions | |
Twe | -0.005 |
le | -0.005 |
ot | -0.005 |
Nem | -0.005 |
Bub | -0.005 |
Token | Whe |
Token ID | 10842 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.012 |
Nem | +0.012 |
le | +0.012 |
Twe | +0.012 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.007 |
hole | -0.007 |
ying | -0.007 |
ma | -0.007 |
Token | e |
Token ID | 68 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
outage | +0.013 |
ouncing | +0.013 |
hole | +0.012 |
ying | +0.012 |
lessly | +0.012 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
le | -0.007 |
Nem | -0.006 |
Twe | -0.006 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Twe | +0.152 |
ot | +0.151 |
Nem | +0.145 |
Twe | +0.143 |
jew | +0.140 |
Neg logit contributions | |
ouncing | -0.120 |
outage | -0.116 |
hole | -0.112 |
ying | -0.110 |
ma | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.007 |
Nem | +0.007 |
le | +0.007 |
Twe | +0.006 |
Neg logit contributions | |
outage | -0.008 |
hole | -0.008 |
ying | -0.008 |
ouncing | -0.008 |
rum | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.003 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
le | -0.003 |
Twe | -0.003 |
Token | Sam |
Token ID | 16305 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
hole | +0.005 |
ying | +0.005 |
ma | +0.005 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
Nem | -0.006 |
le | -0.006 |
Twe | -0.006 |
Token | watches |
Token ID | 16860 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
le | +0.007 |
Twe | +0.006 |
ot | +0.006 |
Nem | +0.006 |
se | +0.006 |
Neg logit contributions | |
outage | -0.006 |
ying | -0.005 |
hole | -0.005 |
lessly | -0.005 |
ouncing | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
hole | +0.004 |
ying | +0.004 |
rum | +0.004 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Twe | -0.002 |
Token | shouted |
Token ID | 17293 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
le | +0.000 |
Twe | +0.000 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
ying | -0.001 |
hole | -0.001 |
rum | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.006 |
Nem | +0.006 |
le | +0.006 |
Twe | +0.006 |
Neg logit contributions | |
outage | -0.011 |
ouncing | -0.010 |
hole | -0.010 |
ying | -0.010 |
ma | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
outage | +0.001 |
ying | +0.001 |
hole | +0.001 |
rum | +0.001 |
instant | +0.001 |
Neg logit contributions | |
Twe | -0.000 |
le | -0.000 |
ot | -0.000 |
Nem | -0.000 |
Bub | -0.000 |
Token | Whe |
Token ID | 10842 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Twe | +0.019 |
ot | +0.019 |
Nem | +0.018 |
le | +0.018 |
jew | +0.017 |
Neg logit contributions | |
outage | -0.012 |
ouncing | -0.012 |
hole | -0.011 |
ying | -0.011 |
ma | -0.011 |
Token | e |
Token ID | 68 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
outage | +0.012 |
ouncing | +0.012 |
hole | +0.012 |
ying | +0.012 |
ma | +0.011 |
Neg logit contributions | |
Twe | -0.009 |
ot | -0.009 |
Nem | -0.008 |
le | -0.008 |
Twe | -0.008 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Twe | +0.165 |
ot | +0.165 |
Nem | +0.160 |
Twe | +0.158 |
jew | +0.156 |
Neg logit contributions | |
ouncing | -0.106 |
outage | -0.098 |
ows | -0.095 |
hole | -0.095 |
ma | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
Twe | +0.016 |
Nem | +0.015 |
ot | +0.015 |
le | +0.015 |
Twe | +0.014 |
Neg logit contributions | |
outage | -0.021 |
hole | -0.020 |
ying | -0.020 |
ouncing | -0.020 |
rum | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
le | +0.000 |
jew | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ying | -0.000 |
ma | -0.000 |
Token | L |
Token ID | 43 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.002 |
hole | +0.002 |
ying | +0.002 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
le | -0.004 |
jew | -0.004 |
Token | ily |
Token ID | 813 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.006 |
Nem | +0.006 |
jew | +0.006 |
Twe | +0.006 |
Neg logit contributions | |
outage | -0.005 |
ying | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ows | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
hole | +0.008 |
ying | +0.008 |
ma | +0.008 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
Twe | -0.006 |
Nem | -0.006 |
le | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.012 |
Twe | +0.011 |
Nem | +0.011 |
jew | +0.011 |
Neg logit contributions | |
ouncing | -0.012 |
outage | -0.012 |
ma | -0.011 |
hole | -0.011 |
lessly | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Twe | +0.008 |
ot | +0.008 |
Nem | +0.008 |
le | +0.008 |
jew | +0.007 |
Neg logit contributions | |
outage | -0.011 |
hole | -0.010 |
ouncing | -0.010 |
ying | -0.010 |
Today | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
outage | +0.013 |
hole | +0.013 |
ouncing | +0.012 |
ying | +0.012 |
rum | +0.012 |
Neg logit contributions | |
Twe | -0.011 |
Nem | -0.011 |
ot | -0.010 |
le | -0.010 |
Bub | -0.010 |
Token | Whe |
Token ID | 10842 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
Twe | +0.022 |
ot | +0.022 |
le | +0.021 |
Nem | +0.021 |
jew | +0.020 |
Neg logit contributions | |
ouncing | -0.021 |
hole | -0.021 |
outage | -0.020 |
Today | -0.020 |
lessly | -0.019 |
Token | e |
Token ID | 68 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
hole | +0.001 |
ying | +0.001 |
ma | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Nem | -0.001 |
le | -0.001 |
Twe | -0.001 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
Twe | +0.150 |
ot | +0.150 |
Nem | +0.144 |
Twe | +0.143 |
jew | +0.140 |
Neg logit contributions | |
ouncing | -0.118 |
outage | -0.111 |
hole | -0.107 |
ma | -0.107 |
ows | -0.106 |
Token | The |
Token ID | 383 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
Twe | +0.019 |
ot | +0.017 |
Nem | +0.017 |
le | +0.016 |
Twe | +0.016 |
Neg logit contributions | |
outage | -0.019 |
ying | -0.018 |
hole | -0.018 |
ouncing | -0.018 |
rum | -0.017 |
Token | subway |
Token ID | 19612 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.012 |
Nem | +0.012 |
Twe | +0.012 |
le | +0.011 |
Neg logit contributions | |
outage | -0.014 |
ouncing | -0.013 |
hole | -0.013 |
ying | -0.013 |
ma | -0.013 |
Token | went |
Token ID | 1816 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.010 |
Nem | +0.009 |
Twe | +0.009 |
le | +0.009 |
Neg logit contributions | |
outage | -0.016 |
ouncing | -0.016 |
hole | -0.015 |
ying | -0.015 |
ma | -0.015 |
Token | under |
Token ID | 739 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
hole | +0.005 |
ying | +0.005 |
lessly | +0.004 |
Neg logit contributions | |
Twe | -0.008 |
ot | -0.008 |
Nem | -0.008 |
Twe | -0.007 |
le | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
outage | +0.008 |
ouncing | +0.008 |
hole | +0.007 |
ying | +0.007 |
Today | +0.007 |
Neg logit contributions | |
Twe | -0.010 |
ot | -0.009 |
le | -0.009 |
Nem | -0.009 |
Twe | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
outage | +0.018 |
hole | +0.018 |
ouncing | +0.017 |
ying | +0.017 |
ma | +0.017 |
Neg logit contributions | |
ot | -0.016 |
Twe | -0.016 |
Twe | -0.015 |
Nem | -0.015 |
le | -0.014 |
Token | grass |
Token ID | 8701 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
le | +0.005 |
Nem | +0.004 |
Twe | +0.004 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
ying | -0.004 |
hole | -0.004 |
rum | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.006 |
le | +0.006 |
Nem | +0.005 |
Twe | +0.005 |
Neg logit contributions | |
ouncing | -0.007 |
outage | -0.007 |
ying | -0.007 |
rum | -0.007 |
Deal | -0.007 |
Token | Whe |
Token ID | 5792 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
ying | +0.009 |
outage | +0.009 |
ouncing | +0.008 |
hole | +0.008 |
rum | +0.008 |
Neg logit contributions | |
Twe | -0.012 |
ot | -0.012 |
Nem | -0.011 |
le | -0.011 |
Twe | -0.011 |
Token | e |
Token ID | 68 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
outage | +0.015 |
ouncing | +0.014 |
hole | +0.014 |
lessly | +0.014 |
Today | +0.014 |
Neg logit contributions | |
Twe | -0.007 |
le | -0.007 |
Nem | -0.007 |
ot | -0.007 |
se | -0.006 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
Twe | +0.166 |
ot | +0.164 |
Nem | +0.158 |
Twe | +0.156 |
le | +0.153 |
Neg logit contributions | |
ouncing | -0.104 |
outage | -0.104 |
hole | -0.098 |
ying | -0.096 |
ma | -0.094 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Twe | +0.014 |
ot | +0.013 |
Nem | +0.013 |
le | +0.012 |
Twe | +0.012 |
Neg logit contributions | |
outage | -0.023 |
hole | -0.023 |
ouncing | -0.023 |
ying | -0.022 |
rum | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
Twe | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
hole | -0.004 |
ying | -0.004 |
ma | -0.004 |
Token | L |
Token ID | 43 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
outage | +0.002 |
hole | +0.002 |
ying | +0.002 |
ouncing | +0.002 |
rum | +0.002 |
Neg logit contributions | |
Twe | -0.001 |
Twe | -0.001 |
le | -0.001 |
ot | -0.001 |
Nem | -0.001 |
Token | ily |
Token ID | 813 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.012 |
Nem | +0.011 |
Twe | +0.011 |
le | +0.011 |
Neg logit contributions | |
outage | -0.011 |
ouncing | -0.011 |
ying | -0.010 |
hole | -0.010 |
ma | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
ouncing | +0.028 |
Deal | +0.027 |
Promise | +0.027 |
outage | +0.027 |
rum | +0.027 |
Neg logit contributions | |
le | -0.020 |
Twe | -0.019 |
ot | -0.018 |
se | -0.018 |
pl | -0.017 |
Token | slides |
Token ID | 19392 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
Twe | +0.019 |
le | +0.018 |
ot | +0.017 |
Nem | +0.017 |
pl | +0.017 |
Neg logit contributions | |
outage | -0.019 |
rum | -0.017 |
ying | -0.017 |
ouncing | -0.016 |
lessness | -0.016 |
Token | down |
Token ID | 866 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Twe | +0.035 |
ot | +0.033 |
le | +0.033 |
Nem | +0.032 |
Twe | +0.031 |
Neg logit contributions | |
outage | -0.017 |
ouncing | -0.015 |
hole | -0.014 |
rum | -0.014 |
ying | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
outage | +0.008 |
ouncing | +0.008 |
hole | +0.008 |
ying | +0.008 |
lessly | +0.008 |
Neg logit contributions | |
ot | -0.006 |
Twe | -0.006 |
Twe | -0.006 |
Nem | -0.006 |
jew | -0.006 |
Token | Whe |
Token ID | 5792 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
outage | +0.006 |
hole | +0.006 |
ying | +0.006 |
rum | +0.006 |
ouncing | +0.005 |
Neg logit contributions | |
Twe | -0.005 |
le | -0.005 |
Nem | -0.005 |
Twe | -0.005 |
ot | -0.005 |
Token | e |
Token ID | 68 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
outage | +0.011 |
ouncing | +0.010 |
hole | +0.010 |
ma | +0.010 |
ying | +0.010 |
Neg logit contributions | |
Twe | -0.006 |
le | -0.005 |
Nem | -0.005 |
ot | -0.005 |
Twe | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ot | +0.144 |
Twe | +0.140 |
Nem | +0.136 |
Twe | +0.135 |
jew | +0.131 |
Neg logit contributions | |
ouncing | -0.129 |
ows | -0.120 |
outage | -0.118 |
hole | -0.116 |
ma | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
Twe | +0.004 |
Nem | +0.004 |
Twe | +0.004 |
le | +0.004 |
Bub | +0.003 |
Neg logit contributions | |
outage | -0.007 |
hole | -0.006 |
ying | -0.006 |
rum | -0.006 |
forth | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.003 |
Neg logit contributions | |
Twe | -0.002 |
Nem | -0.002 |
ot | -0.002 |
Twe | -0.002 |
le | -0.002 |
Token | They |
Token ID | 2990 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.003 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
Twe | -0.004 |
le | -0.004 |
Token | do |
Token ID | 466 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
Twe | +0.036 |
ot | +0.034 |
Nem | +0.033 |
le | +0.033 |
Twe | +0.032 |
Neg logit contributions | |
outage | -0.029 |
ouncing | -0.028 |
ying | -0.027 |
hole | -0.027 |
rum | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
ouncing | +0.030 |
outage | +0.028 |
Deal | +0.028 |
Promise | +0.028 |
rum | +0.028 |
Neg logit contributions | |
le | -0.020 |
Twe | -0.019 |
ot | -0.018 |
se | -0.017 |
Nem | -0.016 |
Token | slides |
Token ID | 19392 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
Twe | +0.020 |
le | +0.020 |
ot | +0.019 |
Nem | +0.019 |
pl | +0.018 |
Neg logit contributions | |
outage | -0.019 |
ying | -0.017 |
rum | -0.017 |
hole | -0.016 |
ouncing | -0.016 |
Token | down |
Token ID | 866 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Twe | +0.037 |
ot | +0.035 |
le | +0.035 |
Nem | +0.035 |
Twe | +0.033 |
Neg logit contributions | |
outage | -0.016 |
ouncing | -0.014 |
hole | -0.014 |
ying | -0.014 |
rum | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +6.00e-02 |
Pos logit contributions | |
outage | +0.006 |
hole | +0.006 |
ouncing | +0.006 |
lessly | +0.006 |
ying | +0.006 |
Neg logit contributions | |
ot | -0.005 |
Twe | -0.004 |
Twe | -0.004 |
Nem | -0.004 |
jew | -0.004 |
Token | Whe |
Token ID | 5792 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
outage | +0.002 |
hole | +0.002 |
ying | +0.002 |
ouncing | +0.002 |
rum | +0.002 |
Neg logit contributions | |
Twe | -0.002 |
Nem | -0.002 |
ot | -0.002 |
le | -0.002 |
Bub | -0.002 |
Token | e |
Token ID | 68 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
outage | +0.007 |
ouncing | +0.007 |
hole | +0.007 |
ma | +0.007 |
lessly | +0.006 |
Neg logit contributions | |
Twe | -0.004 |
le | -0.004 |
Nem | -0.004 |
ot | -0.004 |
Twe | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
ot | +0.149 |
Twe | +0.144 |
Nem | +0.141 |
Twe | +0.139 |
jew | +0.137 |
Neg logit contributions | |
ouncing | -0.124 |
ows | -0.117 |
outage | -0.111 |
hole | -0.110 |
ma | -0.110 |
Token |
|
Token ID | 198 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
Twe | +0.008 |
Nem | +0.007 |
ot | +0.007 |
Twe | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.010 |
hole | -0.010 |
ying | -0.010 |
ouncing | -0.009 |
rum | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
hole | +0.001 |
ying | +0.001 |
ma | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
Nem | -0.001 |
ot | -0.001 |
Twe | -0.001 |
le | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
hole | +0.001 |
ying | +0.001 |
ma | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Nem | -0.001 |
le | -0.001 |
Twe | -0.001 |
Token | Wow |
Token ID | 22017 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
Twe | +0.018 |
ot | +0.018 |
Nem | +0.017 |
le | +0.017 |
Twe | +0.017 |
Neg logit contributions | |
outage | -0.016 |
ouncing | -0.015 |
hole | -0.015 |
ma | -0.015 |
ying | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
hole | +0.001 |
ying | +0.001 |
ma | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Nem | -0.001 |
le | -0.001 |
jew | -0.001 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Twe | +0.018 |
ot | +0.018 |
Twe | +0.017 |
Nem | +0.017 |
le | +0.017 |
Neg logit contributions | |
outage | -0.021 |
ouncing | -0.021 |
ying | -0.020 |
hole | -0.020 |
ma | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
ouncing | +0.007 |
outage | +0.007 |
hole | +0.007 |
ying | +0.007 |
ma | +0.006 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.005 |
Twe | -0.005 |
Nem | -0.005 |
le | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Nem | +0.011 |
le | +0.011 |
Twe | +0.011 |
Neg logit contributions | |
outage | -0.007 |
ouncing | -0.007 |
hole | -0.007 |
ying | -0.006 |
ma | -0.006 |
Token | happiest |
Token ID | 49414 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
Twe | +0.028 |
Twe | +0.026 |
Nem | +0.024 |
le | +0.024 |
ot | +0.024 |
Neg logit contributions | |
ma | -0.012 |
instant | -0.011 |
outage | -0.011 |
lessly | -0.011 |
grin | -0.011 |
Token | oct |
Token ID | 19318 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Twe | +0.006 |
Twe | +0.006 |
ot | +0.005 |
jew | +0.005 |
le | +0.005 |
Neg logit contributions | |
outage | -0.006 |
ying | -0.006 |
ouncing | -0.006 |
ma | -0.006 |
lessly | -0.006 |
Token | opus |
Token ID | 25790 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Twe | +0.184 |
jew | +0.169 |
ot | +0.169 |
Nem | +0.166 |
le | +0.163 |
Neg logit contributions | |
ouncing | -0.097 |
outage | -0.096 |
ying | -0.090 |
apping | -0.089 |
lessly | -0.078 |
Token | in |
Token ID | 287 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
Twe | +0.072 |
ot | +0.069 |
Twe | +0.069 |
le | +0.066 |
Nem | +0.065 |
Neg logit contributions | |
outage | -0.072 |
ying | -0.069 |
ouncing | -0.068 |
hole | -0.067 |
lessly | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Twe | +0.022 |
ot | +0.022 |
Twe | +0.021 |
le | +0.020 |
Nem | +0.020 |
Neg logit contributions | |
outage | -0.029 |
ying | -0.028 |
hole | -0.028 |
ouncing | -0.028 |
ma | -0.027 |
Token | whole |
Token ID | 2187 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
Twe | +0.016 |
Twe | +0.015 |
ot | +0.014 |
le | +0.014 |
Nem | +0.014 |
Neg logit contributions | |
Today | -0.007 |
outage | -0.007 |
instant | -0.007 |
ma | -0.007 |
hole | -0.007 |
Token | ocean |
Token ID | 9151 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Twe | +0.008 |
Twe | +0.008 |
ot | +0.008 |
le | +0.007 |
Nem | +0.007 |
Neg logit contributions | |
outage | -0.004 |
Today | -0.003 |
instant | -0.003 |
hole | -0.003 |
ma | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
outage | +0.005 |
hole | +0.005 |
ying | +0.005 |
ouncing | +0.005 |
rum | +0.005 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.004 |
le | -0.004 |
Nem | -0.004 |
Bub | -0.004 |
Token | shouts |
Token ID | 34757 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
outage | +0.004 |
ying | +0.004 |
hole | +0.004 |
ouncing | +0.004 |
rum | +0.004 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.005 |
le | -0.005 |
Nem | -0.005 |
se | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.003 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
Twe | -0.003 |
le | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
outage | +0.003 |
ying | +0.003 |
hole | +0.003 |
rum | +0.003 |
ouncing | +0.003 |
Neg logit contributions | |
Twe | -0.002 |
le | -0.002 |
ot | -0.002 |
Nem | -0.002 |
Bub | -0.002 |
Token | Whe |
Token ID | 10842 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Twe | +0.017 |
ot | +0.016 |
Nem | +0.016 |
le | +0.015 |
Twe | +0.015 |
Neg logit contributions | |
outage | -0.013 |
ouncing | -0.013 |
hole | -0.012 |
ying | -0.012 |
ma | -0.012 |
Token | e |
Token ID | 68 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
hole | +0.009 |
ying | +0.009 |
lessly | +0.009 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
le | -0.005 |
Nem | -0.004 |
Twe | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
Twe | +0.146 |
ot | +0.144 |
Nem | +0.138 |
Twe | +0.136 |
le | +0.133 |
Neg logit contributions | |
ouncing | -0.122 |
outage | -0.121 |
hole | -0.115 |
ying | -0.114 |
ma | -0.113 |
Token | This |
Token ID | 770 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.003 |
le | +0.003 |
Twe | +0.003 |
Neg logit contributions | |
outage | -0.002 |
ying | -0.002 |
hole | -0.002 |
ouncing | -0.002 |
lessly | -0.002 |
Token | is |
Token ID | 318 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
le | +0.009 |
Twe | +0.009 |
ot | +0.009 |
se | +0.008 |
pl | +0.008 |
Neg logit contributions | |
ouncing | -0.010 |
outage | -0.010 |
ying | -0.010 |
rum | -0.010 |
lessly | -0.010 |
Token | fun |
Token ID | 1257 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
outage | +0.026 |
ouncing | +0.025 |
hole | +0.025 |
ying | +0.024 |
rum | +0.023 |
Neg logit contributions | |
Twe | -0.028 |
ot | -0.027 |
Nem | -0.026 |
le | -0.025 |
Twe | -0.025 |
Token | ! |
Token ID | 0 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ouncing | +0.028 |
outage | +0.028 |
hole | +0.027 |
ying | +0.027 |
itates | +0.026 |
Neg logit contributions | |
Twe | -0.019 |
ot | -0.019 |
le | -0.018 |
Nem | -0.017 |
jew | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
le | +0.002 |
Nem | +0.002 |
se | +0.002 |
Neg logit contributions | |
outage | -0.002 |
ying | -0.002 |
ouncing | -0.002 |
hole | -0.002 |
rum | -0.002 |
Token | shouts |
Token ID | 34757 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
outage | +0.001 |
ying | +0.001 |
hole | +0.001 |
ouncing | +0.001 |
rum | +0.001 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
le | -0.002 |
Nem | -0.002 |
jew | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
ouncing | +0.005 |
outage | +0.005 |
ying | +0.005 |
hole | +0.005 |
ma | +0.005 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
Twe | -0.005 |
Nem | -0.005 |
le | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
outage | +0.003 |
ying | +0.003 |
hole | +0.003 |
rum | +0.003 |
instant | +0.003 |
Neg logit contributions | |
Twe | -0.002 |
le | -0.002 |
ot | -0.002 |
Nem | -0.002 |
Bub | -0.002 |
Token | Whe |
Token ID | 10842 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Twe | +0.020 |
ot | +0.020 |
Nem | +0.019 |
le | +0.019 |
jew | +0.018 |
Neg logit contributions | |
ouncing | -0.011 |
outage | -0.011 |
hole | -0.011 |
ma | -0.010 |
ying | -0.010 |
Token | e |
Token ID | 68 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
hole | +0.009 |
ying | +0.009 |
ma | +0.009 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.005 |
le | -0.005 |
Nem | -0.005 |
Twe | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
Twe | +0.153 |
ot | +0.153 |
Nem | +0.147 |
Twe | +0.146 |
jew | +0.143 |
Neg logit contributions | |
ouncing | -0.114 |
outage | -0.107 |
hole | -0.104 |
ma | -0.104 |
rum | -0.102 |
Token | That |
Token ID | 1320 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
le | +0.004 |
Twe | +0.004 |
Neg logit contributions | |
outage | -0.003 |
ying | -0.002 |
hole | -0.002 |
ouncing | -0.002 |
lessly | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
le | +0.004 |
Nem | +0.003 |
Twe | +0.003 |
Neg logit contributions | |
outage | -0.004 |
ying | -0.004 |
ouncing | -0.004 |
rum | -0.004 |
hole | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
hole | +0.004 |
ying | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.005 |
ot | -0.004 |
Nem | -0.004 |
Twe | -0.004 |
le | -0.004 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
outage | +0.013 |
ouncing | +0.013 |
hole | +0.012 |
ying | +0.012 |
lessly | +0.012 |
Neg logit contributions | |
Twe | -0.010 |
ot | -0.010 |
le | -0.010 |
Nem | -0.009 |
se | -0.008 |
Token | slides |
Token ID | 19392 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
ying | +0.004 |
hole | +0.004 |
rum | +0.004 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.003 |
Nem | -0.003 |
le | -0.003 |
Twe | -0.003 |
Token | down |
Token ID | 866 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Twe | +0.037 |
ot | +0.035 |
Nem | +0.034 |
le | +0.034 |
Twe | +0.033 |
Neg logit contributions | |
outage | -0.027 |
ouncing | -0.026 |
ying | -0.025 |
hole | -0.025 |
rum | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ot | +0.004 |
Twe | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.005 |
hole | -0.005 |
ouncing | -0.005 |
ying | -0.005 |
lessly | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
outage | +0.013 |
ying | +0.012 |
hole | +0.012 |
ouncing | +0.012 |
rum | +0.011 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.015 |
Nem | -0.015 |
Twe | -0.014 |
le | -0.014 |
Token | Whe |
Token ID | 10842 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
ying | -0.005 |
hole | -0.005 |
ows | -0.005 |
Token | e |
Token ID | 68 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
le | +0.002 |
Nem | +0.002 |
Twe | +0.002 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
hole | -0.004 |
ma | -0.004 |
click | -0.004 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Twe | +0.158 |
ot | +0.154 |
Nem | +0.148 |
le | +0.146 |
Twe | +0.146 |
Neg logit contributions | |
outage | -0.113 |
ouncing | -0.109 |
hole | -0.107 |
ying | -0.105 |
ma | -0.101 |
Token | she |
Token ID | 673 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.008 |
Nem | +0.008 |
le | +0.008 |
Twe | +0.008 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.008 |
rum | -0.007 |
Token | says |
Token ID | 1139 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
outage | +0.019 |
ouncing | +0.018 |
ying | +0.018 |
hole | +0.018 |
rum | +0.017 |
Neg logit contributions | |
Twe | -0.020 |
ot | -0.019 |
Nem | -0.019 |
le | -0.018 |
Twe | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
outage | +0.000 |
ouncing | +0.000 |
ying | +0.000 |
hole | +0.000 |
ows | +0.000 |
Neg logit contributions | |
ot | -0.000 |
Twe | -0.000 |
Twe | -0.000 |
Nem | -0.000 |
le | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
outage | +0.010 |
ying | +0.010 |
hole | +0.010 |
ouncing | +0.010 |
rum | +0.009 |
Neg logit contributions | |
Twe | -0.011 |
Nem | -0.010 |
ot | -0.010 |
le | -0.009 |
Twe | -0.009 |
Token | how |
Token ID | 703 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
outage | +0.010 |
ouncing | +0.010 |
ying | +0.010 |
hole | +0.009 |
ma | +0.009 |
Neg logit contributions | |
Twe | -0.010 |
ot | -0.010 |
Twe | -0.010 |
Nem | -0.010 |
le | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.010 |
Twe | +0.010 |
Nem | +0.009 |
le | +0.009 |
Neg logit contributions | |
outage | -0.011 |
ouncing | -0.011 |
ying | -0.010 |
lessly | -0.010 |
hole | -0.010 |
Token | polish |
Token ID | 25245 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
outage | +0.014 |
ouncing | +0.013 |
hole | +0.013 |
ying | +0.013 |
ma | +0.012 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.013 |
Nem | -0.012 |
le | -0.012 |
Twe | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
outage | +0.014 |
ouncing | +0.013 |
hole | +0.013 |
ying | +0.013 |
ma | +0.013 |
Neg logit contributions | |
Twe | -0.011 |
ot | -0.011 |
Nem | -0.010 |
le | -0.010 |
Twe | -0.010 |
Token | tw |
Token ID | 665 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
outage | +0.007 |
ouncing | +0.007 |
ying | +0.007 |
rum | +0.007 |
hole | +0.007 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
le | -0.004 |
jew | -0.004 |
Twe | -0.004 |
Token | igs |
Token ID | 9235 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.008 |
hole | +0.008 |
ying | +0.008 |
ma | +0.008 |
Neg logit contributions | |
Twe | -0.018 |
ot | -0.017 |
le | -0.017 |
Twe | -0.017 |
Nem | -0.017 |
Token | until |
Token ID | 1566 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
outage | +0.091 |
ouncing | +0.089 |
hole | +0.084 |
Deal | +0.084 |
rum | +0.084 |
Neg logit contributions | |
Twe | -0.080 |
ot | -0.079 |
Nem | -0.077 |
le | -0.073 |
Bub | -0.070 |
Token | they |
Token ID | 484 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Twe | +0.017 |
Twe | +0.017 |
ot | +0.016 |
le | +0.015 |
Nem | +0.015 |
Neg logit contributions | |
outage | -0.016 |
ying | -0.016 |
ouncing | -0.015 |
hole | -0.015 |
ma | -0.015 |
Token | spark |
Token ID | 9009 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.013 |
Twe | +0.013 |
le | +0.012 |
Nem | +0.012 |
Neg logit contributions | |
outage | -0.014 |
hole | -0.014 |
ying | -0.014 |
ouncing | -0.013 |
lessly | -0.013 |
Token | led |
Token ID | 992 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Twe | +0.026 |
Twe | +0.025 |
ot | +0.024 |
Nem | +0.023 |
le | +0.023 |
Neg logit contributions | |
ying | -0.022 |
ows | -0.021 |
ouncing | -0.021 |
lessly | -0.021 |
hole | -0.021 |
Token | like |
Token ID | 588 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Twe | +0.046 |
ot | +0.045 |
Twe | +0.044 |
le | +0.042 |
Nem | +0.042 |
Neg logit contributions | |
outage | -0.038 |
hole | -0.037 |
ouncing | -0.037 |
ying | -0.036 |
lessly | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
outage | +0.000 |
ouncing | +0.000 |
hole | +0.000 |
ying | +0.000 |
ma | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
Nem | -0.000 |
ot | -0.000 |
Twe | -0.000 |
le | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
hole | +0.001 |
ying | +0.001 |
ma | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Twe | -0.001 |
Nem | -0.001 |
le | -0.001 |
Token | twins |
Token ID | 20345 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Twe | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
ot | +0.004 |
jew | +0.004 |
Neg logit contributions | |
outage | -0.004 |
ma | -0.004 |
ouncing | -0.003 |
hole | -0.003 |
click | -0.003 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.009 |
Nem | +0.008 |
le | +0.008 |
Twe | +0.008 |
Neg logit contributions | |
outage | -0.014 |
ouncing | -0.013 |
ying | -0.013 |
hole | -0.013 |
rum | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
le | +0.004 |
Twe | +0.004 |
Neg logit contributions | |
outage | -0.003 |
ouncing | -0.003 |
hole | -0.003 |
ying | -0.003 |
ma | -0.003 |
Token | amaz |
Token ID | 40642 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
ying | +0.001 |
hole | +0.001 |
ows | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Nem | -0.001 |
le | -0.001 |
Twe | -0.001 |
Token | ement |
Token ID | 972 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
outage | +0.051 |
ying | +0.051 |
hole | +0.049 |
ouncing | +0.048 |
lessly | +0.046 |
Neg logit contributions | |
Twe | -0.090 |
ot | -0.088 |
Nem | -0.084 |
le | -0.084 |
Twe | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
hole | +0.009 |
ying | +0.009 |
ma | +0.009 |
Neg logit contributions | |
Twe | -0.008 |
ot | -0.007 |
Nem | -0.007 |
le | -0.007 |
Twe | -0.007 |
Token | What |
Token ID | 1867 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Nem | +0.002 |
le | +0.002 |
Twe | +0.002 |
Neg logit contributions | |
outage | -0.001 |
ying | -0.001 |
ouncing | -0.001 |
hole | -0.001 |
rum | -0.001 |
Token | an |
Token ID | 281 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.006 |
Twe | +0.006 |
Nem | +0.006 |
le | +0.006 |
Neg logit contributions | |
outage | -0.010 |
ouncing | -0.009 |
hole | -0.009 |
ying | -0.009 |
ma | -0.009 |
Token | exciting |
Token ID | 7895 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.006 |
Nem | +0.006 |
Twe | +0.006 |
le | +0.006 |
Neg logit contributions | |
outage | -0.007 |
ying | -0.006 |
hole | -0.006 |
ouncing | -0.006 |
rum | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ot | +0.007 |
Twe | +0.007 |
Nem | +0.006 |
Twe | +0.006 |
le | +0.006 |
Neg logit contributions | |
outage | -0.011 |
hole | -0.010 |
ouncing | -0.010 |
about | -0.010 |
ma | -0.010 |
Token | time |
Token ID | 640 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Twe | +0.025 |
ot | +0.025 |
Nem | +0.024 |
Twe | +0.023 |
le | +0.023 |
Neg logit contributions | |
outage | -0.023 |
ouncing | -0.022 |
hole | -0.021 |
ying | -0.021 |
ma | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
ot | +0.004 |
Twe | +0.004 |
Twe | +0.004 |
le | +0.004 |
Nem | +0.004 |
Neg logit contributions | |
ouncing | -0.003 |
outage | -0.003 |
ying | -0.003 |
Today | -0.003 |
hole | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Nem | +0.002 |
le | +0.002 |
Bub | +0.002 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
hole | -0.002 |
rum | -0.002 |
ying | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
outage | +0.000 |
hole | +0.000 |
ma | +0.000 |
Today | +0.000 |
about | +0.000 |
Neg logit contributions | |
ot | -0.000 |
Twe | -0.000 |
Twe | -0.000 |
Nem | -0.000 |
jew | -0.000 |
Token | small |
Token ID | 1402 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
hole | +0.001 |
ma | +0.001 |
Today | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
Nem | -0.001 |
Twe | -0.001 |
le | -0.001 |
Token | house |
Token ID | 2156 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
outage | +0.068 |
ouncing | +0.065 |
hole | +0.064 |
ying | +0.063 |
ma | +0.062 |
Neg logit contributions | |
Twe | -0.078 |
ot | -0.075 |
Nem | -0.073 |
Twe | -0.072 |
le | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
ying | +0.005 |
hole | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
Nem | -0.006 |
Twe | -0.006 |
le | -0.005 |
Token | there |
Token ID | 612 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.011 |
Nem | +0.010 |
le | +0.010 |
Twe | +0.010 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.007 |
rum | -0.007 |
Token | lived |
Token ID | 5615 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
outage | +0.025 |
ouncing | +0.025 |
ying | +0.025 |
hole | +0.025 |
Today | +0.024 |
Neg logit contributions | |
Twe | -0.014 |
ot | -0.014 |
Twe | -0.013 |
Nem | -0.013 |
le | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ot | +0.022 |
Twe | +0.021 |
Twe | +0.021 |
arom | +0.020 |
Nem | +0.020 |
Neg logit contributions | |
about | -0.021 |
ma | -0.021 |
aking | -0.021 |
apping | -0.020 |
Today | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
ot | +0.008 |
Twe | +0.008 |
Nem | +0.007 |
Twe | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.012 |
hole | -0.012 |
ouncing | -0.012 |
Today | -0.012 |
about | -0.012 |
Token | time |
Token ID | 640 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Twe | +0.027 |
ot | +0.026 |
Nem | +0.025 |
Twe | +0.024 |
le | +0.024 |
Neg logit contributions | |
outage | -0.025 |
ouncing | -0.024 |
hole | -0.024 |
ying | -0.023 |
ma | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
ying | -0.004 |
hole | -0.003 |
Today | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.002 |
hole | +0.002 |
rum | +0.002 |
ems | +0.002 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Bub | -0.002 |
Token | an |
Token ID | 281 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
outage | +0.006 |
hole | +0.006 |
ma | +0.006 |
ouncing | +0.006 |
Today | +0.006 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Twe | -0.004 |
Nem | -0.004 |
le | -0.003 |
Token | ordinary |
Token ID | 8850 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
outage | +0.050 |
ouncing | +0.050 |
hole | +0.047 |
ows | +0.047 |
ying | +0.046 |
Neg logit contributions | |
Twe | -0.037 |
ot | -0.037 |
Nem | -0.034 |
le | -0.034 |
Twe | -0.032 |
Token | little |
Token ID | 1310 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
outage | +0.063 |
ouncing | +0.060 |
hole | +0.059 |
Today | +0.059 |
ma | +0.058 |
Neg logit contributions | |
Twe | -0.082 |
ot | -0.078 |
Twe | -0.077 |
Nem | -0.077 |
le | -0.073 |
Token | town |
Token ID | 3240 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
outage | +0.043 |
ouncing | +0.042 |
hole | +0.041 |
ying | +0.040 |
ma | +0.039 |
Neg logit contributions | |
Twe | -0.043 |
ot | -0.041 |
Nem | -0.039 |
le | -0.039 |
Twe | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Nem | +0.011 |
Twe | +0.011 |
le | +0.011 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.009 |
hole | -0.009 |
ying | -0.009 |
ma | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.010 |
Nem | +0.010 |
le | +0.009 |
Twe | +0.009 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.007 |
ying | -0.007 |
rum | -0.007 |
Token | lived |
Token ID | 5615 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
outage | +0.029 |
ouncing | +0.028 |
hole | +0.028 |
ying | +0.027 |
ma | +0.027 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.013 |
Nem | -0.012 |
Twe | -0.011 |
le | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
outage | +0.026 |
ouncing | +0.025 |
hole | +0.024 |
ows | +0.024 |
rum | +0.024 |
Neg logit contributions | |
Twe | -0.017 |
Nem | -0.016 |
ot | -0.016 |
le | -0.015 |
Bub | -0.014 |
Token | box |
Token ID | 3091 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
Twe | +0.007 |
Twe | +0.007 |
ot | +0.006 |
Nem | +0.006 |
jew | +0.006 |
Neg logit contributions | |
outage | -0.007 |
hole | -0.007 |
ma | -0.007 |
ouncing | -0.006 |
ying | -0.006 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Twe | +0.008 |
ot | +0.007 |
Nem | +0.007 |
Twe | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.013 |
hole | -0.013 |
ouncing | -0.012 |
ying | -0.012 |
ows | -0.012 |
Token | 't |
Token ID | 470 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
outage | +0.013 |
hole | +0.012 |
ying | +0.012 |
ouncing | +0.012 |
lessly | +0.012 |
Neg logit contributions | |
ot | -0.016 |
Twe | -0.015 |
jew | -0.015 |
Nem | -0.015 |
le | -0.015 |
Token | bud |
Token ID | 3600 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
ouncing | +0.015 |
outage | +0.014 |
ying | +0.013 |
hole | +0.013 |
itates | +0.013 |
Neg logit contributions | |
Twe | -0.011 |
ot | -0.010 |
Nem | -0.010 |
le | -0.009 |
se | -0.009 |
Token | ge |
Token ID | 469 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
outage | +0.021 |
ouncing | +0.020 |
ying | +0.019 |
hole | +0.019 |
ma | +0.019 |
Neg logit contributions | |
Twe | -0.031 |
ot | -0.030 |
Nem | -0.029 |
le | -0.029 |
Twe | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
outage | +0.084 |
hole | +0.082 |
ouncing | +0.081 |
ying | +0.081 |
rum | +0.078 |
Neg logit contributions | |
Twe | -0.054 |
ot | -0.052 |
Twe | -0.049 |
Nem | -0.048 |
le | -0.047 |
Token | Just |
Token ID | 2329 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
outage | +0.000 |
ouncing | +0.000 |
ying | +0.000 |
hole | +0.000 |
rum | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
Nem | -0.000 |
ot | -0.000 |
le | -0.000 |
Twe | -0.000 |
Token | when |
Token ID | 618 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Nem | +0.011 |
le | +0.010 |
Bub | +0.010 |
Neg logit contributions | |
outage | -0.015 |
ouncing | -0.014 |
ying | -0.014 |
hole | -0.014 |
rum | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
outage | +0.025 |
ouncing | +0.023 |
hole | +0.023 |
ma | +0.023 |
ying | +0.023 |
Neg logit contributions | |
ot | -0.023 |
Twe | -0.023 |
Twe | -0.022 |
le | -0.021 |
Nem | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Twe | +0.003 |
Nem | +0.003 |
le | +0.003 |
Neg logit contributions | |
hole | -0.004 |
outage | -0.003 |
ma | -0.003 |
ying | -0.003 |
ouncing | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
ot | +0.018 |
Nem | +0.018 |
Twe | +0.017 |
jew | +0.017 |
le | +0.016 |
Neg logit contributions | |
outage | -0.015 |
ouncing | -0.014 |
ma | -0.014 |
hole | -0.014 |
Today | -0.014 |
Token | look |
Token ID | 804 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
outage | +0.002 |
Today | +0.002 |
hole | +0.002 |
click | +0.002 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
Twe | -0.003 |
le | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Twe | +0.038 |
ot | +0.036 |
Nem | +0.036 |
le | +0.035 |
Twe | +0.033 |
Neg logit contributions | |
outage | -0.035 |
ouncing | -0.033 |
hole | -0.032 |
ying | -0.031 |
rum | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
ot | +0.005 |
Twe | +0.005 |
Twe | +0.005 |
Nem | +0.005 |
le | +0.005 |
Neg logit contributions | |
hole | -0.005 |
outage | -0.005 |
ying | -0.005 |
ouncing | -0.005 |
ma | -0.005 |
Token | ? |
Token ID | 30 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
outage | +0.001 |
rum | +0.001 |
ouncing | +0.001 |
irk | +0.001 |
lessly | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
ot | -0.001 |
le | -0.001 |
Nem | -0.001 |
Bub | -0.001 |
Token | â |
Token ID | 22940 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.011 |
Twe | +0.011 |
Nem | +0.011 |
le | +0.011 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.008 |
ying | -0.008 |
hole | -0.008 |
rum | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
outage | +0.032 |
ouncing | +0.030 |
hole | +0.029 |
ying | +0.029 |
lessly | +0.029 |
Neg logit contributions | |
Twe | -0.039 |
Twe | -0.036 |
ot | -0.036 |
le | -0.035 |
Nem | -0.035 |
Token | Su |
Token ID | 1778 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Twe | +0.048 |
Twe | +0.043 |
le | +0.042 |
ot | +0.042 |
Nem | +0.041 |
Neg logit contributions | |
outage | -0.048 |
ying | -0.046 |
lessly | -0.045 |
rum | -0.043 |
hole | -0.043 |
Token | zy |
Token ID | 7357 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
hole | +0.001 |
ying | +0.001 |
ma | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
ot | -0.000 |
Nem | -0.000 |
le | -0.000 |
Twe | -0.000 |
Token | asked |
Token ID | 1965 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
Twe | +0.014 |
ot | +0.013 |
Nem | +0.012 |
le | +0.012 |
Twe | +0.012 |
Neg logit contributions | |
outage | -0.017 |
ouncing | -0.017 |
hole | -0.016 |
ying | -0.016 |
ma | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ot | +0.002 |
Twe | +0.002 |
Twe | +0.002 |
le | +0.002 |
Nem | +0.002 |
Neg logit contributions | |
ying | -0.002 |
ouncing | -0.002 |
outage | -0.002 |
ma | -0.002 |
hole | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.010 |
le | +0.010 |
Nem | +0.009 |
Twe | +0.009 |
Neg logit contributions | |
outage | -0.010 |
ouncing | -0.010 |
ying | -0.010 |
hole | -0.010 |
ems | -0.010 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
outage | +0.031 |
hole | +0.030 |
ems | +0.028 |
ying | +0.028 |
ouncing | +0.028 |
Neg logit contributions | |
Twe | -0.036 |
ot | -0.033 |
le | -0.033 |
Nem | -0.033 |
Twe | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Nem | +0.001 |
le | +0.001 |
Twe | +0.001 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
hole | -0.001 |
ying | -0.001 |
ma | -0.001 |
Token | find |
Token ID | 1064 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.013 |
Nem | +0.013 |
Twe | +0.012 |
le | +0.012 |
Neg logit contributions | |
ouncing | -0.010 |
outage | -0.010 |
hole | -0.010 |
ying | -0.010 |
ows | -0.009 |
Token | that |
Token ID | 326 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Twe | +0.014 |
Twe | +0.013 |
ot | +0.013 |
le | +0.012 |
jew | +0.012 |
Neg logit contributions | |
about | -0.013 |
ying | -0.013 |
outage | -0.013 |
lessly | -0.012 |
hole | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
outage | +0.009 |
ouncing | +0.009 |
hole | +0.009 |
ying | +0.009 |
rum | +0.009 |
Neg logit contributions | |
Twe | -0.008 |
ot | -0.008 |
Nem | -0.007 |
le | -0.007 |
Twe | -0.007 |
Token | kitten |
Token ID | 42143 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.006 |
ouncing | -0.006 |
hole | -0.006 |
ying | -0.005 |
ma | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.008 |
Twe | +0.008 |
Nem | +0.008 |
le | +0.008 |
Neg logit contributions | |
outage | -0.013 |
ouncing | -0.012 |
hole | -0.012 |
ying | -0.012 |
ma | -0.012 |
Token | un |
Token ID | 555 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.012 |
Nem | +0.011 |
le | +0.011 |
Twe | +0.011 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.009 |
hole | -0.009 |
ying | -0.008 |
ma | -0.008 |
Token | har |
Token ID | 9869 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
Twe | +0.028 |
ot | +0.028 |
Nem | +0.027 |
le | +0.026 |
Bub | +0.025 |
Neg logit contributions | |
ouncing | -0.026 |
hole | -0.026 |
outage | -0.026 |
aking | -0.025 |
ying | -0.025 |
Token | med |
Token ID | 1150 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Twe | +0.022 |
Nem | +0.022 |
ot | +0.021 |
Twe | +0.020 |
Bub | +0.020 |
Neg logit contributions | |
hole | -0.018 |
ouncing | -0.017 |
outage | -0.016 |
ying | -0.016 |
rum | -0.015 |
Token | deaf |
Token ID | 21815 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
le | +0.003 |
Nem | +0.003 |
Twe | +0.003 |
Neg logit contributions | |
outage | -0.003 |
ouncing | -0.003 |
hole | -0.003 |
ying | -0.003 |
rum | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
outage | +0.008 |
ouncing | +0.007 |
ying | +0.007 |
hole | +0.007 |
ma | +0.007 |
Neg logit contributions | |
Twe | -0.006 |
ot | -0.006 |
le | -0.005 |
Nem | -0.005 |
jew | -0.005 |
Token | couldn |
Token ID | 3521 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
outage | +0.015 |
ouncing | +0.015 |
hole | +0.015 |
ying | +0.015 |
rum | +0.014 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.015 |
Nem | -0.014 |
le | -0.014 |
Twe | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ot | +0.018 |
Twe | +0.018 |
Nem | +0.017 |
jew | +0.017 |
Twe | +0.017 |
Neg logit contributions | |
outage | -0.016 |
ouncing | -0.015 |
Today | -0.015 |
ying | -0.015 |
hole | -0.015 |
Token | hear |
Token ID | 3285 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
outage | +0.005 |
hole | +0.004 |
ying | +0.004 |
ouncing | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
Nem | -0.007 |
le | -0.006 |
Twe | -0.006 |
Token | very |
Token ID | 845 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
hole | +0.005 |
ying | +0.005 |
ma | +0.005 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.003 |
Twe | -0.003 |
le | -0.003 |
Token | well |
Token ID | 880 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ouncing | +0.001 |
outage | +0.001 |
hole | +0.001 |
ying | +0.001 |
rum | +0.001 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.001 |
le | -0.001 |
Nem | -0.001 |
se | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
Twe | +0.025 |
ot | +0.024 |
le | +0.023 |
Nem | +0.022 |
jew | +0.019 |
Neg logit contributions | |
outage | -0.052 |
ouncing | -0.052 |
hole | -0.051 |
ma | -0.050 |
Deal | -0.050 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
outage | +0.002 |
ouncing | +0.002 |
ying | +0.002 |
hole | +0.002 |
rum | +0.002 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
Twe | -0.003 |
le | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
hole | +0.004 |
ying | +0.004 |
rum | +0.003 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Twe | -0.002 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ouncing | +0.006 |
outage | +0.006 |
hole | +0.006 |
ying | +0.006 |
ems | +0.005 |
Neg logit contributions | |
Twe | -0.006 |
le | -0.006 |
ot | -0.006 |
Nem | -0.005 |
jew | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Twe | +0.004 |
Nem | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.005 |
hole | -0.005 |
ying | -0.005 |
ma | -0.005 |
Token | find |
Token ID | 1064 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
outage | +0.010 |
ouncing | +0.010 |
hole | +0.010 |
ying | +0.009 |
ma | +0.009 |
Neg logit contributions | |
Twe | -0.009 |
ot | -0.009 |
Nem | -0.009 |
Twe | -0.009 |
le | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Twe | +0.011 |
Twe | +0.011 |
ot | +0.011 |
le | +0.010 |
Nem | +0.010 |
Neg logit contributions | |
outage | -0.012 |
hole | -0.011 |
about | -0.011 |
ying | -0.011 |
lessly | -0.011 |
Token | chocolate |
Token ID | 11311 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.010 |
le | +0.010 |
Nem | +0.010 |
Twe | +0.010 |
Neg logit contributions | |
ouncing | -0.013 |
outage | -0.013 |
ying | -0.013 |
hole | -0.012 |
rum | -0.012 |
Token | bar |
Token ID | 2318 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
Twe | +0.047 |
ot | +0.046 |
Nem | +0.044 |
le | +0.043 |
Twe | +0.043 |
Neg logit contributions | |
outage | -0.056 |
ouncing | -0.054 |
hole | -0.053 |
ying | -0.053 |
ma | -0.051 |
Token | waiting |
Token ID | 4953 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
Twe | +0.025 |
ot | +0.025 |
le | +0.024 |
Nem | +0.024 |
jew | +0.023 |
Neg logit contributions | |
ouncing | -0.029 |
outage | -0.029 |
ying | -0.028 |
hole | -0.027 |
ma | -0.027 |
Token | for |
Token ID | 329 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
outage | +0.002 |
ouncing | +0.002 |
hole | +0.002 |
ying | +0.002 |
rum | +0.002 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Twe | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
ma | +0.004 |
about | +0.004 |
rum | +0.004 |
Today | +0.003 |
ying | +0.003 |
Neg logit contributions | |
ot | -0.003 |
Twe | -0.003 |
Twe | -0.003 |
le | -0.003 |
se | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.010 |
Nem | +0.010 |
le | +0.010 |
Twe | +0.010 |
Neg logit contributions | |
outage | -0.014 |
ouncing | -0.014 |
hole | -0.014 |
ying | -0.013 |
ma | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.009 |
Nem | +0.009 |
Twe | +0.009 |
le | +0.009 |
Neg logit contributions | |
outage | -0.007 |
ouncing | -0.007 |
ying | -0.007 |
hole | -0.007 |
rum | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
outage | +0.000 |
ouncing | +0.000 |
hole | +0.000 |
ying | +0.000 |
ma | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
ot | -0.000 |
Nem | -0.000 |
Twe | -0.000 |
le | -0.000 |
Token | old |
Token ID | 1468 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
outage | +0.013 |
ouncing | +0.013 |
hole | +0.013 |
ying | +0.013 |
ma | +0.012 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.012 |
Nem | -0.012 |
Twe | -0.012 |
le | -0.011 |
Token | scale |
Token ID | 5046 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
outage | +0.007 |
ouncing | +0.007 |
hole | +0.007 |
ying | +0.007 |
rum | +0.007 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.007 |
le | -0.006 |
Nem | -0.006 |
Twe | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Nem | +0.001 |
Twe | +0.001 |
le | +0.001 |
Neg logit contributions | |
outage | -0.002 |
hole | -0.002 |
ouncing | -0.002 |
ying | -0.002 |
ma | -0.002 |
Token | It |
Token ID | 632 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
ying | +0.003 |
hole | +0.003 |
rum | +0.003 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
Twe | -0.004 |
le | -0.004 |
Token | weighed |
Token ID | 20261 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Twe | +0.033 |
ot | +0.032 |
Nem | +0.031 |
Twe | +0.031 |
jew | +0.029 |
Neg logit contributions | |
outage | -0.044 |
hole | -0.042 |
ouncing | -0.040 |
about | -0.040 |
lessly | -0.040 |
Token | things |
Token ID | 1243 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
outage | +0.025 |
ouncing | +0.024 |
ying | +0.023 |
hole | +0.023 |
ma | +0.023 |
Neg logit contributions | |
Twe | -0.021 |
ot | -0.020 |
Nem | -0.019 |
le | -0.019 |
Twe | -0.019 |
Token | from |
Token ID | 422 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
ouncing | +0.042 |
outage | +0.041 |
rum | +0.039 |
ying | +0.039 |
Deal | +0.039 |
Neg logit contributions | |
Twe | -0.036 |
ot | -0.034 |
Nem | -0.033 |
le | -0.032 |
Twe | -0.030 |
Token | near |
Token ID | 1474 |
Feature activation | -5.20e-04 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Nem | +0.002 |
Twe | +0.002 |
le | +0.002 |
Neg logit contributions | |
outage | -0.003 |
ouncing | -0.002 |
hole | -0.002 |
ying | -0.002 |
ma | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Twe | +0.000 |
ot | +0.000 |
Nem | +0.000 |
le | +0.000 |
Twe | +0.000 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
ying | -0.000 |
hole | -0.000 |
ma | -0.000 |
Token | far |
Token ID | 1290 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
outage | +0.016 |
ouncing | +0.015 |
hole | +0.015 |
ying | +0.015 |
rum | +0.014 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.012 |
Nem | -0.012 |
le | -0.011 |
Twe | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
outage | +0.011 |
ouncing | +0.011 |
Deal | +0.010 |
ying | +0.010 |
ma | +0.010 |
Neg logit contributions | |
Twe | -0.010 |
ot | -0.009 |
Nem | -0.009 |
le | -0.009 |
Twe | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
outage | +0.031 |
hole | +0.031 |
ying | +0.030 |
about | +0.030 |
ouncing | +0.029 |
Neg logit contributions | |
ot | -0.026 |
Twe | -0.026 |
Twe | -0.025 |
le | -0.024 |
Nem | -0.023 |
Token | forest |
Token ID | 8222 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ot | +0.007 |
Twe | +0.007 |
le | +0.007 |
Nem | +0.007 |
jew | +0.007 |
Neg logit contributions | |
outage | -0.010 |
ouncing | -0.010 |
rum | -0.010 |
hole | -0.010 |
ying | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
outage | +0.018 |
ouncing | +0.017 |
hole | +0.017 |
ying | +0.017 |
ows | +0.017 |
Neg logit contributions | |
Twe | -0.011 |
ot | -0.011 |
Nem | -0.010 |
Twe | -0.010 |
le | -0.010 |
Token | As |
Token ID | 1081 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Twe | +0.011 |
Nem | +0.010 |
ot | +0.010 |
le | +0.010 |
Twe | +0.009 |
Neg logit contributions | |
outage | -0.011 |
ying | -0.011 |
ouncing | -0.010 |
hole | -0.010 |
rum | -0.010 |
Token | they |
Token ID | 484 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Twe | +0.003 |
le | +0.003 |
Nem | +0.003 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.003 |
hole | -0.003 |
ying | -0.003 |
ma | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
Twe | +0.028 |
Twe | +0.026 |
ot | +0.026 |
Nem | +0.024 |
le | +0.023 |
Neg logit contributions | |
hole | -0.038 |
outage | -0.037 |
ouncing | -0.037 |
ying | -0.037 |
ma | -0.036 |
Token | walking |
Token ID | 6155 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
Twe | +0.021 |
le | +0.021 |
Nem | +0.020 |
ot | +0.020 |
pl | +0.018 |
Neg logit contributions | |
outage | -0.037 |
ouncing | -0.035 |
hole | -0.034 |
rum | -0.034 |
ying | -0.033 |
Token | through |
Token ID | 832 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.006 |
Nem | +0.006 |
Bub | +0.005 |
le | +0.005 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
rum | -0.008 |
Deal | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Twe | +0.028 |
Twe | +0.028 |
ot | +0.027 |
Nem | +0.026 |
le | +0.025 |
Neg logit contributions | |
outage | -0.030 |
hole | -0.030 |
ma | -0.028 |
Today | -0.028 |
ying | -0.028 |
Token | woods |
Token ID | 16479 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.006 |
Nem | +0.005 |
le | +0.005 |
Twe | +0.005 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.008 |
ying | -0.008 |
hole | -0.008 |
rum | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
outage | +0.022 |
ouncing | +0.022 |
hole | +0.021 |
ying | +0.021 |
rum | +0.020 |
Neg logit contributions | |
Twe | -0.020 |
ot | -0.019 |
Nem | -0.019 |
le | -0.018 |
Twe | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
outage | +0.001 |
ouncing | +0.001 |
ying | +0.001 |
hole | +0.001 |
rum | +0.001 |
Neg logit contributions | |
Twe | -0.001 |
Nem | -0.001 |
ot | -0.001 |
le | -0.001 |
Bub | -0.001 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.009 |
Nem | +0.009 |
Twe | +0.009 |
le | +0.009 |
Neg logit contributions | |
outage | -0.015 |
ouncing | -0.014 |
hole | -0.014 |
ying | -0.014 |
ma | -0.014 |
Token | faster |
Token ID | 5443 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
rum | +0.003 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
le | -0.004 |
Bub | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
outage | +0.027 |
ouncing | +0.025 |
Deal | +0.024 |
ying | +0.024 |
ma | +0.024 |
Neg logit contributions | |
Twe | -0.023 |
le | -0.022 |
ot | -0.022 |
Nem | -0.021 |
se | -0.021 |
Token | faster |
Token ID | 5443 |
Feature activation | +9.06e-02 |
Pos logit contributions | |
Twe | +0.032 |
ot | +0.031 |
Nem | +0.030 |
le | +0.030 |
Twe | +0.029 |
Neg logit contributions | |
outage | -0.020 |
ouncing | -0.019 |
ying | -0.019 |
hole | -0.019 |
rum | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
ying | +0.003 |
hole | +0.003 |
Deal | +0.003 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
le | -0.003 |
Nem | -0.003 |
jew | -0.002 |
Token | felt |
Token ID | 2936 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Twe | +0.043 |
ot | +0.041 |
Nem | +0.041 |
le | +0.040 |
Twe | +0.039 |
Neg logit contributions | |
outage | -0.026 |
ouncing | -0.025 |
ying | -0.024 |
hole | -0.024 |
rum | -0.023 |
Token | very |
Token ID | 845 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
Twe | +0.019 |
ot | +0.019 |
Twe | +0.018 |
Nem | +0.018 |
le | +0.018 |
Neg logit contributions | |
outage | -0.018 |
ouncing | -0.018 |
hole | -0.017 |
ying | -0.017 |
lessly | -0.017 |
Token | powerful |
Token ID | 3665 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Twe | +0.032 |
ot | +0.031 |
Nem | +0.030 |
le | +0.029 |
Twe | +0.029 |
Neg logit contributions | |
outage | -0.024 |
ouncing | -0.023 |
hole | -0.022 |
ying | -0.022 |
ma | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
Twe | +0.030 |
ot | +0.029 |
Nem | +0.027 |
le | +0.027 |
jew | +0.025 |
Neg logit contributions | |
outage | -0.054 |
ouncing | -0.053 |
hole | -0.051 |
ying | -0.051 |
ma | -0.050 |
Token | He |
Token ID | 679 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Twe | +0.006 |
Nem | +0.005 |
ot | +0.005 |
le | +0.005 |
Bub | +0.005 |
Neg logit contributions | |
outage | -0.005 |
ouncing | -0.004 |
hole | -0.004 |
ying | -0.004 |
rum | -0.004 |
Token | proud |
Token ID | 6613 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
outage | +0.031 |
hole | +0.031 |
ouncing | +0.030 |
ying | +0.029 |
Today | +0.027 |
Neg logit contributions | |
Twe | -0.050 |
ot | -0.048 |
Nem | -0.047 |
le | -0.046 |
Twe | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
Twe | +0.021 |
ot | +0.020 |
Nem | +0.019 |
le | +0.019 |
Twe | +0.019 |
Neg logit contributions | |
outage | -0.016 |
ouncing | -0.016 |
hole | -0.015 |
ying | -0.015 |
ma | -0.015 |
Token | himself |
Token ID | 2241 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Twe | +0.018 |
ot | +0.018 |
Nem | +0.017 |
Twe | +0.017 |
le | +0.017 |
Neg logit contributions | |
outage | -0.019 |
ouncing | -0.019 |
hole | -0.019 |
ying | -0.018 |
ma | -0.018 |
Token | for |
Token ID | 329 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
Twe | +0.015 |
ot | +0.015 |
le | +0.014 |
Nem | +0.014 |
Bub | +0.013 |
Neg logit contributions | |
outage | -0.020 |
ouncing | -0.019 |
hole | -0.018 |
ying | -0.018 |
itates | -0.018 |
Token | using |
Token ID | 1262 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
outage | +0.020 |
ouncing | +0.020 |
hole | +0.019 |
Today | +0.018 |
ows | +0.018 |
Neg logit contributions | |
Twe | -0.020 |
ot | -0.019 |
Nem | -0.019 |
le | -0.018 |
jew | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.005 |
ying | +0.004 |
hole | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Nem | -0.003 |
le | -0.003 |
Twe | -0.002 |
Token | sword |
Token ID | 8429 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
Twe | +0.030 |
ot | +0.030 |
Nem | +0.029 |
le | +0.028 |
Twe | +0.028 |
Neg logit contributions | |
outage | -0.020 |
ouncing | -0.020 |
hole | -0.019 |
ying | -0.019 |
ma | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
outage | +0.014 |
ouncing | +0.014 |
ying | +0.014 |
hole | +0.014 |
ma | +0.013 |
Neg logit contributions | |
Twe | -0.009 |
ot | -0.009 |
Nem | -0.008 |
le | -0.008 |
Twe | -0.008 |
Token | From |
Token ID | 3574 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.003 |
ma | +0.003 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
le | -0.004 |
Twe | -0.004 |
Token | then |
Token ID | 788 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
outage | +0.026 |
ouncing | +0.025 |
hole | +0.025 |
ying | +0.024 |
ma | +0.023 |
Neg logit contributions | |
Twe | -0.025 |
ot | -0.024 |
Nem | -0.023 |
le | -0.023 |
Twe | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
le | +0.005 |
Twe | +0.005 |
B | +0.005 |
ot | +0.005 |
B | +0.005 |
Neg logit contributions | |
outage | -0.008 |
ows | -0.007 |
hole | -0.007 |
fuss | -0.007 |
ouncing | -0.007 |
Token | end |
Token ID | 886 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
outage | +0.033 |
ouncing | +0.033 |
ying | +0.032 |
hole | +0.031 |
rum | +0.030 |
Neg logit contributions | |
ot | -0.026 |
Twe | -0.025 |
le | -0.024 |
Nem | -0.024 |
jew | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
outage | +0.018 |
ouncing | +0.018 |
hole | +0.018 |
ying | +0.017 |
rum | +0.017 |
Neg logit contributions | |
Twe | -0.016 |
ot | -0.016 |
Nem | -0.015 |
le | -0.015 |
Twe | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
ouncing | +0.032 |
outage | +0.032 |
ows | +0.031 |
hole | +0.030 |
ying | +0.029 |
Neg logit contributions | |
Twe | -0.019 |
Nem | -0.017 |
ot | -0.017 |
jew | -0.016 |
le | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
outage | +0.007 |
ouncing | +0.006 |
hole | +0.006 |
ying | +0.006 |
ma | +0.006 |
Neg logit contributions | |
Twe | -0.007 |
ot | -0.006 |
Twe | -0.006 |
Nem | -0.006 |
jew | -0.006 |
Token | happy |
Token ID | 3772 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
outage | +0.008 |
ouncing | +0.008 |
hole | +0.008 |
ying | +0.008 |
Today | +0.008 |
Neg logit contributions | |
Twe | -0.008 |
ot | -0.008 |
le | -0.008 |
Nem | -0.008 |
se | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
outage | +0.021 |
ouncing | +0.021 |
hole | +0.021 |
ying | +0.021 |
ows | +0.020 |
Neg logit contributions | |
Twe | -0.012 |
ot | -0.011 |
Nem | -0.011 |
le | -0.011 |
jew | -0.010 |
Token | did |
Token ID | 750 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
Twe | +0.018 |
ot | +0.018 |
Twe | +0.016 |
Nem | +0.016 |
le | +0.016 |
Neg logit contributions | |
outage | -0.014 |
ouncing | -0.014 |
hole | -0.013 |
ying | -0.013 |
lessly | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
Twe | +0.021 |
ot | +0.020 |
le | +0.019 |
Nem | +0.019 |
jew | +0.019 |
Neg logit contributions | |
outage | -0.031 |
ouncing | -0.031 |
hole | -0.030 |
ying | -0.029 |
Today | -0.029 |
Token | The |
Token ID | 383 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
Twe | +0.002 |
Nem | +0.002 |
Twe | +0.002 |
ot | +0.002 |
le | +0.002 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
ying | -0.002 |
ems | -0.002 |
hole | -0.002 |
Token | sunshine |
Token ID | 34488 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
outage | +0.000 |
ouncing | +0.000 |
hole | +0.000 |
ying | +0.000 |
ma | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
ot | -0.000 |
Nem | -0.000 |
le | -0.000 |
Twe | -0.000 |
Token | felt |
Token ID | 2936 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.009 |
Nem | +0.008 |
Twe | +0.008 |
le | +0.008 |
Neg logit contributions | |
outage | -0.020 |
ouncing | -0.020 |
hole | -0.019 |
ying | -0.019 |
ma | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.011 |
Nem | +0.010 |
le | +0.010 |
se | +0.009 |
Neg logit contributions | |
hole | -0.011 |
ouncing | -0.011 |
outage | -0.011 |
ying | -0.011 |
Today | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Twe | +0.012 |
Twe | +0.011 |
ot | +0.011 |
jew | +0.011 |
Nem | +0.011 |
Neg logit contributions | |
outage | -0.012 |
ouncing | -0.011 |
ying | -0.011 |
lessly | -0.011 |
ows | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.009 |
Nem | +0.009 |
Twe | +0.009 |
le | +0.009 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.007 |
ma | -0.007 |
Token | sm |
Token ID | 895 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
outage | +0.002 |
lessly | +0.002 |
ouncing | +0.002 |
ma | +0.002 |
ying | +0.002 |
Neg logit contributions | |
Twe | -0.003 |
Twe | -0.003 |
ot | -0.003 |
jew | -0.002 |
Nem | -0.002 |
Token | elly |
Token ID | 6148 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Twe | +0.069 |
ot | +0.067 |
Nem | +0.065 |
le | +0.064 |
Twe | +0.064 |
Neg logit contributions | |
outage | -0.034 |
ouncing | -0.032 |
hole | -0.031 |
ying | -0.031 |
ma | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
Twe | +0.028 |
ot | +0.027 |
Nem | +0.025 |
le | +0.025 |
Twe | +0.025 |
Neg logit contributions | |
outage | -0.049 |
ouncing | -0.048 |
hole | -0.047 |
ying | -0.047 |
ma | -0.045 |
Token | One |
Token ID | 1881 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
ot | +0.027 |
Twe | +0.027 |
le | +0.026 |
Twe | +0.025 |
jew | +0.025 |
Neg logit contributions | |
outage | -0.023 |
Today | -0.022 |
ouncing | -0.022 |
hole | -0.022 |
ma | -0.022 |
Token | day |
Token ID | 1110 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
outage | +0.028 |
ouncing | +0.027 |
hole | +0.027 |
ying | +0.026 |
ma | +0.025 |
Neg logit contributions | |
Twe | -0.029 |
ot | -0.028 |
Nem | -0.026 |
Twe | -0.026 |
le | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.013 |
Twe | +0.013 |
jew | +0.012 |
Nem | +0.012 |
Neg logit contributions | |
ouncing | -0.007 |
Today | -0.007 |
outage | -0.007 |
ma | -0.007 |
about | -0.007 |
Token | someone |
Token ID | 2130 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
Twe | +0.003 |
ot | +0.003 |
Twe | +0.003 |
jew | +0.003 |
Nem | +0.003 |
Neg logit contributions | |
ma | -0.004 |
outage | -0.004 |
click | -0.004 |
Today | -0.004 |
hole | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
ying | +0.004 |
hole | +0.003 |
ma | +0.003 |
Neg logit contributions | |
Twe | -0.003 |
ot | -0.003 |
Twe | -0.002 |
Nem | -0.002 |
le | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
Twe | +0.005 |
ot | +0.005 |
Nem | +0.005 |
le | +0.005 |
Twe | +0.004 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.008 |
rum | -0.007 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
outage | +0.021 |
hole | +0.020 |
ouncing | +0.020 |
Deal | +0.020 |
itates | +0.020 |
Neg logit contributions | |
ot | -0.011 |
Twe | -0.011 |
le | -0.010 |
Nem | -0.010 |
se | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
Twe | +0.006 |
Twe | +0.006 |
ot | +0.005 |
Nem | +0.005 |
Bub | +0.005 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
about | -0.004 |
ying | -0.004 |
hole | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
Twe | +0.019 |
ot | +0.019 |
Nem | +0.017 |
le | +0.017 |
Twe | +0.017 |
Neg logit contributions | |
outage | -0.030 |
ouncing | -0.029 |
hole | -0.029 |
ying | -0.028 |
ma | -0.027 |
Token | things |
Token ID | 1243 |
Feature activation | +7.29e-02 |
Pos logit contributions | |
outage | +0.004 |
hole | +0.004 |
ouncing | +0.004 |
ying | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.004 |
ot | -0.004 |
le | -0.004 |
Nem | -0.004 |
Twe | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
outage | +0.003 |
ouncing | +0.003 |
hole | +0.003 |
ying | +0.002 |
ma | +0.002 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Twe | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
ot | +0.102 |
jew | +0.102 |
Twe | +0.098 |
Nem | +0.098 |
Bub | +0.092 |
Neg logit contributions | |
ouncing | -0.131 |
ying | -0.128 |
outage | -0.125 |
lessly | -0.118 |
ows | -0.118 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Twe | +0.017 |
ot | +0.017 |
Twe | +0.016 |
le | +0.016 |
Nem | +0.016 |
Neg logit contributions | |
outage | -0.015 |
ouncing | -0.014 |
hole | -0.014 |
lessly | -0.014 |
ying | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
Twe | +0.013 |
ot | +0.012 |
Nem | +0.012 |
le | +0.012 |
Twe | +0.012 |
Neg logit contributions | |
outage | -0.011 |
ouncing | -0.010 |
hole | -0.010 |
ying | -0.010 |
ma | -0.010 |
Token | jumped |
Token ID | 11687 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
Twe | +0.007 |
ot | +0.006 |
le | +0.006 |
Nem | +0.006 |
Twe | +0.006 |
Neg logit contributions | |
outage | -0.007 |
ying | -0.006 |
rum | -0.006 |
hole | -0.006 |
ouncing | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Nem | +0.001 |
Twe | +0.001 |
le | +0.001 |
Neg logit contributions | |
outage | -0.000 |
ouncing | -0.000 |
hole | -0.000 |
ying | -0.000 |
ma | -0.000 |
Token | play |
Token ID | 711 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
outage | +0.000 |
ouncing | +0.000 |
hole | +0.000 |
ying | +0.000 |
ma | +0.000 |
Neg logit contributions | |
Twe | -0.000 |
ot | -0.000 |
Nem | -0.000 |
Twe | -0.000 |
le | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.011 |
Nem | +0.010 |
le | +0.010 |
Twe | +0.010 |
Neg logit contributions | |
outage | -0.013 |
ouncing | -0.012 |
hole | -0.012 |
ying | -0.012 |
ma | -0.012 |
Token | game |
Token ID | 983 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Twe | +0.042 |
ot | +0.041 |
Nem | +0.040 |
Twe | +0.038 |
jew | +0.037 |
Neg logit contributions | |
outage | -0.032 |
hole | -0.029 |
ouncing | -0.028 |
ma | -0.028 |
click | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
outage | +0.014 |
ouncing | +0.014 |
hole | +0.014 |
ying | +0.014 |
ma | +0.013 |
Neg logit contributions | |
Twe | -0.013 |
ot | -0.013 |
Nem | -0.012 |
Twe | -0.012 |
le | -0.012 |
Token | tug |
Token ID | 27762 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Twe | +0.017 |
ot | +0.017 |
Nem | +0.016 |
le | +0.016 |
Twe | +0.016 |
Neg logit contributions | |
outage | -0.019 |
ouncing | -0.018 |
hole | -0.018 |
ying | -0.018 |
ma | -0.017 |
Token | - |
Token ID | 12 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
Twe | +0.010 |
ot | +0.010 |
le | +0.009 |
Nem | +0.009 |
Twe | +0.009 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.007 |
hole | -0.007 |
ma | -0.007 |
Today | -0.007 |
Token | o |
Token ID | 78 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
ot | +0.140 |
Twe | +0.136 |
Nem | +0.133 |
jew | +0.130 |
Twe | +0.125 |
Neg logit contributions | |
ouncing | -0.060 |
outage | -0.059 |
hole | -0.058 |
ying | -0.058 |
lessly | -0.055 |
Token | - |
Token ID | 12 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Twe | +0.021 |
ot | +0.021 |
le | +0.020 |
Nem | +0.020 |
Twe | +0.019 |
Neg logit contributions | |
outage | -0.022 |
ouncing | -0.021 |
hole | -0.020 |
ying | -0.020 |
ma | -0.020 |
Token | war |
Token ID | 5767 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
ot | +0.137 |
Twe | +0.131 |
Nem | +0.128 |
jew | +0.127 |
Bub | +0.120 |
Neg logit contributions | |
ouncing | -0.059 |
hole | -0.056 |
outage | -0.056 |
lessly | -0.055 |
ying | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Twe | +0.001 |
ot | +0.001 |
Nem | +0.001 |
Twe | +0.001 |
le | +0.001 |
Neg logit contributions | |
outage | -0.001 |
ouncing | -0.001 |
hole | -0.001 |
ying | -0.001 |
ows | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Twe | +0.011 |
ot | +0.011 |
Nem | +0.011 |
Twe | +0.010 |
le | +0.010 |
Neg logit contributions | |
outage | -0.009 |
ouncing | -0.009 |
hole | -0.009 |
ying | -0.009 |
ma | -0.008 |
Token | calm |
Token ID | 9480 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
outage | +0.015 |
ouncing | +0.014 |
ma | +0.013 |
hole | +0.013 |
ying | +0.013 |
Neg logit contributions | |
ot | -0.014 |
Twe | -0.014 |
Nem | -0.013 |
le | -0.013 |
Twe | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Twe | +0.006 |
ot | +0.006 |
Nem | +0.005 |
le | +0.005 |
jew | +0.005 |
Neg logit contributions | |
outage | -0.007 |
ouncing | -0.006 |
ma | -0.006 |
hole | -0.006 |
ying | -0.006 |
Token | listen |
Token ID | 6004 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
Twe | +0.032 |
ot | +0.031 |
le | +0.029 |
Nem | +0.029 |
se | +0.028 |
Neg logit contributions | |
outage | -0.033 |
ouncing | -0.033 |
hole | -0.033 |
ying | -0.033 |
rum | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Twe | +0.025 |
ot | +0.024 |
Nem | +0.023 |
le | +0.022 |
Twe | +0.022 |
Neg logit contributions | |
outage | -0.036 |
ouncing | -0.035 |
hole | -0.034 |
ying | -0.034 |
ma | -0.033 |
Token | grown |
Token ID | 7334 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Twe | +0.009 |
ot | +0.009 |
Nem | +0.008 |
le | +0.008 |
Twe | +0.008 |
Neg logit contributions | |
outage | -0.013 |
ouncing | -0.012 |
hole | -0.012 |
ying | -0.012 |
ma | -0.012 |
Token | - |
Token ID | 12 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
Twe | +0.012 |
ot | +0.012 |
Nem | +0.011 |
Twe | +0.011 |
le | +0.010 |
Neg logit contributions | |
outage | -0.016 |
ying | -0.015 |
ouncing | -0.015 |
hole | -0.015 |
rum | -0.015 |
Token | ups |
Token ID | 4739 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Twe | +0.110 |
ot | +0.109 |
Nem | +0.105 |
jew | +0.102 |
Bub | +0.100 |
Neg logit contributions | |
ouncing | -0.098 |
ying | -0.097 |
outage | -0.093 |
aking | -0.089 |
hole | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
outage | +0.028 |
ouncing | +0.027 |
ma | +0.026 |
hole | +0.026 |
rum | +0.026 |
Neg logit contributions | |
Twe | -0.017 |
ot | -0.017 |
Nem | -0.016 |
le | -0.016 |
jew | -0.014 |
Token | The |
Token ID | 383 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
Twe | +0.008 |
ot | +0.007 |
Nem | +0.007 |
Twe | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.007 |
hole | -0.007 |
ying | -0.007 |
ma | -0.007 |
Token | end |
Token ID | 886 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
Twe | +0.008 |
ot | +0.008 |
Nem | +0.008 |
Twe | +0.007 |
le | +0.007 |
Neg logit contributions | |
outage | -0.008 |
ouncing | -0.008 |
hole | -0.008 |
ying | -0.008 |
ma | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ouncing | +0.004 |
hole | +0.004 |
ying | +0.004 |
ma | +0.004 |
outage | +0.004 |
Neg logit contributions | |
Twe | -0.001 |
le | -0.001 |
ot | -0.001 |
Nem | -0.001 |
Twe | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
outage | +0.004 |
ying | +0.004 |
hole | +0.004 |
rum | +0.004 |
ouncing | +0.004 |
Neg logit contributions | |
Twe | -0.005 |
Nem | -0.004 |
Bub | -0.004 |
ot | -0.004 |
Twe | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ot | +0.007 |
Twe | +0.006 |
Nem | +0.006 |
jew | +0.006 |
Twe | +0.006 |
Neg logit contributions | |
about | -0.005 |
ouncing | -0.004 |
outage | -0.004 |
itates | -0.004 |
has | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
outage | +0.004 |
ouncing | +0.004 |
ying | +0.004 |
about | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.004 |
Twe | -0.004 |
ot | -0.004 |
Nem | -0.004 |
Bub | -0.004 |
Token | play |
Token ID | 711 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
outage | +0.027 |
ma | +0.026 |
Today | +0.026 |
ouncing | +0.025 |
click | +0.025 |
Neg logit contributions | |
Twe | -0.026 |
ot | -0.025 |
Nem | -0.024 |
Twe | -0.024 |
le | -0.022 |
Token | hide |
Token ID | 7808 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Twe | +0.004 |
ot | +0.004 |
Nem | +0.004 |
Twe | +0.004 |
le | +0.004 |
Neg logit contributions | |
outage | -0.004 |
ouncing | -0.004 |
ying | -0.004 |
hole | -0.004 |
ma | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
ying | +0.023 |
ows | +0.023 |
ouncing | +0.023 |
about | +0.022 |
lessly | +0.021 |
Neg logit contributions | |
Twe | -0.034 |
ot | -0.034 |
Nem | -0.033 |
Twe | -0.033 |
Bub | -0.032 |
Token | and |
Token ID | 392 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ot | +0.165 |
Twe | +0.162 |
Nem | +0.162 |
le | +0.152 |
jew | +0.152 |
Neg logit contributions | |
ouncing | -0.024 |
outage | -0.024 |
aking | -0.021 |
ying | -0.019 |
ows | -0.018 |
Token | - |
Token ID | 12 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ouncing | +0.032 |
ying | +0.031 |
ows | +0.030 |
outage | +0.030 |
hole | +0.029 |
Neg logit contributions | |
ot | -0.019 |
Twe | -0.018 |
Nem | -0.018 |
Twe | -0.016 |
Bub | -0.015 |
Token | seek |
Token ID | 36163 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
ot | +0.124 |
Nem | +0.117 |
Twe | +0.116 |
jew | +0.107 |
le | +0.107 |
Neg logit contributions | |
ouncing | -0.095 |
outage | -0.094 |
ows | -0.087 |
ying | -0.087 |
aking | -0.085 |
Token | with |
Token ID | 351 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Twe | +0.022 |
ot | +0.021 |
Nem | +0.020 |
Twe | +0.020 |
le | +0.020 |
Neg logit contributions | |
outage | -0.019 |
ouncing | -0.018 |
ying | -0.018 |
hole | -0.018 |
about | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
pre | +0.055 |
Twe | +0.053 |
ot | +0.053 |
Twe | +0.052 |
Nem | +0.050 |
Neg logit contributions | |
about | -0.031 |
mat | -0.026 |
ma | -0.025 |
Today | -0.025 |
Lisa | -0.025 |
Token | ara |
Token ID | 3301 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
Twe | +0.053 |
ot | +0.052 |
Twe | +0.049 |
Nem | +0.048 |
le | +0.047 |
Neg logit contributions | |
hole | -0.031 |
ouncing | -0.031 |
ying | -0.030 |
ma | -0.030 |
outage | -0.030 |
Token | loves |
Token ID | 10408 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Twe | +0.032 |
ot | +0.031 |
Nem | +0.030 |
Twe | +0.030 |
le | +0.030 |
Neg logit contributions | |
outage | -0.018 |
ouncing | -0.018 |
hole | -0.017 |
ying | -0.017 |
ma | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
Twe | +0.037 |
Twe | +0.035 |
jew | +0.033 |
ot | +0.033 |
Bub | +0.032 |
Neg logit contributions | |
ma | -0.030 |
ying | -0.029 |
ouncing | -0.029 |
about | -0.028 |
outage | -0.028 |
Token | play |
Token ID | 711 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
outage | +0.020 |
ouncing | +0.019 |
Today | +0.019 |
ma | +0.018 |
hole | +0.018 |
Neg logit contributions | |
Twe | -0.018 |
ot | -0.017 |
Twe | -0.017 |
Nem | -0.016 |
le | -0.016 |
Token | dress |
Token ID | 6576 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Twe | +0.013 |
Twe | +0.012 |
ot | +0.012 |
Nem | +0.012 |
le | +0.012 |
Neg logit contributions | |
ying | -0.008 |
about | -0.008 |
ma | -0.007 |
Today | -0.007 |
iving | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
Nem | +0.006 |
Twe | +0.006 |
ot | +0.006 |
Bub | +0.006 |
Twe | +0.006 |
Neg logit contributions | |
ying | -0.009 |
ouncing | -0.009 |
ows | -0.008 |
about | -0.008 |
hole | -0.008 |
Token | up |
Token ID | 929 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
ot | +0.101 |
Nem | +0.097 |
Twe | +0.090 |
jew | +0.087 |
cuc | +0.085 |
Neg logit contributions | |
outage | -0.120 |
ouncing | -0.116 |
ying | -0.114 |
ows | -0.113 |
aking | -0.111 |
Token | with |
Token ID | 351 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Twe | +0.002 |
ot | +0.002 |
Nem | +0.002 |
Twe | +0.002 |
le | +0.001 |
Neg logit contributions | |
outage | -0.002 |
ouncing | -0.002 |
hole | -0.002 |
ying | -0.002 |
ows | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
pre | +0.044 |
Twe | +0.042 |
ho | +0.042 |
ot | +0.042 |
mer | +0.041 |
Neg logit contributions | |
about | -0.019 |
Lisa | -0.013 |
ma | -0.013 |
aps | -0.013 |
Today | -0.013 |
Token | costumes |
Token ID | 24138 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
outage | +0.003 |
hole | +0.002 |
ma | +0.002 |
ouncing | +0.002 |
Today | +0.002 |
Neg logit contributions | |
Twe | -0.004 |
Twe | -0.004 |
Nem | -0.003 |
ot | -0.003 |
le | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
outage | +0.005 |
ouncing | +0.004 |
hole | +0.004 |
ying | +0.004 |
ma | +0.004 |
Neg logit contributions | |
Twe | -0.002 |
ot | -0.002 |
Nem | -0.002 |
le | -0.002 |
Twe | -0.002 |