Token | " |
Token ID | 366 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
onna | +0.061 |
der | +0.058 |
oons | +0.058 |
outage | +0.057 |
alk | +0.057 |
Neg logit contributions | |
lucky | -0.031 |
great | -0.024 |
good | -0.024 |
dog | -0.023 |
reward | -0.023 |
Token | I |
Token ID | 40 |
Feature activation | -8.92e-03 |
Pos logit contributions | |
onna | +0.078 |
oons | +0.076 |
outage | +0.076 |
alk | +0.075 |
der | +0.074 |
Neg logit contributions | |
lucky | -0.042 |
good | -0.033 |
great | -0.032 |
dog | -0.031 |
little | -0.031 |
Token | like |
Token ID | 588 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
lucky | +0.010 |
dog | +0.008 |
little | +0.008 |
good | +0.008 |
's | +0.008 |
Neg logit contributions | |
onna | -0.019 |
outage | -0.018 |
alk | -0.018 |
oons | -0.018 |
der | -0.017 |
Token | your |
Token ID | 534 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
lucky | +0.029 |
good | +0.023 |
great | +0.021 |
little | +0.021 |
dog | +0.021 |
Neg logit contributions | |
oons | -0.070 |
onna | -0.070 |
outage | -0.069 |
lights | -0.069 |
alk | -0.068 |
Token | smile |
Token ID | 8212 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
onna | +0.013 |
outage | +0.012 |
oons | +0.012 |
der | +0.012 |
alk | +0.012 |
Neg logit contributions | |
lucky | -0.007 |
's | -0.006 |
good | -0.006 |
great | -0.006 |
dog | -0.005 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.010 |
great | +0.010 |
dog | +0.010 |
's | +0.010 |
Neg logit contributions | |
onna | -0.026 |
oons | -0.025 |
outage | -0.025 |
alk | -0.025 |
der | -0.025 |
Token | ud |
Token ID | 463 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
onna | +0.138 |
pan | +0.132 |
alk | +0.130 |
fray | +0.124 |
ulk | +0.123 |
Neg logit contributions | |
lucky | -0.206 |
's | -0.197 |
little | -0.195 |
job | -0.191 |
best | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
lights | +0.118 |
outage | +0.117 |
oons | +0.117 |
onna | +0.115 |
ubs | +0.115 |
Neg logit contributions | |
, | -0.077 |
lucky | -0.075 |
dog | -0.070 |
at | -0.068 |
's | -0.068 |
Token | You |
Token ID | 921 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
lucky | +0.011 |
good | +0.009 |
great | +0.008 |
dog | +0.008 |
little | +0.008 |
Neg logit contributions | |
onna | -0.019 |
oons | -0.018 |
outage | -0.018 |
alk | -0.018 |
der | -0.018 |
Token | always |
Token ID | 1464 |
Feature activation | +6.07e-03 |
Pos logit contributions | |
lucky | +0.021 |
dog | +0.017 |
bye | +0.016 |
loyal | +0.016 |
good | +0.015 |
Neg logit contributions | |
onna | -0.049 |
outage | -0.048 |
alk | -0.047 |
oons | -0.047 |
der | -0.047 |
Token | make |
Token ID | 787 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
onna | +0.013 |
outage | +0.012 |
alk | +0.012 |
der | +0.012 |
oons | +0.012 |
Neg logit contributions | |
lucky | -0.007 |
dog | -0.005 |
great | -0.005 |
little | -0.005 |
good | -0.005 |
Token | swoop |
Token ID | 38527 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
lucky | +0.019 |
great | +0.015 |
job | +0.015 |
good | +0.015 |
best | +0.015 |
Neg logit contributions | |
onna | -0.032 |
der | -0.030 |
oons | -0.029 |
outage | -0.029 |
alk | -0.028 |
Token | ed |
Token ID | 276 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
lucky | +0.051 |
great | +0.042 |
reward | +0.041 |
good | +0.041 |
job | +0.040 |
Neg logit contributions | |
onna | -0.065 |
der | -0.064 |
oons | -0.062 |
ubs | -0.061 |
alk | -0.060 |
Token | down |
Token ID | 866 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
lucky | +0.008 |
reward | +0.006 |
job | +0.006 |
great | +0.006 |
loyal | +0.005 |
Neg logit contributions | |
onna | -0.013 |
der | -0.013 |
pan | -0.012 |
lights | -0.012 |
heavily | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
lucky | +0.013 |
great | +0.010 |
good | +0.009 |
reward | +0.009 |
job | +0.009 |
Neg logit contributions | |
onna | -0.021 |
der | -0.021 |
alk | -0.020 |
oons | -0.020 |
outage | -0.019 |
Token | catch |
Token ID | 4929 |
Feature activation | +3.28e-03 |
Pos logit contributions | |
onna | +0.037 |
alk | +0.035 |
oons | +0.034 |
der | +0.034 |
outage | +0.034 |
Neg logit contributions | |
lucky | -0.017 |
best | -0.013 |
good | -0.013 |
loyal | -0.013 |
great | -0.012 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
onna | +0.007 |
oons | +0.007 |
der | +0.007 |
alk | +0.007 |
outage | +0.007 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.003 |
great | -0.003 |
dog | -0.003 |
reward | -0.003 |
Token | ide |
Token ID | 485 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
onna | +0.112 |
bars | +0.111 |
ulk | +0.109 |
pan | +0.109 |
bench | +0.108 |
Neg logit contributions | |
little | -0.206 |
's | -0.204 |
lucky | -0.194 |
- | -0.190 |
great | -0.184 |
Token | y |
Token ID | 88 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
onna | +0.025 |
oons | +0.024 |
outage | +0.024 |
alk | +0.023 |
ands | +0.023 |
Neg logit contributions | |
lucky | -0.024 |
good | -0.021 |
dog | -0.021 |
's | -0.021 |
little | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
onna | +0.022 |
oons | +0.021 |
der | +0.021 |
outage | +0.021 |
alk | +0.021 |
Neg logit contributions | |
lucky | -0.017 |
good | -0.014 |
great | -0.013 |
dog | -0.013 |
reward | -0.013 |
Token | Sp |
Token ID | 1338 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
lucky | +0.006 |
good | +0.005 |
great | +0.005 |
little | +0.004 |
dog | +0.004 |
Neg logit contributions | |
onna | -0.012 |
oons | -0.012 |
outage | -0.012 |
alk | -0.012 |
der | -0.012 |
Token | ide |
Token ID | 485 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
bench | +0.079 |
onna | +0.078 |
pan | +0.076 |
bars | +0.076 |
ulk | +0.075 |
Neg logit contributions | |
lucky | -0.154 |
little | -0.151 |
's | -0.139 |
great | -0.138 |
at | -0.138 |
Token | because |
Token ID | 780 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
onna | +0.053 |
oons | +0.051 |
outage | +0.051 |
alk | +0.051 |
der | +0.050 |
Neg logit contributions | |
lucky | -0.024 |
good | -0.018 |
great | -0.018 |
dog | -0.017 |
little | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
onna | +0.017 |
oons | +0.016 |
outage | +0.016 |
der | +0.016 |
lights | +0.016 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.007 |
great | -0.007 |
dog | -0.007 |
's | -0.007 |
Token | knee |
Token ID | 10329 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
onna | +0.033 |
oons | +0.032 |
outage | +0.032 |
der | +0.032 |
lights | +0.032 |
Neg logit contributions | |
lucky | -0.014 |
great | -0.011 |
good | -0.011 |
's | -0.011 |
reward | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
onna | +0.054 |
oons | +0.052 |
outage | +0.052 |
alk | +0.052 |
der | +0.051 |
Neg logit contributions | |
lucky | -0.018 |
good | -0.013 |
's | -0.013 |
great | -0.012 |
dog | -0.012 |
Token | all |
Token ID | 477 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
oons | +0.054 |
onna | +0.053 |
alk | +0.052 |
outage | +0.052 |
ands | +0.051 |
Neg logit contributions | |
lucky | -0.030 |
good | -0.025 |
great | -0.024 |
little | -0.023 |
fine | -0.023 |
Token | scrap |
Token ID | 15881 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
onna | +0.057 |
oons | +0.057 |
alk | +0.056 |
der | +0.056 |
ands | +0.055 |
Neg logit contributions | |
lucky | -0.033 |
good | -0.028 |
great | -0.026 |
little | -0.025 |
's | -0.025 |
Token | ed |
Token ID | 276 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
onna | +0.265 |
outage | +0.249 |
lights | +0.239 |
alk | +0.239 |
oons | +0.238 |
Neg logit contributions | |
lucky | -0.100 |
's | -0.090 |
, | -0.086 |
good | -0.083 |
at | -0.082 |
Token | up |
Token ID | 510 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
onna | +0.040 |
oons | +0.038 |
der | +0.038 |
outage | +0.038 |
alk | +0.037 |
Neg logit contributions | |
lucky | -0.022 |
good | -0.017 |
great | -0.017 |
dog | -0.017 |
reward | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
lucky | +0.002 |
good | +0.002 |
great | +0.002 |
little | +0.002 |
dog | +0.002 |
Neg logit contributions | |
onna | -0.005 |
oons | -0.005 |
outage | -0.005 |
alk | -0.005 |
der | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
onna | +0.012 |
outage | +0.011 |
der | +0.011 |
oons | +0.011 |
lights | +0.011 |
Neg logit contributions | |
lucky | -0.007 |
great | -0.006 |
good | -0.006 |
reward | -0.006 |
dog | -0.006 |
Token | didn |
Token ID | 1422 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
onna | +0.093 |
alk | +0.091 |
outage | +0.091 |
oons | +0.090 |
ands | +0.089 |
Neg logit contributions | |
lucky | -0.038 |
's | -0.029 |
good | -0.028 |
great | -0.028 |
little | -0.027 |
Token | Annie |
Token ID | 25860 |
Feature activation | +9.16e-03 |
Pos logit contributions | |
onna | +0.001 |
oons | +0.001 |
outage | +0.001 |
alk | +0.001 |
ands | +0.001 |
Neg logit contributions | |
lucky | -0.001 |
little | -0.001 |
's | -0.001 |
good | -0.001 |
great | -0.001 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
onna | +0.018 |
der | +0.017 |
alk | +0.017 |
outage | +0.017 |
ide | +0.017 |
Neg logit contributions | |
lucky | -0.011 |
job | -0.010 |
reward | -0.010 |
good | -0.009 |
great | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -4.01e-03 |
Pos logit contributions | |
lucky | +0.004 |
great | +0.003 |
reward | +0.003 |
good | +0.003 |
dog | +0.003 |
Neg logit contributions | |
onna | -0.007 |
outage | -0.007 |
oons | -0.006 |
ubs | -0.006 |
der | -0.006 |
Token | come |
Token ID | 1282 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
lucky | +0.004 |
good | +0.003 |
great | +0.003 |
dog | +0.003 |
's | +0.003 |
Neg logit contributions | |
onna | -0.009 |
outage | -0.009 |
alk | -0.009 |
oons | -0.009 |
ubs | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
lucky | +0.054 |
reward | +0.042 |
good | +0.042 |
great | +0.041 |
dog | +0.040 |
Neg logit contributions | |
onna | -0.109 |
outage | -0.104 |
ubs | -0.104 |
alk | -0.103 |
lights | -0.098 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
lucky | +0.020 |
good | +0.016 |
great | +0.016 |
dog | +0.015 |
little | +0.015 |
Neg logit contributions | |
onna | -0.036 |
outage | -0.035 |
oons | -0.035 |
der | -0.035 |
alk | -0.035 |
Token | ide |
Token ID | 485 |
Feature activation | +9.39e-03 |
Pos logit contributions | |
pan | +0.138 |
fray | +0.127 |
onna | +0.127 |
bars | +0.126 |
bench | +0.124 |
Neg logit contributions | |
little | -0.168 |
's | -0.164 |
lucky | -0.164 |
at | -0.160 |
by | -0.156 |
Token | y |
Token ID | 88 |
Feature activation | +6.75e-03 |
Pos logit contributions | |
onna | +0.015 |
bench | +0.015 |
ands | +0.014 |
oons | +0.014 |
outage | +0.014 |
Neg logit contributions | |
lucky | -0.016 |
, | -0.015 |
's | -0.014 |
dog | -0.014 |
little | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -6.38e-03 |
Pos logit contributions | |
onna | +0.016 |
oons | +0.015 |
outage | +0.015 |
der | +0.015 |
alk | +0.015 |
Neg logit contributions | |
lucky | -0.007 |
good | -0.005 |
great | -0.005 |
dog | -0.005 |
little | -0.005 |
Token | explore |
Token ID | 7301 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
lucky | +0.008 |
good | +0.006 |
great | +0.006 |
best | +0.006 |
fine | +0.006 |
Neg logit contributions | |
onna | -0.013 |
outage | -0.012 |
alk | -0.012 |
ubs | -0.012 |
der | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
onna | +0.028 |
oons | +0.027 |
outage | +0.027 |
alk | +0.027 |
der | +0.026 |
Neg logit contributions | |
lucky | -0.008 |
, | -0.006 |
good | -0.006 |
great | -0.006 |
's | -0.005 |
Token | friendly |
Token ID | 8030 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
lucky | +0.008 |
's | +0.007 |
at | +0.006 |
bye | +0.006 |
turns | +0.005 |
Neg logit contributions | |
onna | -0.019 |
outage | -0.019 |
bench | -0.018 |
lights | -0.018 |
alk | -0.018 |
Token | bee |
Token ID | 20697 |
Feature activation | +1.77e-03 |
Pos logit contributions | |
lucky | +0.024 |
great | +0.019 |
's | +0.018 |
good | +0.018 |
best | +0.018 |
Neg logit contributions | |
onna | -0.041 |
outage | -0.040 |
alk | -0.039 |
der | -0.039 |
ware | -0.037 |
Token | named |
Token ID | 3706 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
onna | +0.004 |
outage | +0.004 |
der | +0.004 |
alk | +0.004 |
oons | +0.004 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.002 |
great | -0.002 |
reward | -0.002 |
job | -0.002 |
Token | Buzz |
Token ID | 15753 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
outage | +0.053 |
oons | +0.053 |
lights | +0.053 |
onna | +0.053 |
ands | +0.052 |
Neg logit contributions | |
lucky | -0.032 |
little | -0.027 |
's | -0.026 |
dog | -0.026 |
good | -0.025 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
onna | +0.026 |
oons | +0.025 |
outage | +0.025 |
der | +0.024 |
alk | +0.024 |
Neg logit contributions | |
lucky | -0.041 |
good | -0.036 |
great | -0.036 |
dog | -0.036 |
little | -0.035 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
onna | +0.010 |
outage | +0.009 |
oons | +0.009 |
lights | +0.009 |
alk | +0.009 |
Neg logit contributions | |
lucky | -0.005 |
little | -0.004 |
good | -0.004 |
dog | -0.003 |
great | -0.003 |
Token | ide |
Token ID | 485 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
bars | +0.120 |
ulk | +0.111 |
bench | +0.111 |
onna | +0.110 |
fray | +0.108 |
Neg logit contributions | |
little | -0.185 |
's | -0.178 |
lucky | -0.176 |
at | -0.173 |
by | -0.169 |
Token | y |
Token ID | 88 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
onna | +0.015 |
outage | +0.014 |
oons | +0.014 |
ands | +0.014 |
alk | +0.014 |
Neg logit contributions | |
lucky | -0.019 |
dog | -0.016 |
little | -0.016 |
good | -0.016 |
's | -0.016 |
Token | struggling |
Token ID | 9648 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
onna | +0.020 |
oons | +0.019 |
outage | +0.019 |
der | +0.019 |
alk | +0.019 |
Neg logit contributions | |
lucky | -0.010 |
good | -0.008 |
great | -0.008 |
dog | -0.007 |
reward | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +4.54e-03 |
Pos logit contributions | |
oons | +0.079 |
outage | +0.079 |
onna | +0.078 |
lights | +0.077 |
alk | +0.076 |
Neg logit contributions | |
lucky | -0.026 |
good | -0.021 |
, | -0.021 |
at | -0.020 |
's | -0.020 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
onna | +0.010 |
oons | +0.010 |
outage | +0.009 |
der | +0.009 |
alk | +0.009 |
Neg logit contributions | |
lucky | -0.005 |
good | -0.004 |
great | -0.004 |
dog | -0.004 |
reward | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
onna | +0.043 |
outage | +0.042 |
der | +0.042 |
alk | +0.042 |
oons | +0.041 |
Neg logit contributions | |
lucky | -0.018 |
's | -0.014 |
little | -0.014 |
good | -0.014 |
great | -0.013 |
Token | I |
Token ID | 40 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
onna | +0.052 |
oons | +0.050 |
outage | +0.050 |
alk | +0.049 |
der | +0.049 |
Neg logit contributions | |
lucky | -0.028 |
good | -0.022 |
great | -0.022 |
dog | -0.021 |
little | -0.021 |
Token | am |
Token ID | 716 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
onna | +0.007 |
outage | +0.006 |
alk | +0.006 |
ubs | +0.006 |
oons | +0.006 |
Neg logit contributions | |
lucky | -0.004 |
dog | -0.003 |
bye | -0.003 |
good | -0.003 |
little | -0.003 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
onna | +0.064 |
ubs | +0.059 |
outage | +0.059 |
der | +0.058 |
alk | +0.058 |
Neg logit contributions | |
lucky | -0.026 |
reward | -0.021 |
's | -0.021 |
dog | -0.021 |
arrived | -0.020 |
Token | replied |
Token ID | 8712 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
onna | +0.083 |
oons | +0.079 |
der | +0.078 |
alk | +0.077 |
ware | +0.077 |
Neg logit contributions | |
lucky | -0.047 |
great | -0.037 |
good | -0.035 |
best | -0.034 |
loyal | -0.033 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
onna | +0.042 |
oons | +0.039 |
der | +0.039 |
alk | +0.038 |
ware | +0.038 |
Neg logit contributions | |
lucky | -0.027 |
great | -0.020 |
good | -0.020 |
loyal | -0.019 |
dog | -0.019 |
Token | ud |
Token ID | 463 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
pan | +0.116 |
fray | +0.116 |
alk | +0.112 |
bars | +0.110 |
ulk | +0.109 |
Neg logit contributions | |
little | -0.186 |
lucky | -0.172 |
good | -0.166 |
at | -0.165 |
's | -0.163 |
Token | . |
Token ID | 13 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
lights | +0.138 |
outage | +0.135 |
oons | +0.135 |
alk | +0.130 |
reating | +0.130 |
Neg logit contributions | |
, | -0.062 |
lucky | -0.054 |
little | -0.052 |
at | -0.052 |
's | -0.049 |
Token | " |
Token ID | 366 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
onna | +0.052 |
oons | +0.050 |
outage | +0.050 |
der | +0.050 |
alk | +0.049 |
Neg logit contributions | |
lucky | -0.024 |
good | -0.018 |
great | -0.018 |
dog | -0.017 |
little | -0.017 |
Token | I |
Token ID | 40 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
onna | +0.079 |
oons | +0.078 |
outage | +0.078 |
alk | +0.078 |
lights | +0.077 |
Neg logit contributions | |
lucky | -0.045 |
good | -0.036 |
great | -0.035 |
little | -0.034 |
's | -0.034 |
Token | just |
Token ID | 655 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
onna | +0.007 |
outage | +0.007 |
alk | +0.006 |
oons | +0.006 |
ubs | +0.006 |
Neg logit contributions | |
lucky | -0.005 |
bye | -0.004 |
little | -0.004 |
dog | -0.004 |
good | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
lucky | +0.025 |
reward | +0.019 |
bye | +0.019 |
good | +0.018 |
loyal | +0.017 |
Neg logit contributions | |
onna | -0.051 |
oons | -0.050 |
ide | -0.048 |
alk | -0.047 |
ubs | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
onna | +0.006 |
outage | +0.006 |
oons | +0.006 |
der | +0.006 |
alk | +0.006 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.002 |
great | -0.002 |
dog | -0.001 |
little | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
arrived | +0.011 |
turns | +0.011 |
lucky | +0.011 |
's | +0.011 |
away | +0.010 |
Neg logit contributions | |
onna | -0.036 |
oons | -0.032 |
ware | -0.032 |
iky | -0.032 |
der | -0.032 |
Token | potato |
Token ID | 21219 |
Feature activation | -9.73e-04 |
Pos logit contributions | |
lucky | +0.026 |
's | +0.020 |
turns | +0.020 |
great | +0.019 |
relieved | +0.019 |
Neg logit contributions | |
onna | -0.062 |
der | -0.059 |
alk | -0.059 |
oons | -0.059 |
outage | -0.058 |
Token | named |
Token ID | 3706 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
lucky | +0.001 |
dog | +0.001 |
good | +0.001 |
's | +0.001 |
little | +0.001 |
Neg logit contributions | |
onna | -0.002 |
oons | -0.002 |
outage | -0.002 |
lights | -0.002 |
alk | -0.002 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
onna | +0.046 |
outage | +0.044 |
oons | +0.044 |
der | +0.044 |
alk | +0.044 |
Neg logit contributions | |
lucky | -0.025 |
good | -0.020 |
great | -0.020 |
dog | -0.019 |
little | -0.019 |
Token | ud |
Token ID | 463 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
pan | +0.122 |
ulk | +0.118 |
bars | +0.112 |
fray | +0.111 |
onna | +0.101 |
Neg logit contributions | |
little | -0.186 |
's | -0.179 |
lucky | -0.173 |
at | -0.171 |
by | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
outage | +0.093 |
lights | +0.091 |
onna | +0.090 |
bench | +0.089 |
alk | +0.088 |
Neg logit contributions | |
, | -0.038 |
dog | -0.033 |
at | -0.032 |
lucky | -0.031 |
little | -0.031 |
Token | Sp |
Token ID | 1338 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
lucky | +0.008 |
good | +0.008 |
, | +0.007 |
little | +0.007 |
great | +0.007 |
Neg logit contributions | |
outage | -0.012 |
oons | -0.011 |
alk | -0.011 |
ubs | -0.011 |
der | -0.011 |
Token | ud |
Token ID | 463 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
pan | +0.102 |
onna | +0.096 |
bars | +0.096 |
reating | +0.094 |
fray | +0.094 |
Neg logit contributions | |
little | -0.154 |
lucky | -0.153 |
's | -0.147 |
at | -0.144 |
good | -0.141 |
Token | was |
Token ID | 373 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
outage | +0.067 |
lights | +0.066 |
reating | +0.066 |
ands | +0.065 |
bench | +0.065 |
Neg logit contributions | |
, | -0.039 |
at | -0.033 |
's | -0.033 |
got | -0.032 |
little | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
onna | +0.033 |
ands | +0.032 |
der | +0.032 |
oons | +0.032 |
alk | +0.031 |
Neg logit contributions | |
lucky | -0.016 |
great | -0.012 |
arrived | -0.011 |
dog | -0.011 |
little | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
lucky | +0.007 |
good | +0.005 |
great | +0.005 |
little | +0.005 |
dog | +0.004 |
Neg logit contributions | |
onna | -0.021 |
oons | -0.020 |
outage | -0.020 |
alk | -0.020 |
der | -0.020 |
Token | much |
Token ID | 881 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
onna | +0.010 |
outage | +0.009 |
oons | +0.009 |
alk | +0.009 |
lights | +0.009 |
Neg logit contributions | |
lucky | -0.006 |
good | -0.005 |
great | -0.005 |
little | -0.005 |
fine | -0.005 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.001 |
great | +0.001 |
little | +0.001 |
dog | +0.001 |
Neg logit contributions | |
onna | -0.003 |
oons | -0.003 |
alk | -0.002 |
outage | -0.002 |
lights | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
onna | +0.045 |
der | +0.043 |
alk | +0.042 |
oons | +0.042 |
outage | +0.041 |
Neg logit contributions | |
lucky | -0.028 |
great | -0.022 |
good | -0.021 |
job | -0.021 |
best | -0.021 |
Token | Sp |
Token ID | 1338 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
onna | +0.002 |
alk | +0.002 |
der | +0.002 |
ware | +0.002 |
oons | +0.002 |
Neg logit contributions | |
lucky | -0.002 |
great | -0.001 |
's | -0.001 |
good | -0.001 |
loyal | -0.001 |
Token | ide |
Token ID | 485 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
bars | +0.125 |
bench | +0.118 |
ulk | +0.118 |
fray | +0.114 |
pan | +0.111 |
Neg logit contributions | |
little | -0.187 |
lucky | -0.180 |
, | -0.169 |
at | -0.166 |
good | -0.164 |
Token | y |
Token ID | 88 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
outage | +0.019 |
onna | +0.019 |
oons | +0.019 |
ands | +0.018 |
ubs | +0.018 |
Neg logit contributions | |
lucky | -0.023 |
little | -0.020 |
good | -0.020 |
's | -0.020 |
, | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
onna | +0.026 |
outage | +0.025 |
oons | +0.025 |
alk | +0.025 |
ubs | +0.025 |
Neg logit contributions | |
lucky | -0.013 |
good | -0.010 |
's | -0.010 |
little | -0.010 |
great | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
onna | +0.029 |
oons | +0.028 |
outage | +0.028 |
der | +0.027 |
alk | +0.027 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.011 |
great | -0.011 |
dog | -0.011 |
little | -0.011 |
Token | You |
Token ID | 1639 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
outage | +0.058 |
onna | +0.057 |
oons | +0.057 |
lights | +0.056 |
alk | +0.056 |
Neg logit contributions | |
lucky | -0.029 |
good | -0.023 |
great | -0.022 |
's | -0.021 |
loyal | -0.021 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
lights | +0.021 |
ware | +0.021 |
oons | +0.021 |
onna | +0.021 |
outage | +0.021 |
Neg logit contributions | |
lucky | -0.011 |
thank | -0.008 |
relieved | -0.008 |
arrived | -0.008 |
bye | -0.008 |
Token | when |
Token ID | 618 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
onna | +0.057 |
oons | +0.055 |
outage | +0.055 |
alk | +0.054 |
lights | +0.054 |
Neg logit contributions | |
lucky | -0.027 |
good | -0.021 |
's | -0.021 |
dog | -0.021 |
great | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
onna | +0.014 |
oons | +0.014 |
outage | +0.014 |
alk | +0.013 |
der | +0.013 |
Neg logit contributions | |
lucky | -0.005 |
good | -0.004 |
great | -0.004 |
dog | -0.004 |
little | -0.003 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
onna | +0.058 |
oons | +0.056 |
outage | +0.055 |
alk | +0.055 |
der | +0.055 |
Neg logit contributions | |
lucky | -0.028 |
good | -0.021 |
great | -0.021 |
dog | -0.020 |
reward | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
oons | +0.055 |
iders | +0.054 |
onna | +0.054 |
ands | +0.053 |
ills | +0.053 |
Neg logit contributions | |
, | -0.015 |
on | -0.014 |
back | -0.014 |
at | -0.014 |
good | -0.012 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
lucky | +0.003 |
good | +0.002 |
's | +0.002 |
little | +0.002 |
dog | +0.002 |
Neg logit contributions | |
onna | -0.006 |
oons | -0.006 |
alk | -0.006 |
outage | -0.006 |
ands | -0.006 |
Token | ed |
Token ID | 276 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
onna | +0.267 |
outage | +0.254 |
lights | +0.247 |
alk | +0.246 |
oons | +0.243 |
Neg logit contributions | |
lucky | -0.071 |
's | -0.057 |
good | -0.056 |
, | -0.053 |
at | -0.053 |
Token | his |
Token ID | 465 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
onna | +0.041 |
outage | +0.039 |
oons | +0.039 |
alk | +0.039 |
der | +0.038 |
Neg logit contributions | |
lucky | -0.020 |
good | -0.015 |
great | -0.015 |
dog | -0.015 |
little | -0.014 |
Token | skin |
Token ID | 4168 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
onna | +0.071 |
oons | +0.068 |
outage | +0.068 |
alk | +0.067 |
ubs | +0.066 |
Neg logit contributions | |
lucky | -0.061 |
good | -0.052 |
little | -0.051 |
dog | -0.051 |
great | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
alk | +0.039 |
ands | +0.039 |
onna | +0.039 |
outage | +0.038 |
oons | +0.037 |
Neg logit contributions | |
's | -0.014 |
at | -0.014 |
, | -0.014 |
lucky | -0.013 |
good | -0.013 |
Token | It |
Token ID | 632 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
onna | +0.029 |
oons | +0.028 |
der | +0.027 |
alk | +0.027 |
ubs | +0.027 |
Neg logit contributions | |
lucky | -0.016 |
good | -0.012 |
great | -0.012 |
reward | -0.012 |
dog | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
lucky | +0.008 |
good | +0.006 |
great | +0.006 |
dog | +0.006 |
reward | +0.005 |
Neg logit contributions | |
onna | -0.019 |
oons | -0.018 |
outage | -0.018 |
der | -0.018 |
alk | -0.018 |
Token | is |
Token ID | 318 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
onna | +0.009 |
oons | +0.009 |
outage | +0.009 |
der | +0.009 |
alk | +0.008 |
Neg logit contributions | |
lucky | -0.004 |
reward | -0.003 |
bye | -0.003 |
great | -0.002 |
good | -0.002 |
Token | dirty |
Token ID | 11841 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
onna | +0.037 |
oons | +0.037 |
outage | +0.037 |
der | +0.036 |
alk | +0.036 |
Neg logit contributions | |
lucky | -0.017 |
good | -0.013 |
great | -0.013 |
little | -0.012 |
fine | -0.011 |
Token | or |
Token ID | 393 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
alk | +0.085 |
onna | +0.083 |
ulk | +0.079 |
eways | +0.078 |
ands | +0.078 |
Neg logit contributions | |
, | -0.044 |
at | -0.040 |
good | -0.037 |
lucky | -0.036 |
little | -0.034 |
Token | has |
Token ID | 468 |
Feature activation | +4.00e-03 |
Pos logit contributions | |
lucky | +0.017 |
good | +0.015 |
great | +0.013 |
little | +0.013 |
fine | +0.013 |
Neg logit contributions | |
oons | -0.034 |
alk | -0.034 |
onna | -0.034 |
outage | -0.034 |
ands | -0.033 |
Token | ger |
Token ID | 27602 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
outage | +0.009 |
oons | +0.009 |
onna | +0.009 |
bench | +0.009 |
alk | +0.009 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.004 |
little | -0.004 |
great | -0.004 |
dog | -0.003 |
Token | ms |
Token ID | 907 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
onna | +0.117 |
lights | +0.117 |
alk | +0.114 |
outage | +0.107 |
eways | +0.107 |
Neg logit contributions | |
lucky | -0.209 |
good | -0.197 |
at | -0.192 |
dog | -0.189 |
, | -0.188 |
Token | ." |
Token ID | 526 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
lucky | +0.022 |
good | +0.019 |
's | +0.019 |
at | +0.019 |
dog | +0.018 |
Neg logit contributions | |
onna | -0.024 |
alk | -0.022 |
oons | -0.022 |
outage | -0.022 |
lights | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
onna | +0.082 |
oons | +0.080 |
outage | +0.079 |
alk | +0.078 |
der | +0.078 |
Neg logit contributions | |
lucky | -0.034 |
good | -0.025 |
great | -0.025 |
dog | -0.024 |
's | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
der | +0.040 |
onna | +0.040 |
outage | +0.040 |
alk | +0.039 |
oons | +0.039 |
Neg logit contributions | |
lucky | -0.010 |
good | -0.007 |
little | -0.006 |
's | -0.006 |
great | -0.006 |
Token | They |
Token ID | 2990 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
onna | +0.022 |
oons | +0.022 |
outage | +0.022 |
alk | +0.021 |
der | +0.021 |
Neg logit contributions | |
lucky | -0.016 |
good | -0.013 |
great | -0.013 |
dog | -0.013 |
's | -0.013 |
Token | Do |
Token ID | 5211 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
onna | +0.064 |
outage | +0.062 |
oons | +0.062 |
alk | +0.061 |
lights | +0.061 |
Neg logit contributions | |
lucky | -0.050 |
good | -0.042 |
great | -0.041 |
little | -0.041 |
dog | -0.041 |
Token | you |
Token ID | 345 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
lucky | +0.029 |
delivery | +0.023 |
dog | +0.023 |
reward | +0.022 |
relieved | +0.022 |
Neg logit contributions | |
onna | -0.060 |
alk | -0.057 |
oons | -0.057 |
der | -0.056 |
ands | -0.056 |
Token | need |
Token ID | 761 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
lucky | +0.040 |
good | +0.032 |
great | +0.031 |
little | +0.030 |
dog | +0.030 |
Neg logit contributions | |
onna | -0.070 |
oons | -0.069 |
outage | -0.068 |
der | -0.068 |
lights | -0.067 |
Token | help |
Token ID | 1037 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
lucky | +0.006 |
good | +0.003 |
great | +0.003 |
little | +0.003 |
reward | +0.003 |
Neg logit contributions | |
onna | -0.031 |
oons | -0.031 |
lights | -0.031 |
outage | -0.031 |
der | -0.030 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
lights | +0.079 |
der | +0.079 |
oons | +0.078 |
onna | +0.078 |
outage | +0.077 |
Neg logit contributions | |
, | -0.026 |
lucky | -0.024 |
little | -0.023 |
's | -0.021 |
good | -0.019 |
Token | Sp |
Token ID | 1338 |
Feature activation | +9.77e-02 |
Pos logit contributions | |
onna | +0.103 |
oons | +0.098 |
outage | +0.097 |
der | +0.097 |
alk | +0.096 |
Neg logit contributions | |
lucky | -0.073 |
good | -0.059 |
great | -0.059 |
dog | -0.057 |
little | -0.056 |
Token | ide |
Token ID | 485 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
bars | +0.122 |
ulk | +0.112 |
bench | +0.111 |
fray | +0.110 |
pan | +0.106 |
Neg logit contributions | |
little | -0.180 |
lucky | -0.175 |
, | -0.166 |
's | -0.166 |
at | -0.166 |
Token | y |
Token ID | 88 |
Feature activation | +7.67e-03 |
Pos logit contributions | |
onna | +0.015 |
outage | +0.015 |
ands | +0.015 |
ubs | +0.014 |
oons | +0.014 |
Neg logit contributions | |
lucky | -0.017 |
little | -0.015 |
's | -0.015 |
, | -0.015 |
good | -0.015 |
Token | nodded |
Token ID | 14464 |
Feature activation | +5.78e-02 |
Pos logit contributions | |
onna | +0.017 |
oons | +0.017 |
der | +0.017 |
outage | +0.016 |
alk | +0.016 |
Neg logit contributions | |
lucky | -0.008 |
good | -0.006 |
great | -0.006 |
dog | -0.006 |
reward | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
onna | +0.137 |
oons | +0.133 |
outage | +0.133 |
alk | +0.131 |
der | +0.131 |
Neg logit contributions | |
lucky | -0.056 |
good | -0.041 |
great | -0.040 |
dog | -0.039 |
little | -0.038 |
Token | head |
Token ID | 1182 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
onna | +0.043 |
der | +0.042 |
alk | +0.041 |
oons | +0.041 |
outage | +0.040 |
Neg logit contributions | |
lucky | -0.029 |
great | -0.023 |
good | -0.023 |
reward | -0.023 |
dog | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.83e-04 |
Pos logit contributions | |
onna | +0.086 |
oons | +0.083 |
alk | +0.083 |
outage | +0.082 |
lights | +0.081 |
Neg logit contributions | |
lucky | -0.031 |
dog | -0.024 |
good | -0.024 |
at | -0.023 |
's | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
onna | +0.000 |
oons | +0.000 |
outage | +0.000 |
alk | +0.000 |
der | +0.000 |
Neg logit contributions | |
lucky | -0.000 |
good | -0.000 |
great | -0.000 |
dog | -0.000 |
little | -0.000 |
Token | fell |
Token ID | 3214 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
onna | +0.092 |
alk | +0.090 |
outage | +0.090 |
oons | +0.089 |
lights | +0.088 |
Neg logit contributions | |
lucky | -0.037 |
's | -0.028 |
good | -0.028 |
great | -0.027 |
little | -0.027 |
Token | down |
Token ID | 866 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
oons | +0.052 |
ands | +0.050 |
ware | +0.050 |
alk | +0.050 |
aghetti | +0.049 |
Neg logit contributions | |
back | -0.007 |
on | -0.007 |
at | -0.007 |
, | -0.007 |
good | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -5.01e-04 |
Pos logit contributions | |
lucky | +0.009 |
, | +0.009 |
good | +0.009 |
at | +0.008 |
great | +0.007 |
Neg logit contributions | |
oons | -0.028 |
onna | -0.028 |
lights | -0.027 |
outage | -0.027 |
ills | -0.027 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.000 |
great | +0.000 |
dog | +0.000 |
's | +0.000 |
Neg logit contributions | |
onna | -0.001 |
oons | -0.001 |
outage | -0.001 |
alk | -0.001 |
der | -0.001 |
Token | ed |
Token ID | 276 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
onna | +0.275 |
outage | +0.261 |
lights | +0.252 |
alk | +0.252 |
oons | +0.248 |
Neg logit contributions | |
lucky | -0.063 |
's | -0.049 |
at | -0.047 |
good | -0.047 |
, | -0.044 |
Token | her |
Token ID | 607 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
onna | +0.041 |
outage | +0.040 |
oons | +0.039 |
alk | +0.039 |
lights | +0.038 |
Neg logit contributions | |
lucky | -0.022 |
good | -0.019 |
great | -0.018 |
little | -0.018 |
dog | -0.018 |
Token | knee |
Token ID | 10329 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
onna | +0.076 |
outage | +0.075 |
oons | +0.074 |
alk | +0.073 |
ubs | +0.071 |
Neg logit contributions | |
lucky | -0.076 |
good | -0.066 |
little | -0.066 |
dog | -0.066 |
's | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +7.96e-03 |
Pos logit contributions | |
oons | +0.081 |
onna | +0.081 |
alk | +0.080 |
outage | +0.079 |
ands | +0.078 |
Neg logit contributions | |
lucky | -0.042 |
's | -0.038 |
good | -0.037 |
at | -0.036 |
, | -0.035 |
Token | It |
Token ID | 632 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
onna | +0.018 |
outage | +0.017 |
oons | +0.017 |
alk | +0.017 |
lights | +0.017 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.007 |
dog | -0.007 |
's | -0.007 |
little | -0.007 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
lucky | +0.002 |
good | +0.001 |
great | +0.001 |
dog | +0.001 |
little | +0.001 |
Neg logit contributions | |
onna | -0.007 |
oons | -0.007 |
outage | -0.007 |
alk | -0.007 |
der | -0.007 |
Token | when |
Token ID | 618 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
lucky | +0.012 |
good | +0.008 |
's | +0.008 |
little | +0.008 |
dog | +0.008 |
Neg logit contributions | |
onna | -0.039 |
oons | -0.038 |
outage | -0.038 |
alk | -0.037 |
der | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
onna | +0.004 |
oons | +0.004 |
outage | +0.004 |
alk | +0.004 |
der | +0.004 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.002 |
great | -0.001 |
dog | -0.001 |
little | -0.001 |
Token | stumbled |
Token ID | 24241 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
onna | +0.056 |
oons | +0.054 |
outage | +0.054 |
der | +0.053 |
alk | +0.053 |
Neg logit contributions | |
lucky | -0.020 |
good | -0.014 |
great | -0.014 |
dog | -0.013 |
little | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -8.15e-03 |
Pos logit contributions | |
oons | +0.081 |
lights | +0.080 |
onna | +0.079 |
outage | +0.078 |
ands | +0.078 |
Neg logit contributions | |
lucky | -0.021 |
, | -0.018 |
back | -0.018 |
at | -0.018 |
little | -0.017 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.75e-02 |
Pos logit contributions | |
lucky | +0.009 |
good | +0.007 |
's | +0.007 |
dog | +0.007 |
little | +0.007 |
Neg logit contributions | |
onna | -0.018 |
oons | -0.018 |
outage | -0.018 |
alk | -0.018 |
lights | -0.018 |
Token | ed |
Token ID | 276 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
onna | +0.260 |
outage | +0.248 |
lights | +0.242 |
oons | +0.240 |
alk | +0.240 |
Neg logit contributions | |
lucky | -0.072 |
good | -0.054 |
's | -0.054 |
, | -0.053 |
at | -0.052 |
Token | her |
Token ID | 607 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
onna | +0.024 |
oons | +0.023 |
outage | +0.023 |
alk | +0.023 |
der | +0.022 |
Neg logit contributions | |
lucky | -0.016 |
good | -0.013 |
great | -0.013 |
dog | -0.013 |
little | -0.013 |
Token | knee |
Token ID | 10329 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
onna | +0.068 |
outage | +0.065 |
oons | +0.065 |
alk | +0.064 |
ubs | +0.062 |
Neg logit contributions | |
lucky | -0.067 |
good | -0.057 |
dog | -0.056 |
little | -0.056 |
great | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
onna | +0.066 |
oons | +0.065 |
alk | +0.065 |
outage | +0.064 |
ands | +0.063 |
Neg logit contributions | |
lucky | -0.036 |
's | -0.033 |
good | -0.031 |
, | -0.031 |
at | -0.030 |
Token | At |
Token ID | 1629 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
onna | +0.021 |
oons | +0.020 |
outage | +0.020 |
der | +0.019 |
alk | +0.019 |
Neg logit contributions | |
lucky | -0.018 |
good | -0.015 |
great | -0.015 |
dog | -0.015 |
little | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
lucky | +0.000 |
reward | +0.000 |
welcome | +0.000 |
great | +0.000 |
delivery | +0.000 |
Neg logit contributions | |
der | -0.000 |
onna | -0.000 |
lights | -0.000 |
outage | -0.000 |
ware | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
onna | +0.021 |
der | +0.021 |
oons | +0.020 |
lights | +0.020 |
ubs | +0.020 |
Neg logit contributions | |
lucky | -0.011 |
reward | -0.009 |
great | -0.009 |
good | -0.009 |
welcome | -0.008 |
Token | tri |
Token ID | 1333 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
onna | +0.030 |
oons | +0.029 |
outage | +0.029 |
der | +0.029 |
alk | +0.028 |
Neg logit contributions | |
lucky | -0.013 |
good | -0.010 |
great | -0.010 |
dog | -0.009 |
reward | -0.009 |
Token | pped |
Token ID | 1496 |
Feature activation | +8.74e-04 |
Pos logit contributions | |
lights | +0.075 |
onna | +0.072 |
outage | +0.070 |
oons | +0.068 |
alk | +0.068 |
Neg logit contributions | |
lucky | -0.079 |
at | -0.073 |
's | -0.070 |
on | -0.069 |
good | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
oons | +0.002 |
outage | +0.002 |
onna | +0.002 |
lights | +0.002 |
ands | +0.002 |
Neg logit contributions | |
lucky | -0.001 |
good | -0.000 |
's | -0.000 |
at | -0.000 |
, | -0.000 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.010 |
little | +0.010 |
's | +0.010 |
great | +0.010 |
Neg logit contributions | |
outage | -0.026 |
onna | -0.026 |
alk | -0.026 |
oons | -0.025 |
lights | -0.025 |
Token | ed |
Token ID | 276 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
onna | +0.249 |
outage | +0.242 |
lights | +0.235 |
oons | +0.234 |
alk | +0.232 |
Neg logit contributions | |
lucky | -0.077 |
good | -0.060 |
's | -0.056 |
dog | -0.055 |
, | -0.055 |
Token | his |
Token ID | 465 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
onna | +0.024 |
der | +0.024 |
ubs | +0.023 |
lights | +0.023 |
oons | +0.022 |
Neg logit contributions | |
lucky | -0.017 |
reward | -0.014 |
great | -0.013 |
job | -0.013 |
bye | -0.012 |
Token | knee |
Token ID | 10329 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
onna | +0.063 |
oons | +0.061 |
outage | +0.061 |
alk | +0.059 |
der | +0.059 |
Neg logit contributions | |
lucky | -0.054 |
good | -0.046 |
little | -0.045 |
dog | -0.045 |
great | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
onna | +0.061 |
oons | +0.060 |
alk | +0.060 |
outage | +0.059 |
lights | +0.058 |
Neg logit contributions | |
lucky | -0.039 |
good | -0.033 |
's | -0.033 |
little | -0.031 |
great | -0.031 |
Token | |
Token ID | 220 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
onna | +0.020 |
oons | +0.019 |
outage | +0.018 |
der | +0.018 |
alk | +0.018 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.007 |
great | -0.007 |
reward | -0.007 |
dog | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.63e-04 |
Pos logit contributions | |
onna | +0.011 |
oons | +0.010 |
outage | +0.010 |
der | +0.010 |
alk | +0.010 |
Neg logit contributions | |
lucky | -0.005 |
good | -0.004 |
great | -0.004 |
dog | -0.004 |
little | -0.003 |
Token | upset |
Token ID | 9247 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
onna | +0.000 |
outage | +0.000 |
oons | +0.000 |
der | +0.000 |
alk | +0.000 |
Neg logit contributions | |
lucky | -0.000 |
good | -0.000 |
great | -0.000 |
dog | -0.000 |
reward | -0.000 |
Token | because |
Token ID | 780 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
oons | +0.031 |
onna | +0.030 |
alk | +0.030 |
ands | +0.030 |
bench | +0.029 |
Neg logit contributions | |
lucky | -0.009 |
, | -0.007 |
at | -0.007 |
good | -0.006 |
little | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
onna | +0.011 |
oons | +0.011 |
outage | +0.011 |
alk | +0.011 |
der | +0.010 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.003 |
great | -0.003 |
dog | -0.003 |
little | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
onna | +0.075 |
oons | +0.073 |
outage | +0.073 |
alk | +0.072 |
der | +0.072 |
Neg logit contributions | |
lucky | -0.033 |
good | -0.025 |
great | -0.025 |
dog | -0.024 |
little | -0.023 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
lucky | +0.008 |
good | +0.006 |
great | +0.006 |
little | +0.006 |
's | +0.006 |
Neg logit contributions | |
oons | -0.016 |
onna | -0.015 |
lights | -0.015 |
outage | -0.015 |
alk | -0.015 |
Token | ed |
Token ID | 276 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
onna | +0.254 |
outage | +0.245 |
lights | +0.238 |
oons | +0.236 |
alk | +0.235 |
Neg logit contributions | |
lucky | -0.076 |
good | -0.058 |
's | -0.058 |
, | -0.057 |
at | -0.055 |
Token | his |
Token ID | 465 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
onna | +0.029 |
oons | +0.028 |
outage | +0.028 |
der | +0.028 |
alk | +0.028 |
Neg logit contributions | |
lucky | -0.016 |
good | -0.012 |
great | -0.012 |
dog | -0.012 |
's | -0.012 |
Token | knee |
Token ID | 10329 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
onna | +0.059 |
oons | +0.058 |
outage | +0.058 |
alk | +0.056 |
ubs | +0.055 |
Neg logit contributions | |
lucky | -0.059 |
little | -0.051 |
good | -0.050 |
dog | -0.049 |
great | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
onna | +0.078 |
oons | +0.077 |
outage | +0.076 |
alk | +0.075 |
ands | +0.074 |
Neg logit contributions | |
lucky | -0.037 |
good | -0.030 |
's | -0.030 |
great | -0.028 |
little | -0.028 |
Token | His |
Token ID | 2399 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
onna | +0.020 |
outage | +0.019 |
oons | +0.019 |
alk | +0.019 |
ands | +0.019 |
Neg logit contributions | |
lucky | -0.008 |
good | -0.006 |
great | -0.006 |
little | -0.006 |
dog | -0.006 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
lucky | +0.009 |
little | +0.007 |
good | +0.007 |
dog | +0.007 |
great | +0.007 |
Neg logit contributions | |
onna | -0.026 |
outage | -0.025 |
alk | -0.025 |
oons | -0.025 |
ands | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
onna | +0.038 |
oons | +0.037 |
outage | +0.036 |
lights | +0.036 |
der | +0.036 |
Neg logit contributions | |
lucky | -0.018 |
's | -0.014 |
good | -0.014 |
dog | -0.014 |
great | -0.013 |
Token | dirty |
Token ID | 11841 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
lucky | +0.012 |
good | +0.010 |
great | +0.009 |
dog | +0.009 |
's | +0.009 |
Neg logit contributions | |
onna | -0.023 |
outage | -0.022 |
oons | -0.022 |
der | -0.022 |
alk | -0.022 |
Token | clothes |
Token ID | 8242 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
onna | +0.038 |
outage | +0.036 |
alk | +0.035 |
oons | +0.034 |
ands | +0.034 |
Neg logit contributions | |
lucky | -0.018 |
dog | -0.018 |
little | -0.017 |
, | -0.017 |
's | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
lucky | +0.025 |
's | +0.021 |
good | +0.021 |
, | +0.020 |
at | +0.020 |
Neg logit contributions | |
onna | -0.051 |
alk | -0.049 |
oons | -0.049 |
outage | -0.049 |
ands | -0.048 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
lucky | +0.028 |
good | +0.024 |
dog | +0.023 |
little | +0.023 |
's | +0.023 |
Neg logit contributions | |
onna | -0.053 |
outage | -0.051 |
alk | -0.051 |
oons | -0.051 |
der | -0.050 |
Token | ed |
Token ID | 276 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
onna | +0.233 |
outage | +0.224 |
alk | +0.211 |
lights | +0.209 |
oons | +0.205 |
Neg logit contributions | |
lucky | -0.092 |
's | -0.085 |
good | -0.083 |
, | -0.081 |
at | -0.079 |
Token | knee |
Token ID | 10329 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
onna | +0.023 |
outage | +0.022 |
oons | +0.022 |
alk | +0.022 |
der | +0.022 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.012 |
great | -0.012 |
dog | -0.012 |
little | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
onna | +0.080 |
alk | +0.078 |
oons | +0.077 |
outage | +0.076 |
ware | +0.075 |
Neg logit contributions | |
lucky | -0.039 |
's | -0.034 |
good | -0.034 |
at | -0.033 |
, | -0.032 |
Token | She |
Token ID | 1375 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
lucky | +0.015 |
dog | +0.013 |
little | +0.012 |
's | +0.012 |
, | +0.012 |
Neg logit contributions | |
outage | -0.034 |
ands | -0.034 |
oons | -0.034 |
lights | -0.032 |
onna | -0.032 |
Token | sees |
Token ID | 7224 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
onna | +0.017 |
outage | +0.017 |
alk | +0.016 |
oons | +0.016 |
lights | +0.016 |
Neg logit contributions | |
lucky | -0.007 |
's | -0.006 |
good | -0.006 |
dog | -0.006 |
little | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +7.24e-03 |
Pos logit contributions | |
lucky | +0.017 |
good | +0.012 |
reward | +0.011 |
great | +0.011 |
bye | +0.011 |
Neg logit contributions | |
oons | -0.044 |
onna | -0.043 |
der | -0.042 |
alk | -0.042 |
outage | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
onna | +0.019 |
outage | +0.019 |
oons | +0.018 |
alk | +0.018 |
der | +0.018 |
Neg logit contributions | |
lucky | -0.006 |
great | -0.004 |
good | -0.004 |
little | -0.004 |
dog | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
's | +0.006 |
lucky | +0.006 |
turns | +0.006 |
rescued | +0.006 |
arrived | +0.006 |
Neg logit contributions | |
onna | -0.017 |
ware | -0.016 |
outage | -0.016 |
heavily | -0.015 |
hers | -0.015 |
Token | spider |
Token ID | 19230 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
lucky | +0.007 |
great | +0.005 |
reward | +0.005 |
's | +0.005 |
good | +0.005 |
Neg logit contributions | |
onna | -0.020 |
outage | -0.020 |
der | -0.019 |
oons | -0.019 |
alk | -0.019 |
Token | named |
Token ID | 3706 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
onna | +0.080 |
oons | +0.079 |
alk | +0.077 |
ands | +0.077 |
ubs | +0.077 |
Neg logit contributions | |
lucky | -0.029 |
's | -0.026 |
, | -0.025 |
dog | -0.025 |
at | -0.024 |
Token | Sp |
Token ID | 1338 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
lights | +0.059 |
oons | +0.057 |
outage | +0.057 |
der | +0.057 |
onna | +0.056 |
Neg logit contributions | |
lucky | -0.033 |
little | -0.028 |
dog | -0.026 |
good | -0.026 |
's | -0.026 |
Token | ide |
Token ID | 485 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
bars | +0.121 |
fray | +0.113 |
ulk | +0.110 |
pan | +0.110 |
numb | +0.107 |
Neg logit contributions | |
little | -0.166 |
's | -0.160 |
at | -0.158 |
, | -0.154 |
lucky | -0.153 |
Token | y |
Token ID | 88 |
Feature activation | +4.99e-03 |
Pos logit contributions | |
onna | +0.013 |
outage | +0.013 |
bench | +0.012 |
ands | +0.012 |
ubs | +0.012 |
Neg logit contributions | |
lucky | -0.013 |
, | -0.011 |
little | -0.011 |
at | -0.011 |
good | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
onna | +0.011 |
outage | +0.011 |
oons | +0.011 |
ubs | +0.011 |
ands | +0.011 |
Neg logit contributions | |
lucky | -0.005 |
, | -0.005 |
little | -0.005 |
dog | -0.005 |
's | -0.005 |
Token | Sp |
Token ID | 1338 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
lucky | +0.005 |
little | +0.005 |
, | +0.005 |
's | +0.005 |
good | +0.005 |
Neg logit contributions | |
outage | -0.009 |
oons | -0.009 |
ands | -0.009 |
bench | -0.009 |
lights | -0.009 |
Token | ide |
Token ID | 485 |
Feature activation | +3.60e-03 |
Pos logit contributions | |
bars | +0.113 |
pan | +0.104 |
fray | +0.103 |
ulk | +0.102 |
bench | +0.101 |
Neg logit contributions | |
lucky | -0.169 |
little | -0.166 |
at | -0.158 |
's | -0.158 |
, | -0.154 |
Token | that |
Token ID | 326 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
lucky | +0.003 |
good | +0.003 |
great | +0.003 |
dog | +0.002 |
little | +0.002 |
Neg logit contributions | |
onna | -0.008 |
oons | -0.008 |
outage | -0.008 |
alk | -0.008 |
der | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +4.75e-03 |
Pos logit contributions | |
onna | +0.007 |
oons | +0.007 |
outage | +0.007 |
alk | +0.007 |
der | +0.007 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.002 |
great | -0.002 |
dog | -0.002 |
little | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
onna | +0.012 |
oons | +0.011 |
der | +0.011 |
outage | +0.011 |
alk | +0.011 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.003 |
bye | -0.003 |
reward | -0.003 |
dog | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
onna | +0.005 |
oons | +0.005 |
outage | +0.005 |
alk | +0.005 |
der | +0.005 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.002 |
great | -0.002 |
dog | -0.002 |
little | -0.002 |
Token | tiny |
Token ID | 7009 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
onna | +0.017 |
outage | +0.016 |
alk | +0.015 |
oons | +0.015 |
der | +0.015 |
Neg logit contributions | |
lucky | -0.008 |
's | -0.006 |
good | -0.006 |
bye | -0.006 |
dog | -0.006 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
onna | +0.027 |
outage | +0.026 |
oons | +0.026 |
alk | +0.025 |
der | +0.025 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.012 |
great | -0.012 |
dog | -0.011 |
's | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
onna | +0.209 |
lights | +0.198 |
outage | +0.197 |
oons | +0.196 |
ands | +0.192 |
Neg logit contributions | |
lucky | -0.104 |
, | -0.098 |
's | -0.093 |
dog | -0.091 |
at | -0.091 |
Token | paper |
Token ID | 3348 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
onna | +0.013 |
oons | +0.012 |
outage | +0.012 |
alk | +0.012 |
der | +0.012 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.008 |
great | -0.007 |
dog | -0.007 |
little | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
onna | +0.012 |
oons | +0.011 |
outage | +0.011 |
alk | +0.011 |
der | +0.011 |
Neg logit contributions | |
lucky | -0.005 |
good | -0.004 |
great | -0.004 |
's | -0.004 |
dog | -0.004 |
Token | its |
Token ID | 663 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
outage | +0.078 |
onna | +0.078 |
oons | +0.078 |
lights | +0.076 |
der | +0.076 |
Neg logit contributions | |
lucky | -0.021 |
little | -0.017 |
good | -0.017 |
great | -0.016 |
dog | -0.015 |
Token | mouth |
Token ID | 5422 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
onna | +0.059 |
alk | +0.056 |
der | +0.055 |
outage | +0.054 |
ands | +0.053 |
Neg logit contributions | |
lucky | -0.049 |
good | -0.040 |
great | -0.040 |
dog | -0.039 |
arrived | -0.039 |
Token | ! |
Token ID | 0 |
Feature activation | +9.38e-03 |
Pos logit contributions | |
onna | +0.061 |
oons | +0.060 |
lights | +0.058 |
alk | +0.058 |
ands | +0.058 |
Neg logit contributions | |
lucky | -0.029 |
at | -0.028 |
's | -0.027 |
, | -0.026 |
dog | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
onna | +0.019 |
oons | +0.018 |
outage | +0.018 |
der | +0.017 |
alk | +0.017 |
Neg logit contributions | |
lucky | -0.013 |
good | -0.010 |
great | -0.010 |
reward | -0.010 |
dog | -0.010 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
onna | +0.038 |
oons | +0.037 |
outage | +0.037 |
der | +0.036 |
alk | +0.036 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.011 |
great | -0.011 |
dog | -0.011 |
reward | -0.010 |
Token | down |
Token ID | 866 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
oons | +0.060 |
onna | +0.058 |
alk | +0.058 |
ands | +0.057 |
outage | +0.057 |
Neg logit contributions | |
lucky | -0.011 |
, | -0.008 |
at | -0.008 |
good | -0.008 |
back | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +5.21e-04 |
Pos logit contributions | |
lucky | +0.011 |
good | +0.008 |
, | +0.008 |
great | +0.008 |
dog | +0.007 |
Neg logit contributions | |
oons | -0.035 |
onna | -0.035 |
outage | -0.034 |
alk | -0.034 |
lights | -0.034 |
Token | scrap |
Token ID | 15881 |
Feature activation | +9.54e-02 |
Pos logit contributions | |
onna | +0.001 |
outage | +0.001 |
der | +0.001 |
oons | +0.001 |
ubs | +0.001 |
Neg logit contributions | |
lucky | -0.001 |
great | -0.001 |
reward | -0.001 |
good | -0.001 |
dog | -0.001 |
Token | ed |
Token ID | 276 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
onna | +0.255 |
outage | +0.245 |
lights | +0.238 |
oons | +0.237 |
alk | +0.237 |
Neg logit contributions | |
lucky | -0.072 |
good | -0.053 |
at | -0.051 |
's | -0.051 |
, | -0.050 |
Token | his |
Token ID | 465 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
onna | +0.031 |
der | +0.030 |
oons | +0.030 |
ubs | +0.030 |
outage | +0.030 |
Neg logit contributions | |
lucky | -0.017 |
reward | -0.013 |
good | -0.013 |
great | -0.013 |
dog | -0.013 |
Token | knee |
Token ID | 10329 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
onna | +0.065 |
oons | +0.064 |
outage | +0.063 |
alk | +0.062 |
lights | +0.061 |
Neg logit contributions | |
lucky | -0.058 |
good | -0.050 |
little | -0.050 |
dog | -0.049 |
great | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
onna | +0.074 |
oons | +0.073 |
alk | +0.072 |
outage | +0.072 |
lights | +0.070 |
Neg logit contributions | |
lucky | -0.043 |
good | -0.037 |
's | -0.037 |
little | -0.035 |
great | -0.035 |
Token | O |
Token ID | 440 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
onna | +0.028 |
oons | +0.027 |
der | +0.027 |
outage | +0.026 |
alk | +0.026 |
Neg logit contributions | |
lucky | -0.014 |
good | -0.011 |
great | -0.011 |
reward | -0.011 |
dog | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +6.55e-05 |
Pos logit contributions | |
lucky | +0.027 |
reward | +0.021 |
bye | +0.020 |
good | +0.019 |
job | +0.019 |
Neg logit contributions | |
onna | -0.055 |
oons | -0.054 |
ide | -0.052 |
ubs | -0.052 |
alk | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
onna | +0.000 |
oons | +0.000 |
alk | +0.000 |
ubs | +0.000 |
outage | +0.000 |
Neg logit contributions | |
lucky | -0.000 |
reward | -0.000 |
good | -0.000 |
dog | -0.000 |
great | -0.000 |
Token | little |
Token ID | 1310 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
turns | +0.011 |
arrived | +0.011 |
's | +0.010 |
reward | +0.010 |
rescued | +0.010 |
Neg logit contributions | |
onna | -0.031 |
ware | -0.028 |
iky | -0.028 |
oons | -0.028 |
outage | -0.027 |
Token | spider |
Token ID | 19230 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
lucky | +0.010 |
arrived | +0.008 |
reward | +0.007 |
great | +0.007 |
's | +0.007 |
Neg logit contributions | |
onna | -0.022 |
outage | -0.021 |
oons | -0.021 |
ware | -0.021 |
der | -0.021 |
Token | named |
Token ID | 3706 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
onna | +0.068 |
oons | +0.068 |
alk | +0.066 |
ands | +0.066 |
reating | +0.066 |
Neg logit contributions | |
lucky | -0.015 |
, | -0.014 |
's | -0.013 |
dog | -0.013 |
at | -0.012 |
Token | Sp |
Token ID | 1338 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
lights | +0.052 |
outage | +0.051 |
oons | +0.051 |
der | +0.050 |
bench | +0.050 |
Neg logit contributions | |
lucky | -0.026 |
little | -0.022 |
's | -0.021 |
good | -0.021 |
dog | -0.021 |
Token | ide |
Token ID | 485 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
pan | +0.119 |
bars | +0.118 |
ulk | +0.118 |
fray | +0.112 |
bench | +0.107 |
Neg logit contributions | |
little | -0.169 |
's | -0.159 |
lucky | -0.157 |
at | -0.154 |
, | -0.151 |
Token | y |
Token ID | 88 |
Feature activation | +1.21e-03 |
Pos logit contributions | |
onna | +0.007 |
outage | +0.007 |
bench | +0.007 |
ands | +0.007 |
lights | +0.007 |
Neg logit contributions | |
lucky | -0.006 |
, | -0.005 |
at | -0.005 |
dog | -0.005 |
little | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
onna | +0.003 |
outage | +0.003 |
oons | +0.003 |
bench | +0.003 |
ands | +0.003 |
Neg logit contributions | |
, | -0.001 |
little | -0.001 |
lucky | -0.001 |
dog | -0.001 |
's | -0.001 |
Token | Sp |
Token ID | 1338 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
lucky | +0.009 |
good | +0.008 |
, | +0.008 |
little | +0.007 |
's | +0.007 |
Neg logit contributions | |
outage | -0.013 |
oons | -0.012 |
bench | -0.012 |
lights | -0.012 |
der | -0.012 |
Token | ide |
Token ID | 485 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
bars | +0.109 |
pan | +0.108 |
ulk | +0.103 |
fray | +0.101 |
bench | +0.100 |
Neg logit contributions | |
lucky | -0.169 |
little | -0.167 |
at | -0.158 |
's | -0.158 |
, | -0.152 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
onna | +0.018 |
outage | +0.017 |
lights | +0.017 |
der | +0.017 |
oons | +0.017 |
Neg logit contributions | |
lucky | -0.006 |
loyal | -0.003 |
dog | -0.003 |
good | -0.003 |
je | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
lucky | +0.013 |
arrived | +0.010 |
great | +0.010 |
's | +0.010 |
job | +0.009 |
Neg logit contributions | |
onna | -0.024 |
der | -0.024 |
lights | -0.023 |
outage | -0.023 |
ubs | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
lucky | +0.003 |
good | +0.002 |
great | +0.002 |
dog | +0.002 |
little | +0.002 |
Neg logit contributions | |
onna | -0.006 |
outage | -0.006 |
oons | -0.006 |
der | -0.006 |
alk | -0.006 |
Token | we |
Token ID | 356 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
lucky | +0.033 |
mis | +0.031 |
job | +0.030 |
arrived | +0.030 |
great | +0.029 |
Neg logit contributions | |
outage | -0.039 |
onna | -0.039 |
pan | -0.036 |
der | -0.036 |
reating | -0.035 |
Token | 're |
Token ID | 821 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
lucky | +0.013 |
loyal | +0.009 |
dog | +0.009 |
bye | +0.009 |
little | +0.009 |
Neg logit contributions | |
onna | -0.027 |
outage | -0.026 |
oons | -0.025 |
ubs | -0.025 |
alk | -0.025 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
lucky | +0.036 |
reward | +0.035 |
arrived | +0.032 |
turns | +0.031 |
je | +0.030 |
Neg logit contributions | |
onna | -0.078 |
ubs | -0.076 |
outage | -0.075 |
hers | -0.074 |
pan | -0.073 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
lucky | +0.141 |
good | +0.116 |
great | +0.114 |
dog | +0.112 |
little | +0.110 |
Neg logit contributions | |
onna | -0.190 |
outage | -0.181 |
oons | -0.181 |
alk | -0.178 |
der | -0.177 |
Token | Tim |
Token ID | 5045 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
onna | +0.031 |
der | +0.029 |
ubs | +0.029 |
oons | +0.029 |
alk | +0.029 |
Neg logit contributions | |
lucky | -0.015 |
great | -0.011 |
good | -0.011 |
reward | -0.011 |
best | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
onna | +0.024 |
oons | +0.024 |
alk | +0.024 |
outage | +0.024 |
lights | +0.024 |
Neg logit contributions | |
lucky | -0.008 |
's | -0.006 |
dog | -0.006 |
good | -0.006 |
little | -0.005 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
lucky | +0.053 |
good | +0.042 |
great | +0.042 |
's | +0.039 |
reward | +0.039 |
Neg logit contributions | |
onna | -0.087 |
oons | -0.083 |
outage | -0.082 |
der | -0.082 |
alk | -0.081 |
Token | shout |
Token ID | 9191 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
lucky | +0.002 |
good | +0.002 |
great | +0.002 |
loyal | +0.002 |
reward | +0.002 |
Neg logit contributions | |
onna | -0.005 |
outage | -0.005 |
oons | -0.005 |
alk | -0.005 |
der | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
onna | +0.009 |
oons | +0.009 |
outage | +0.009 |
der | +0.009 |
alk | +0.009 |
Neg logit contributions | |
lucky | -0.002 |
great | -0.001 |
good | -0.001 |
dog | -0.001 |
's | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
lucky | +0.012 |
arrived | +0.011 |
turns | +0.010 |
great | +0.010 |
job | +0.010 |
Neg logit contributions | |
der | -0.025 |
onna | -0.024 |
lights | -0.023 |
outage | -0.022 |
pan | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
lucky | +0.002 |
good | +0.002 |
's | +0.002 |
dog | +0.002 |
, | +0.002 |
Neg logit contributions | |
onna | -0.004 |
oons | -0.004 |
alk | -0.004 |
der | -0.004 |
outage | -0.004 |
Token | We |
Token ID | 775 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
lucky | +0.050 |
great | +0.044 |
good | +0.042 |
arrived | +0.040 |
little | +0.040 |
Neg logit contributions | |
onna | -0.059 |
der | -0.056 |
outage | -0.055 |
lights | -0.052 |
alk | -0.050 |
Token | are |
Token ID | 389 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
lucky | +0.021 |
dog | +0.015 |
little | +0.015 |
loyal | +0.015 |
good | +0.015 |
Neg logit contributions | |
onna | -0.045 |
alk | -0.043 |
outage | -0.043 |
oons | -0.043 |
ubs | -0.042 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
reward | +0.029 |
lucky | +0.029 |
arrived | +0.027 |
turns | +0.026 |
dog | +0.026 |
Neg logit contributions | |
onna | -0.080 |
ubs | -0.077 |
hers | -0.076 |
outage | -0.074 |
pan | -0.073 |
Token | ," |
Token ID | 553 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
lucky | +0.133 |
good | +0.108 |
great | +0.106 |
dog | +0.104 |
little | +0.102 |
Neg logit contributions | |
onna | -0.197 |
oons | -0.190 |
outage | -0.189 |
der | -0.186 |
alk | -0.186 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
onna | +0.059 |
der | +0.055 |
oons | +0.055 |
alk | +0.055 |
ubs | +0.054 |
Neg logit contributions | |
lucky | -0.045 |
great | -0.036 |
job | -0.035 |
good | -0.035 |
reward | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
onna | +0.038 |
oons | +0.037 |
outage | +0.037 |
der | +0.036 |
alk | +0.036 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.011 |
great | -0.011 |
dog | -0.011 |
little | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
lucky | +0.015 |
good | +0.013 |
's | +0.013 |
little | +0.012 |
great | +0.012 |
Neg logit contributions | |
onna | -0.022 |
oons | -0.021 |
outage | -0.021 |
alk | -0.021 |
der | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
outage | +0.016 |
oons | +0.016 |
onna | +0.016 |
ands | +0.016 |
alk | +0.015 |
Neg logit contributions | |
lucky | -0.004 |
dog | -0.003 |
good | -0.003 |
little | -0.003 |
, | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
onna | +0.051 |
oons | +0.049 |
outage | +0.048 |
der | +0.048 |
alk | +0.048 |
Neg logit contributions | |
lucky | -0.010 |
great | -0.005 |
good | -0.005 |
dog | -0.005 |
's | -0.004 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
lucky | +0.009 |
great | +0.007 |
arrived | +0.007 |
je | +0.007 |
job | +0.007 |
Neg logit contributions | |
onna | -0.015 |
der | -0.015 |
oons | -0.014 |
lights | -0.014 |
outage | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.001 |
great | +0.001 |
dog | +0.001 |
's | +0.001 |
Neg logit contributions | |
onna | -0.003 |
oons | -0.003 |
outage | -0.003 |
der | -0.003 |
alk | -0.003 |
Token | we |
Token ID | 356 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
lucky | +0.024 |
arrived | +0.020 |
mis | +0.020 |
job | +0.020 |
great | +0.020 |
Neg logit contributions | |
onna | -0.037 |
der | -0.036 |
outage | -0.035 |
pan | -0.034 |
oons | -0.033 |
Token | are |
Token ID | 389 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
lucky | +0.010 |
good | +0.006 |
dog | +0.006 |
great | +0.006 |
little | +0.006 |
Neg logit contributions | |
onna | -0.028 |
oons | -0.027 |
outage | -0.027 |
alk | -0.027 |
der | -0.027 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
lucky | +0.034 |
dog | +0.028 |
reward | +0.027 |
's | +0.026 |
bye | +0.026 |
Neg logit contributions | |
onna | -0.083 |
oons | -0.078 |
ubs | -0.078 |
outage | -0.078 |
der | -0.076 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
lucky | +0.149 |
good | +0.126 |
great | +0.122 |
dog | +0.121 |
's | +0.121 |
Neg logit contributions | |
onna | -0.178 |
oons | -0.177 |
der | -0.173 |
outage | -0.173 |
alk | -0.171 |
Token | Anna |
Token ID | 11735 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
onna | +0.025 |
oons | +0.024 |
der | +0.023 |
outage | +0.023 |
alk | +0.023 |
Neg logit contributions | |
lucky | -0.020 |
great | -0.016 |
good | -0.016 |
reward | -0.015 |
job | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
onna | +0.031 |
oons | +0.031 |
outage | +0.030 |
alk | +0.030 |
der | +0.030 |
Neg logit contributions | |
lucky | -0.012 |
good | -0.009 |
's | -0.008 |
dog | -0.008 |
great | -0.008 |
Token | Ben |
Token ID | 3932 |
Feature activation | -5.88e-04 |
Pos logit contributions | |
lucky | +0.053 |
great | +0.043 |
good | +0.043 |
reward | +0.040 |
best | +0.040 |
Neg logit contributions | |
onna | -0.072 |
der | -0.068 |
oons | -0.068 |
alk | -0.066 |
outage | -0.066 |
Token | say |
Token ID | 910 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.000 |
great | +0.000 |
loyal | +0.000 |
fine | +0.000 |
Neg logit contributions | |
onna | -0.001 |
oons | -0.001 |
alk | -0.001 |
outage | -0.001 |
der | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.35e-03 |
Pos logit contributions | |
onna | +0.035 |
oons | +0.034 |
outage | +0.034 |
der | +0.034 |
lights | +0.034 |
Neg logit contributions | |
lucky | -0.008 |
great | -0.004 |
good | -0.004 |
dog | -0.004 |
loyal | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
lucky | +0.004 |
arrived | +0.003 |
great | +0.003 |
's | +0.003 |
job | +0.003 |
Neg logit contributions | |
onna | -0.009 |
der | -0.009 |
lights | -0.009 |
outage | -0.009 |
pan | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
onna | +0.009 |
oons | +0.009 |
outage | +0.009 |
der | +0.009 |
alk | +0.009 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.003 |
great | -0.003 |
dog | -0.003 |
little | -0.003 |
Token | we |
Token ID | 356 |
Feature activation | -9.62e-03 |
Pos logit contributions | |
lucky | +0.023 |
mis | +0.021 |
job | +0.020 |
arrived | +0.020 |
great | +0.020 |
Neg logit contributions | |
onna | -0.031 |
outage | -0.030 |
pan | -0.029 |
der | -0.029 |
reating | -0.027 |
Token | are |
Token ID | 389 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
lucky | +0.009 |
dog | +0.006 |
loyal | +0.006 |
good | +0.006 |
little | +0.006 |
Neg logit contributions | |
onna | -0.022 |
outage | -0.021 |
oons | -0.021 |
alk | -0.021 |
ubs | -0.021 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
lucky | +0.035 |
reward | +0.027 |
dog | +0.027 |
great | +0.026 |
's | +0.026 |
Neg logit contributions | |
onna | -0.077 |
outage | -0.073 |
oons | -0.073 |
ubs | -0.072 |
der | -0.071 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
lucky | +0.148 |
good | +0.125 |
great | +0.121 |
dog | +0.121 |
's | +0.120 |
Neg logit contributions | |
onna | -0.175 |
oons | -0.175 |
der | -0.172 |
outage | -0.170 |
alk | -0.169 |
Token | they |
Token ID | 484 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
onna | +0.038 |
oons | +0.036 |
der | +0.036 |
outage | +0.036 |
alk | +0.035 |
Neg logit contributions | |
lucky | -0.021 |
great | -0.016 |
good | -0.016 |
's | -0.015 |
reward | -0.015 |
Token | say |
Token ID | 910 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
onna | +0.085 |
oons | +0.082 |
outage | +0.082 |
alk | +0.081 |
ubs | +0.080 |
Neg logit contributions | |
lucky | -0.037 |
great | -0.026 |
good | -0.026 |
reward | -0.025 |
loyal | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
lucky | +0.051 |
good | +0.043 |
great | +0.042 |
dog | +0.041 |
's | +0.041 |
Neg logit contributions | |
onna | -0.065 |
oons | -0.062 |
outage | -0.062 |
alk | -0.061 |
der | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | +3.04e-03 |
Pos logit contributions | |
onna | +0.026 |
oons | +0.026 |
outage | +0.025 |
alk | +0.025 |
der | +0.025 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.006 |
dog | -0.006 |
little | -0.006 |
great | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -4.58e-03 |
Pos logit contributions | |
onna | +0.068 |
oons | +0.066 |
outage | +0.066 |
der | +0.065 |
alk | +0.065 |
Neg logit contributions | |
lucky | -0.014 |
good | -0.007 |
great | -0.007 |
dog | -0.007 |
loyal | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
lucky | +0.005 |
arrived | +0.004 |
great | +0.004 |
good | +0.004 |
's | +0.004 |
Neg logit contributions | |
onna | -0.010 |
der | -0.009 |
outage | -0.009 |
lights | -0.009 |
oons | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
onna | +0.016 |
oons | +0.016 |
outage | +0.016 |
alk | +0.016 |
der | +0.016 |
Neg logit contributions | |
lucky | -0.005 |
good | -0.004 |
dog | -0.004 |
great | -0.004 |
's | -0.004 |
Token | we |
Token ID | 356 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
lucky | +0.025 |
mis | +0.022 |
arrived | +0.022 |
great | +0.021 |
job | +0.021 |
Neg logit contributions | |
onna | -0.032 |
outage | -0.032 |
der | -0.030 |
pan | -0.030 |
reating | -0.028 |
Token | 're |
Token ID | 821 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
lucky | +0.008 |
good | +0.006 |
dog | +0.006 |
great | +0.006 |
little | +0.005 |
Neg logit contributions | |
onna | -0.021 |
oons | -0.020 |
outage | -0.020 |
alk | -0.020 |
der | -0.020 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.63e-02 |
Pos logit contributions | |
lucky | +0.037 |
reward | +0.033 |
dog | +0.032 |
arrived | +0.032 |
's | +0.031 |
Neg logit contributions | |
onna | -0.072 |
ubs | -0.070 |
outage | -0.069 |
hers | -0.067 |
oons | -0.067 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
lucky | +0.106 |
good | +0.082 |
great | +0.080 |
dog | +0.079 |
's | +0.077 |
Neg logit contributions | |
onna | -0.215 |
oons | -0.210 |
outage | -0.207 |
der | -0.207 |
alk | -0.206 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
onna | +0.040 |
oons | +0.038 |
alk | +0.038 |
outage | +0.038 |
der | +0.038 |
Neg logit contributions | |
lucky | -0.021 |
good | -0.016 |
great | -0.016 |
reward | -0.016 |
dog | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
onna | +0.046 |
oons | +0.045 |
outage | +0.045 |
alk | +0.044 |
lights | +0.044 |
Neg logit contributions | |
lucky | -0.015 |
's | -0.011 |
good | -0.011 |
dog | -0.010 |
little | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
lucky | +0.014 |
good | +0.012 |
's | +0.011 |
little | +0.011 |
great | +0.011 |
Neg logit contributions | |
onna | -0.020 |
oons | -0.020 |
outage | -0.020 |
alk | -0.019 |
der | -0.019 |
Token | turning |
Token ID | 6225 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
onna | +0.035 |
der | +0.034 |
outage | +0.033 |
pan | +0.033 |
oons | +0.032 |
Neg logit contributions | |
lucky | -0.027 |
great | -0.023 |
good | -0.022 |
reward | -0.022 |
job | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
onna | +0.026 |
outage | +0.025 |
der | +0.025 |
oons | +0.025 |
lights | +0.025 |
Neg logit contributions | |
lucky | -0.007 |
dog | -0.004 |
great | -0.004 |
je | -0.003 |
good | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +7.35e-03 |
Pos logit contributions | |
lucky | +0.018 |
arrived | +0.015 |
rescued | +0.015 |
great | +0.014 |
job | +0.014 |
Neg logit contributions | |
onna | -0.028 |
der | -0.027 |
lights | -0.026 |
outage | -0.025 |
reating | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
onna | +0.018 |
oons | +0.017 |
alk | +0.017 |
outage | +0.017 |
der | +0.017 |
Neg logit contributions | |
lucky | -0.007 |
good | -0.005 |
's | -0.005 |
dog | -0.005 |
great | -0.005 |
Token | we |
Token ID | 356 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
lucky | +0.030 |
rescued | +0.026 |
mis | +0.026 |
arrived | +0.026 |
job | +0.025 |
Neg logit contributions | |
onna | -0.042 |
der | -0.039 |
outage | -0.039 |
reating | -0.037 |
pan | -0.037 |
Token | are |
Token ID | 389 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
lucky | +0.008 |
dog | +0.006 |
loyal | +0.005 |
good | +0.005 |
little | +0.005 |
Neg logit contributions | |
onna | -0.018 |
oons | -0.018 |
outage | -0.018 |
alk | -0.017 |
der | -0.017 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
lucky | +0.028 |
reward | +0.021 |
dog | +0.021 |
's | +0.020 |
great | +0.020 |
Neg logit contributions | |
onna | -0.081 |
oons | -0.077 |
outage | -0.076 |
ubs | -0.076 |
der | -0.076 |
Token | ." |
Token ID | 526 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
lucky | +0.129 |
good | +0.106 |
great | +0.103 |
dog | +0.102 |
's | +0.100 |
Neg logit contributions | |
onna | -0.191 |
oons | -0.187 |
outage | -0.184 |
der | -0.183 |
alk | -0.183 |
Token |
|
Token ID | 198 |
Feature activation | -1.53e-03 |
Pos logit contributions | |
onna | +0.053 |
oons | +0.051 |
outage | +0.051 |
alk | +0.051 |
der | +0.051 |
Neg logit contributions | |
lucky | -0.023 |
good | -0.017 |
great | -0.017 |
dog | -0.016 |
little | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -5.85e-03 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.001 |
little | +0.001 |
dog | +0.001 |
great | +0.001 |
Neg logit contributions | |
outage | -0.004 |
onna | -0.004 |
der | -0.004 |
ware | -0.004 |
alk | -0.004 |
Token | They |
Token ID | 2990 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
lucky | +0.011 |
great | +0.009 |
good | +0.009 |
dog | +0.009 |
reward | +0.009 |
Neg logit contributions | |
onna | -0.009 |
oons | -0.008 |
outage | -0.008 |
ubs | -0.008 |
der | -0.008 |
Token | take |
Token ID | 1011 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
lucky | +0.002 |
loyal | +0.001 |
good | +0.001 |
best | +0.001 |
great | +0.001 |
Neg logit contributions | |
onna | -0.003 |
oons | -0.003 |
alk | -0.003 |
der | -0.003 |
ands | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
onna | +0.064 |
oons | +0.062 |
outage | +0.062 |
der | +0.061 |
alk | +0.061 |
Neg logit contributions | |
lucky | -0.010 |
good | -0.005 |
great | -0.004 |
dog | -0.004 |
's | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
lucky | +0.007 |
arrived | +0.006 |
rescued | +0.006 |
job | +0.006 |
great | +0.006 |
Neg logit contributions | |
der | -0.011 |
outage | -0.011 |
onna | -0.011 |
lights | -0.011 |
reating | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
onna | +0.014 |
oons | +0.014 |
alk | +0.014 |
outage | +0.014 |
der | +0.014 |
Neg logit contributions | |
lucky | -0.006 |
good | -0.005 |
's | -0.005 |
dog | -0.005 |
great | -0.004 |
Token | we |
Token ID | 356 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
lucky | +0.026 |
mis | +0.022 |
arrived | +0.022 |
rescued | +0.022 |
job | +0.022 |
Neg logit contributions | |
onna | -0.038 |
outage | -0.037 |
der | -0.037 |
pan | -0.034 |
reating | -0.034 |
Token | 're |
Token ID | 821 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
lucky | +0.007 |
good | +0.005 |
dog | +0.005 |
great | +0.005 |
little | +0.005 |
Neg logit contributions | |
onna | -0.018 |
oons | -0.017 |
outage | -0.017 |
alk | -0.017 |
der | -0.017 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
lucky | +0.029 |
reward | +0.023 |
dog | +0.023 |
's | +0.022 |
great | +0.021 |
Neg logit contributions | |
onna | -0.078 |
ubs | -0.074 |
oons | -0.074 |
outage | -0.074 |
der | -0.073 |
Token | ," |
Token ID | 553 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
lucky | +0.108 |
good | +0.086 |
great | +0.082 |
dog | +0.081 |
's | +0.081 |
Neg logit contributions | |
onna | -0.211 |
oons | -0.209 |
der | -0.205 |
outage | -0.205 |
alk | -0.203 |
Token | they |
Token ID | 484 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
onna | +0.081 |
der | +0.077 |
oons | +0.077 |
lights | +0.076 |
outage | +0.076 |
Neg logit contributions | |
lucky | -0.038 |
great | -0.029 |
good | -0.028 |
job | -0.028 |
reward | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
onna | +0.104 |
oons | +0.101 |
outage | +0.101 |
der | +0.100 |
alk | +0.100 |
Neg logit contributions | |
lucky | -0.037 |
good | -0.026 |
great | -0.026 |
dog | -0.025 |
little | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
lucky | +0.015 |
good | +0.012 |
's | +0.012 |
great | +0.012 |
little | +0.012 |
Neg logit contributions | |
onna | -0.020 |
outage | -0.019 |
oons | -0.019 |
alk | -0.019 |
der | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
onna | +0.025 |
oons | +0.024 |
outage | +0.024 |
alk | +0.024 |
der | +0.024 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.007 |
dog | -0.006 |
great | -0.006 |
little | -0.006 |
Token | say |
Token ID | 910 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
onna | +0.083 |
oons | +0.080 |
alk | +0.079 |
outage | +0.079 |
der | +0.078 |
Neg logit contributions | |
lucky | -0.034 |
good | -0.023 |
great | -0.023 |
loyal | -0.022 |
dog | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +7.39e-03 |
Pos logit contributions | |
lucky | +0.051 |
good | +0.043 |
great | +0.042 |
dog | +0.041 |
's | +0.041 |
Neg logit contributions | |
onna | -0.066 |
oons | -0.064 |
outage | -0.064 |
alk | -0.063 |
der | -0.062 |
Token | " |
Token ID | 366 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
onna | +0.018 |
oons | +0.017 |
outage | +0.017 |
alk | +0.017 |
der | +0.017 |
Neg logit contributions | |
lucky | -0.007 |
good | -0.005 |
dog | -0.005 |
great | -0.005 |
little | -0.005 |
Token | We |
Token ID | 1135 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
onna | +0.049 |
oons | +0.047 |
outage | +0.046 |
alk | +0.046 |
der | +0.046 |
Neg logit contributions | |
lucky | -0.041 |
good | -0.035 |
great | -0.034 |
dog | -0.034 |
little | -0.033 |
Token | are |
Token ID | 389 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
lucky | +0.024 |
bye | +0.017 |
loyal | +0.017 |
dog | +0.017 |
little | +0.017 |
Neg logit contributions | |
onna | -0.049 |
oons | -0.047 |
alk | -0.047 |
outage | -0.046 |
ubs | -0.045 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
arrived | +0.028 |
lucky | +0.026 |
reward | +0.026 |
je | +0.025 |
's | +0.024 |
Neg logit contributions | |
onna | -0.062 |
hers | -0.060 |
ubs | -0.059 |
oons | -0.057 |
ills | -0.056 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
lucky | +0.113 |
good | +0.087 |
great | +0.087 |
dog | +0.084 |
reward | +0.082 |
Neg logit contributions | |
onna | -0.206 |
outage | -0.197 |
oons | -0.196 |
alk | -0.193 |
der | -0.193 |
Token |
|
Token ID | 198 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
onna | +0.054 |
oons | +0.053 |
outage | +0.053 |
ware | +0.052 |
alk | +0.052 |
Neg logit contributions | |
lucky | -0.012 |
good | -0.008 |
little | -0.008 |
, | -0.008 |
dog | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
ware | +0.023 |
der | +0.023 |
onna | +0.022 |
outage | +0.022 |
pan | +0.022 |
Neg logit contributions | |
lucky | -0.003 |
little | -0.002 |
good | -0.002 |
, | -0.001 |
dog | -0.001 |
Token | They |
Token ID | 2990 |
Feature activation | -2.93e-05 |
Pos logit contributions | |
onna | +0.004 |
der | +0.003 |
oons | +0.003 |
alk | +0.003 |
outage | +0.003 |
Neg logit contributions | |
lucky | -0.003 |
good | -0.002 |
great | -0.002 |
dog | -0.002 |
little | -0.002 |
Token | leave |
Token ID | 2666 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
lucky | +0.000 |
loyal | +0.000 |
good | +0.000 |
best | +0.000 |
great | +0.000 |
Neg logit contributions | |
onna | -0.000 |
oons | -0.000 |
alk | -0.000 |
outage | -0.000 |
ands | -0.000 |
Token | get |
Token ID | 651 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
onna | +0.004 |
outage | +0.003 |
alk | +0.003 |
oons | +0.003 |
ware | +0.003 |
Neg logit contributions | |
lucky | -0.002 |
loyal | -0.001 |
bye | -0.001 |
good | -0.001 |
great | -0.001 |
Token | there |
Token ID | 612 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
lucky | +0.036 |
great | +0.028 |
good | +0.027 |
dog | +0.027 |
reward | +0.026 |
Neg logit contributions | |
onna | -0.078 |
oons | -0.075 |
outage | -0.074 |
alk | -0.073 |
der | -0.073 |
Token | ? |
Token ID | 30 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
lucky | +0.027 |
, | +0.026 |
good | +0.025 |
at | +0.025 |
great | +0.024 |
Neg logit contributions | |
oons | -0.029 |
outage | -0.029 |
der | -0.029 |
onna | -0.028 |
lights | -0.028 |
Token | I |
Token ID | 314 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
lucky | +0.044 |
great | +0.038 |
good | +0.037 |
job | +0.036 |
little | +0.035 |
Neg logit contributions | |
onna | -0.051 |
outage | -0.048 |
der | -0.047 |
oons | -0.046 |
alk | -0.044 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
onna | +0.009 |
outage | +0.008 |
alk | +0.008 |
ubs | +0.008 |
oons | +0.008 |
Neg logit contributions | |
lucky | -0.005 |
bye | -0.004 |
dog | -0.004 |
little | -0.004 |
loyal | -0.003 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
onna | +0.030 |
outage | +0.028 |
ubs | +0.028 |
der | +0.028 |
oons | +0.028 |
Neg logit contributions | |
lucky | -0.009 |
reward | -0.007 |
dog | -0.007 |
's | -0.007 |
great | -0.007 |
Token | right |
Token ID | 826 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
lucky | +0.087 |
good | +0.065 |
dog | +0.062 |
little | +0.061 |
's | +0.060 |
Neg logit contributions | |
oons | -0.232 |
onna | -0.229 |
der | -0.228 |
outage | -0.225 |
alk | -0.223 |
Token | now |
Token ID | 783 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
lucky | +0.023 |
at | +0.021 |
, | +0.021 |
back | +0.020 |
good | +0.019 |
Neg logit contributions | |
onna | -0.050 |
oons | -0.050 |
alk | -0.049 |
outage | -0.049 |
ubs | -0.048 |
Token | ," |
Token ID | 553 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
oons | +0.004 |
onna | +0.004 |
alk | +0.004 |
outage | +0.004 |
lights | +0.004 |
Neg logit contributions | |
, | -0.003 |
lucky | -0.002 |
at | -0.002 |
good | -0.002 |
's | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +7.38e-04 |
Pos logit contributions | |
onna | +0.070 |
oons | +0.067 |
outage | +0.067 |
der | +0.066 |
alk | +0.066 |
Neg logit contributions | |
lucky | -0.027 |
good | -0.019 |
great | -0.019 |
dog | -0.018 |
's | -0.017 |
Token | woman |
Token ID | 2415 |
Feature activation | -3.76e-03 |
Pos logit contributions | |
onna | +0.002 |
oons | +0.002 |
outage | +0.001 |
der | +0.001 |
alk | +0.001 |
Neg logit contributions | |
lucky | -0.001 |
good | -0.001 |
great | -0.001 |
dog | -0.001 |
little | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.88e-03 |
Pos logit contributions | |
lucky | +0.021 |
good | +0.017 |
great | +0.017 |
dog | +0.017 |
's | +0.016 |
Neg logit contributions | |
onna | -0.030 |
oons | -0.029 |
outage | -0.029 |
alk | -0.028 |
der | -0.028 |
Token | boys |
Token ID | 6510 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
lucky | +0.006 |
arrived | +0.005 |
's | +0.005 |
bey | +0.005 |
turns | +0.005 |
Neg logit contributions | |
onna | -0.009 |
der | -0.008 |
outage | -0.008 |
reating | -0.008 |
pan | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
lucky | +0.034 |
great | +0.027 |
good | +0.027 |
loyal | +0.027 |
reward | +0.026 |
Neg logit contributions | |
onna | -0.039 |
oons | -0.037 |
outage | -0.036 |
alk | -0.035 |
der | -0.035 |
Token | You |
Token ID | 921 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
lucky | +0.038 |
great | +0.033 |
good | +0.031 |
best | +0.031 |
reward | +0.030 |
Neg logit contributions | |
onna | -0.048 |
der | -0.046 |
outage | -0.045 |
oons | -0.044 |
alk | -0.043 |
Token | are |
Token ID | 389 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
lucky | +0.042 |
bye | +0.032 |
loyal | +0.032 |
best | +0.030 |
fine | +0.030 |
Neg logit contributions | |
onna | -0.076 |
outage | -0.075 |
oons | -0.072 |
ands | -0.072 |
alk | -0.071 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
arrived | +0.048 |
bye | +0.048 |
oc | +0.047 |
Sorry | +0.046 |
reward | +0.045 |
Neg logit contributions | |
hers | -0.070 |
onna | -0.066 |
ands | -0.061 |
outage | -0.060 |
ubs | -0.059 |
Token | with |
Token ID | 351 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
lucky | +0.102 |
good | +0.078 |
great | +0.076 |
dog | +0.074 |
little | +0.073 |
Neg logit contributions | |
onna | -0.216 |
oons | -0.209 |
outage | -0.208 |
der | -0.206 |
alk | -0.206 |
Token | me |
Token ID | 502 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
lucky | +0.040 |
good | +0.031 |
great | +0.030 |
dog | +0.030 |
's | +0.029 |
Neg logit contributions | |
onna | -0.078 |
oons | -0.075 |
outage | -0.075 |
der | -0.074 |
alk | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
lucky | +0.018 |
good | +0.015 |
great | +0.015 |
's | +0.015 |
dog | +0.015 |
Neg logit contributions | |
onna | -0.021 |
oons | -0.020 |
outage | -0.020 |
alk | -0.020 |
der | -0.020 |
Token | You |
Token ID | 921 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
lucky | +0.043 |
great | +0.037 |
good | +0.035 |
little | +0.034 |
reward | +0.034 |
Neg logit contributions | |
onna | -0.056 |
outage | -0.053 |
der | -0.052 |
oons | -0.051 |
ubs | -0.050 |
Token | are |
Token ID | 389 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
lucky | +0.039 |
bye | +0.030 |
loyal | +0.029 |
fine | +0.028 |
great | +0.028 |
Neg logit contributions | |
outage | -0.073 |
onna | -0.072 |
oons | -0.070 |
ands | -0.069 |
alk | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
onna | +0.022 |
oons | +0.021 |
outage | +0.021 |
der | +0.021 |
alk | +0.021 |
Neg logit contributions | |
lucky | -0.007 |
good | -0.005 |
great | -0.005 |
dog | -0.005 |
little | -0.005 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
lucky | +0.070 |
great | +0.062 |
reward | +0.060 |
good | +0.057 |
best | +0.056 |
Neg logit contributions | |
onna | -0.083 |
der | -0.078 |
ubs | -0.077 |
oons | -0.075 |
outage | -0.074 |
Token | ! |
Token ID | 0 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
lucky | +0.002 |
great | +0.002 |
reward | +0.002 |
good | +0.002 |
bye | +0.002 |
Neg logit contributions | |
onna | -0.004 |
outage | -0.004 |
oons | -0.004 |
der | -0.004 |
alk | -0.004 |
Token | I |
Token ID | 314 |
Feature activation | +5.15e-03 |
Pos logit contributions | |
lucky | +0.047 |
great | +0.037 |
good | +0.037 |
reward | +0.036 |
best | +0.034 |
Neg logit contributions | |
onna | -0.082 |
outage | -0.078 |
der | -0.078 |
oons | -0.078 |
alk | -0.077 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
onna | +0.011 |
outage | +0.011 |
ubs | +0.010 |
oons | +0.010 |
alk | +0.010 |
Neg logit contributions | |
lucky | -0.006 |
bye | -0.005 |
good | -0.005 |
little | -0.004 |
loyal | -0.004 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
onna | +0.029 |
outage | +0.028 |
ubs | +0.028 |
der | +0.027 |
pan | +0.027 |
Neg logit contributions | |
lucky | -0.013 |
reward | -0.013 |
arrived | -0.012 |
bye | -0.011 |
dog | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
lucky | +0.112 |
good | +0.087 |
great | +0.086 |
dog | +0.083 |
little | +0.082 |
Neg logit contributions | |
onna | -0.203 |
outage | -0.194 |
oons | -0.192 |
alk | -0.190 |
der | -0.189 |
Token | get |
Token ID | 651 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
lucky | +0.013 |
best | +0.010 |
's | +0.009 |
good | +0.009 |
great | +0.009 |
Neg logit contributions | |
onna | -0.030 |
alk | -0.028 |
ubs | -0.028 |
outage | -0.028 |
ands | -0.027 |
Token | you |
Token ID | 345 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
lucky | +0.018 |
great | +0.013 |
reward | +0.013 |
dog | +0.013 |
little | +0.013 |
Neg logit contributions | |
onna | -0.040 |
outage | -0.038 |
oons | -0.038 |
ubs | -0.037 |
lights | -0.037 |
Token | !" |
Token ID | 2474 |
Feature activation | +9.84e-03 |
Pos logit contributions | |
lucky | +0.028 |
good | +0.023 |
great | +0.022 |
dog | +0.022 |
little | +0.021 |
Neg logit contributions | |
onna | -0.042 |
oons | -0.041 |
outage | -0.040 |
der | -0.040 |
alk | -0.040 |
Token | she |
Token ID | 673 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
onna | +0.022 |
oons | +0.022 |
outage | +0.021 |
alk | +0.021 |
der | +0.021 |
Neg logit contributions | |
lucky | -0.011 |
good | -0.008 |
great | -0.008 |
dog | -0.008 |
little | -0.008 |
Token | |
Token ID | 220 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.010 |
great | +0.009 |
dog | +0.009 |
reward | +0.009 |
Neg logit contributions | |
onna | -0.026 |
outage | -0.025 |
alk | -0.025 |
oons | -0.025 |
der | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
onna | +0.090 |
outage | +0.088 |
oons | +0.088 |
der | +0.087 |
alk | +0.086 |
Neg logit contributions | |
lucky | -0.030 |
good | -0.020 |
great | -0.020 |
's | -0.020 |
little | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
lucky | +0.010 |
great | +0.007 |
good | +0.007 |
little | +0.006 |
's | +0.006 |
Neg logit contributions | |
onna | -0.033 |
der | -0.032 |
outage | -0.032 |
oons | -0.032 |
alk | -0.031 |
Token | When |
Token ID | 2215 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
lucky | +0.024 |
good | +0.020 |
dog | +0.020 |
great | +0.020 |
reward | +0.019 |
Neg logit contributions | |
onna | -0.024 |
oons | -0.023 |
outage | -0.023 |
alk | -0.022 |
der | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
lucky | +0.066 |
oc | +0.056 |
loyal | +0.055 |
welcome | +0.054 |
dog | +0.054 |
Neg logit contributions | |
lights | -0.065 |
reating | -0.062 |
outage | -0.059 |
onna | -0.058 |
ubs | -0.058 |
Token | parade |
Token ID | 16134 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
lucky | +0.037 |
oc | +0.034 |
's | +0.032 |
rescued | +0.030 |
at | +0.030 |
Neg logit contributions | |
lights | -0.060 |
outage | -0.054 |
oons | -0.051 |
der | -0.051 |
reating | -0.051 |
Token | was |
Token ID | 373 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
lucky | +0.130 |
loyal | +0.100 |
clever | +0.096 |
good | +0.095 |
fine | +0.094 |
Neg logit contributions | |
lights | -0.165 |
outage | -0.164 |
ide | -0.164 |
oons | -0.161 |
der | -0.157 |
Token | finished |
Token ID | 5201 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
lucky | +0.032 |
dog | +0.029 |
's | +0.027 |
reward | +0.026 |
par | +0.025 |
Neg logit contributions | |
onna | -0.038 |
lights | -0.037 |
ubs | -0.036 |
outage | -0.036 |
alk | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -8.04e-04 |
Pos logit contributions | |
lucky | +0.003 |
dog | +0.002 |
reward | +0.001 |
loyal | +0.001 |
good | +0.001 |
Neg logit contributions | |
onna | -0.009 |
lights | -0.009 |
der | -0.009 |
oons | -0.009 |
alk | -0.009 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
lucky | +0.001 |
je | +0.001 |
dog | +0.001 |
loyal | +0.001 |
welcome | +0.001 |
Neg logit contributions | |
lights | -0.001 |
reating | -0.001 |
der | -0.001 |
outage | -0.001 |
ubs | -0.001 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
lucky | +0.018 |
good | +0.014 |
job | +0.014 |
great | +0.014 |
reward | +0.014 |
Neg logit contributions | |
onna | -0.040 |
oons | -0.038 |
der | -0.038 |
outage | -0.037 |
ubs | -0.036 |
Token | are |
Token ID | 389 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
lucky | +0.063 |
reward | +0.043 |
great | +0.041 |
good | +0.041 |
fine | +0.039 |
Neg logit contributions | |
onna | -0.166 |
oons | -0.166 |
outage | -0.165 |
alk | -0.158 |
der | -0.157 |
Token | you |
Token ID | 345 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
lucky | +0.030 |
relieved | +0.025 |
reward | +0.023 |
proud | +0.022 |
great | +0.022 |
Neg logit contributions | |
onna | -0.052 |
oons | -0.052 |
reating | -0.049 |
der | -0.049 |
lights | -0.048 |
Token | ? |
Token ID | 30 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
lucky | +0.051 |
good | +0.044 |
great | +0.044 |
dog | +0.043 |
little | +0.042 |
Neg logit contributions | |
onna | -0.045 |
oons | -0.042 |
outage | -0.042 |
alk | -0.041 |
der | -0.041 |
Token | I |
Token ID | 314 |
Feature activation | -3.83e-04 |
Pos logit contributions | |
lucky | +0.031 |
great | +0.026 |
good | +0.026 |
little | +0.024 |
reward | +0.024 |
Neg logit contributions | |
onna | -0.042 |
outage | -0.039 |
oons | -0.038 |
der | -0.038 |
alk | -0.038 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
lucky | +0.000 |
bye | +0.000 |
good | +0.000 |
loyal | +0.000 |
best | +0.000 |
Neg logit contributions | |
onna | -0.001 |
outage | -0.001 |
alk | -0.001 |
oons | -0.001 |
ubs | -0.001 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
onna | +0.022 |
outage | +0.021 |
der | +0.021 |
ubs | +0.021 |
oons | +0.021 |
Neg logit contributions | |
lucky | -0.013 |
reward | -0.011 |
good | -0.011 |
great | -0.011 |
dog | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
lucky | +0.131 |
good | +0.108 |
dog | +0.107 |
great | +0.105 |
little | +0.104 |
Neg logit contributions | |
oons | -0.181 |
onna | -0.181 |
der | -0.177 |
outage | -0.175 |
alk | -0.173 |
Token | find |
Token ID | 1064 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.009 |
great | +0.009 |
best | +0.009 |
's | +0.008 |
Neg logit contributions | |
onna | -0.036 |
alk | -0.034 |
outage | -0.034 |
oons | -0.034 |
ubs | -0.034 |
Token | you |
Token ID | 345 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.010 |
great | +0.010 |
dog | +0.009 |
reward | +0.009 |
Neg logit contributions | |
onna | -0.029 |
oons | -0.029 |
outage | -0.028 |
der | -0.028 |
alk | -0.028 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
lucky | +0.023 |
, | +0.020 |
's | +0.020 |
at | +0.020 |
little | +0.020 |
Neg logit contributions | |
bench | -0.026 |
oons | -0.026 |
onna | -0.026 |
alk | -0.025 |
lights | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +3.63e-03 |
Pos logit contributions | |
onna | +0.040 |
oons | +0.038 |
outage | +0.038 |
der | +0.037 |
alk | +0.037 |
Neg logit contributions | |
lucky | -0.022 |
good | -0.018 |
great | -0.017 |
dog | -0.017 |
little | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
outage | +0.012 |
onna | +0.012 |
lights | +0.012 |
oons | +0.012 |
alk | +0.012 |
Neg logit contributions | |
lucky | -0.007 |
good | -0.006 |
dog | -0.006 |
little | -0.006 |
's | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.75e-03 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.001 |
little | +0.001 |
, | +0.001 |
's | +0.001 |
Neg logit contributions | |
der | -0.006 |
onna | -0.006 |
lights | -0.006 |
outage | -0.006 |
ware | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
lucky | +0.006 |
good | +0.005 |
great | +0.005 |
dog | +0.005 |
reward | +0.005 |
Neg logit contributions | |
onna | -0.007 |
oons | -0.006 |
outage | -0.006 |
der | -0.006 |
alk | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | -6.94e-03 |
Pos logit contributions | |
onna | +0.025 |
oons | +0.024 |
outage | +0.024 |
der | +0.024 |
alk | +0.024 |
Neg logit contributions | |
lucky | -0.018 |
good | -0.014 |
great | -0.014 |
dog | -0.014 |
's | -0.014 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
lucky | +0.008 |
dog | +0.006 |
loyal | +0.006 |
bye | +0.006 |
little | +0.006 |
Neg logit contributions | |
onna | -0.014 |
outage | -0.014 |
ubs | -0.013 |
oons | -0.013 |
alk | -0.013 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
onna | +0.031 |
ubs | +0.030 |
outage | +0.029 |
der | +0.028 |
pan | +0.027 |
Neg logit contributions | |
lucky | -0.019 |
reward | -0.019 |
arrived | -0.018 |
delivery | -0.018 |
's | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
lucky | +0.133 |
great | +0.108 |
good | +0.107 |
reward | +0.105 |
's | +0.104 |
Neg logit contributions | |
onna | -0.177 |
outage | -0.166 |
ubs | -0.162 |
alk | -0.161 |
der | -0.160 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
onna | +0.023 |
der | +0.022 |
oons | +0.022 |
lights | +0.021 |
outage | +0.021 |
Neg logit contributions | |
lucky | -0.014 |
great | -0.011 |
's | -0.011 |
good | -0.011 |
arrived | -0.011 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
onna | +0.032 |
oons | +0.032 |
alk | +0.031 |
lights | +0.031 |
der | +0.031 |
Neg logit contributions | |
lucky | -0.024 |
dog | -0.021 |
, | -0.021 |
good | -0.021 |
's | -0.021 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
onna | +0.043 |
oons | +0.041 |
der | +0.040 |
ubs | +0.039 |
alk | +0.039 |
Neg logit contributions | |
lucky | -0.035 |
great | -0.028 |
good | -0.028 |
reward | -0.028 |
loyal | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
onna | +0.044 |
outage | +0.043 |
oons | +0.043 |
der | +0.042 |
ubs | +0.041 |
Neg logit contributions | |
lucky | -0.027 |
great | -0.022 |
good | -0.021 |
reward | -0.020 |
fine | -0.020 |
Token | are |
Token ID | 389 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
lucky | +0.066 |
reward | +0.046 |
great | +0.045 |
good | +0.043 |
fine | +0.042 |
Neg logit contributions | |
oons | -0.165 |
onna | -0.164 |
outage | -0.164 |
alk | -0.155 |
der | -0.155 |
Token | you |
Token ID | 345 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
lucky | +0.030 |
relieved | +0.025 |
proud | +0.023 |
great | +0.022 |
delivery | +0.021 |
Neg logit contributions | |
onna | -0.048 |
oons | -0.047 |
der | -0.045 |
reating | -0.043 |
ware | -0.043 |
Token | ? |
Token ID | 30 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
lucky | +0.047 |
good | +0.040 |
great | +0.040 |
dog | +0.039 |
's | +0.039 |
Neg logit contributions | |
onna | -0.044 |
oons | -0.042 |
outage | -0.042 |
der | -0.041 |
alk | -0.041 |
Token | I |
Token ID | 314 |
Feature activation | -1.50e-03 |
Pos logit contributions | |
lucky | +0.038 |
great | +0.032 |
good | +0.032 |
little | +0.030 |
best | +0.029 |
Neg logit contributions | |
onna | -0.049 |
outage | -0.045 |
der | -0.044 |
oons | -0.044 |
alk | -0.043 |
Token | 'm |
Token ID | 1101 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
lucky | +0.002 |
bye | +0.001 |
delivery | +0.001 |
good | +0.001 |
loyal | +0.001 |
Neg logit contributions | |
onna | -0.003 |
outage | -0.003 |
ubs | -0.003 |
oons | -0.003 |
alk | -0.003 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
onna | +0.021 |
outage | +0.020 |
oons | +0.020 |
der | +0.020 |
ubs | +0.020 |
Neg logit contributions | |
lucky | -0.012 |
good | -0.009 |
great | -0.009 |
reward | -0.009 |
dog | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
lucky | +0.136 |
good | +0.114 |
dog | +0.112 |
great | +0.111 |
little | +0.109 |
Neg logit contributions | |
onna | -0.175 |
oons | -0.175 |
der | -0.170 |
outage | -0.169 |
alk | -0.167 |
Token | find |
Token ID | 1064 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
lucky | +0.014 |
good | +0.010 |
best | +0.010 |
great | +0.010 |
's | +0.009 |
Neg logit contributions | |
onna | -0.032 |
alk | -0.030 |
outage | -0.030 |
ubs | -0.030 |
oons | -0.030 |
Token | you |
Token ID | 345 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
lucky | +0.012 |
good | +0.009 |
great | +0.009 |
dog | +0.008 |
little | +0.008 |
Neg logit contributions | |
onna | -0.028 |
oons | -0.027 |
outage | -0.027 |
der | -0.027 |
alk | -0.026 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
lucky | +0.022 |
, | +0.020 |
's | +0.020 |
at | +0.020 |
good | +0.019 |
Neg logit contributions | |
oons | -0.028 |
onna | -0.028 |
lights | -0.028 |
bench | -0.027 |
alk | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
onna | +0.036 |
oons | +0.035 |
outage | +0.035 |
der | +0.034 |
alk | +0.034 |
Neg logit contributions | |
lucky | -0.023 |
good | -0.018 |
great | -0.018 |
dog | -0.017 |
little | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
onna | +0.024 |
der | +0.024 |
outage | +0.022 |
oons | +0.022 |
pan | +0.022 |
Neg logit contributions | |
lucky | -0.015 |
great | -0.012 |
job | -0.012 |
good | -0.011 |
reward | -0.011 |
Token | OK |
Token ID | 11380 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
onna | +0.050 |
outage | +0.048 |
der | +0.048 |
oons | +0.048 |
alk | +0.046 |
Neg logit contributions | |
lucky | -0.039 |
good | -0.032 |
great | -0.032 |
dog | -0.031 |
little | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -7.66e-03 |
Pos logit contributions | |
onna | +0.031 |
oons | +0.030 |
outage | +0.030 |
der | +0.030 |
lights | +0.030 |
Neg logit contributions | |
lucky | -0.010 |
dog | -0.006 |
good | -0.006 |
great | -0.006 |
's | -0.006 |
Token | I |
Token ID | 314 |
Feature activation | -1.99e-03 |
Pos logit contributions | |
lucky | +0.011 |
great | +0.009 |
je | +0.009 |
job | +0.009 |
arrived | +0.009 |
Neg logit contributions | |
onna | -0.014 |
der | -0.013 |
outage | -0.013 |
oons | -0.012 |
lights | -0.012 |
Token | 'm |
Token ID | 1101 |
Feature activation | +5.94e-03 |
Pos logit contributions | |
lucky | +0.002 |
good | +0.002 |
great | +0.002 |
dog | +0.002 |
little | +0.002 |
Neg logit contributions | |
onna | -0.005 |
outage | -0.004 |
oons | -0.004 |
der | -0.004 |
alk | -0.004 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
onna | +0.015 |
outage | +0.014 |
ubs | +0.014 |
der | +0.014 |
oons | +0.014 |
Neg logit contributions | |
lucky | -0.004 |
dog | -0.003 |
reward | -0.003 |
's | -0.003 |
great | -0.003 |
Token | down |
Token ID | 866 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
lucky | +0.110 |
good | +0.086 |
great | +0.085 |
dog | +0.083 |
little | +0.081 |
Neg logit contributions | |
onna | -0.200 |
oons | -0.192 |
outage | -0.192 |
der | -0.189 |
alk | -0.189 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
lucky | +0.035 |
good | +0.028 |
great | +0.027 |
dog | +0.026 |
little | +0.026 |
Neg logit contributions | |
onna | -0.071 |
oons | -0.069 |
outage | -0.068 |
alk | -0.068 |
der | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
outage | +0.056 |
onna | +0.056 |
oons | +0.055 |
alk | +0.055 |
ubs | +0.054 |
Neg logit contributions | |
lucky | -0.018 |
good | -0.013 |
little | -0.012 |
dog | -0.012 |
's | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
outage | +0.008 |
ware | +0.008 |
der | +0.008 |
alk | +0.008 |
onna | +0.008 |
Neg logit contributions | |
lucky | -0.001 |
good | -0.001 |
little | -0.001 |
dog | -0.001 |
, | -0.001 |
Token | He |
Token ID | 1544 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
lucky | +0.004 |
good | +0.004 |
little | +0.004 |
's | +0.004 |
great | +0.004 |
Neg logit contributions | |
onna | -0.005 |
outage | -0.005 |
alk | -0.005 |
der | -0.005 |
oons | -0.005 |
Token | are |
Token ID | 389 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
lucky | +0.063 |
reward | +0.045 |
great | +0.043 |
good | +0.042 |
fine | +0.039 |
Neg logit contributions | |
onna | -0.168 |
oons | -0.167 |
outage | -0.165 |
alk | -0.160 |
der | -0.158 |
Token | you |
Token ID | 345 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
lucky | +0.029 |
relieved | +0.024 |
reward | +0.023 |
job | +0.023 |
proud | +0.023 |
Neg logit contributions | |
onna | -0.052 |
oons | -0.052 |
der | -0.048 |
ide | -0.048 |
reating | -0.048 |
Token | ? |
Token ID | 30 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
lucky | +0.056 |
good | +0.048 |
great | +0.048 |
dog | +0.048 |
reward | +0.047 |
Neg logit contributions | |
onna | -0.045 |
oons | -0.043 |
outage | -0.043 |
alk | -0.042 |
der | -0.042 |
Token | I |
Token ID | 314 |
Feature activation | +5.26e-04 |
Pos logit contributions | |
lucky | +0.033 |
great | +0.028 |
good | +0.028 |
little | +0.025 |
reward | +0.025 |
Neg logit contributions | |
onna | -0.047 |
outage | -0.045 |
der | -0.044 |
oons | -0.043 |
alk | -0.043 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
onna | +0.001 |
outage | +0.001 |
alk | +0.001 |
ubs | +0.001 |
oons | +0.001 |
Neg logit contributions | |
lucky | -0.001 |
bye | -0.001 |
good | -0.000 |
best | -0.000 |
loyal | -0.000 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
onna | +0.023 |
outage | +0.021 |
ubs | +0.021 |
der | +0.021 |
oons | +0.021 |
Neg logit contributions | |
lucky | -0.013 |
reward | -0.011 |
great | -0.011 |
good | -0.011 |
dog | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
lucky | +0.133 |
good | +0.111 |
dog | +0.108 |
great | +0.107 |
little | +0.106 |
Neg logit contributions | |
oons | -0.178 |
onna | -0.177 |
der | -0.174 |
outage | -0.172 |
alk | -0.170 |
Token | find |
Token ID | 1064 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
lucky | +0.012 |
good | +0.008 |
great | +0.008 |
dog | +0.007 |
's | +0.007 |
Neg logit contributions | |
onna | -0.035 |
outage | -0.034 |
alk | -0.034 |
oons | -0.034 |
ubs | -0.033 |
Token | you |
Token ID | 345 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
lucky | +0.012 |
good | +0.009 |
great | +0.009 |
dog | +0.009 |
little | +0.008 |
Neg logit contributions | |
onna | -0.028 |
oons | -0.027 |
outage | -0.027 |
der | -0.026 |
alk | -0.026 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
lucky | +0.021 |
's | +0.018 |
, | +0.018 |
good | +0.018 |
little | +0.018 |
Neg logit contributions | |
onna | -0.024 |
bench | -0.024 |
oons | -0.024 |
outage | -0.024 |
lights | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
onna | +0.051 |
outage | +0.049 |
oons | +0.049 |
alk | +0.048 |
der | +0.048 |
Neg logit contributions | |
lucky | -0.024 |
good | -0.018 |
great | -0.018 |
dog | -0.018 |
's | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
lucky | +0.004 |
good | +0.002 |
great | +0.001 |
dog | +0.001 |
's | +0.001 |
Neg logit contributions | |
onna | -0.023 |
oons | -0.023 |
outage | -0.023 |
der | -0.022 |
alk | -0.022 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
lucky | +0.010 |
par | +0.009 |
je | +0.009 |
job | +0.009 |
's | +0.009 |
Neg logit contributions | |
der | -0.011 |
onna | -0.011 |
outage | -0.011 |
oons | -0.011 |
lights | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
onna | +0.016 |
outage | +0.015 |
oons | +0.015 |
der | +0.015 |
alk | +0.014 |
Neg logit contributions | |
lucky | -0.015 |
great | -0.013 |
good | -0.013 |
reward | -0.013 |
dog | -0.012 |
Token | We |
Token ID | 775 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
lucky | +0.056 |
great | +0.051 |
good | +0.048 |
reward | +0.046 |
little | +0.045 |
Neg logit contributions | |
onna | -0.069 |
outage | -0.065 |
der | -0.063 |
alk | -0.062 |
oons | -0.059 |
Token | are |
Token ID | 389 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
lucky | +0.016 |
bye | +0.013 |
loyal | +0.012 |
great | +0.012 |
little | +0.012 |
Neg logit contributions | |
onna | -0.031 |
outage | -0.031 |
alk | -0.031 |
ubs | -0.030 |
oons | -0.030 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
arrived | +0.033 |
reward | +0.033 |
bye | +0.030 |
turns | +0.029 |
lucky | +0.028 |
Neg logit contributions | |
onna | -0.065 |
ubs | -0.064 |
hers | -0.062 |
outage | -0.062 |
der | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
lucky | +0.101 |
good | +0.078 |
great | +0.075 |
dog | +0.074 |
's | +0.073 |
Neg logit contributions | |
onna | -0.210 |
oons | -0.207 |
outage | -0.203 |
der | -0.203 |
alk | -0.202 |
Token | Stay |
Token ID | 16160 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
lucky | +0.049 |
great | +0.043 |
good | +0.041 |
reward | +0.040 |
little | +0.039 |
Neg logit contributions | |
onna | -0.066 |
outage | -0.066 |
der | -0.063 |
alk | -0.062 |
lights | -0.061 |
Token | where |
Token ID | 810 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
lucky | +0.016 |
reward | +0.015 |
thank | +0.014 |
arrived | +0.014 |
great | +0.014 |
Neg logit contributions | |
onna | -0.030 |
outage | -0.030 |
ubs | -0.029 |
ands | -0.028 |
hers | -0.028 |
Token | you |
Token ID | 345 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
lucky | +0.046 |
great | +0.034 |
reward | +0.034 |
good | +0.033 |
dog | +0.031 |
Neg logit contributions | |
onna | -0.122 |
oons | -0.120 |
outage | -0.118 |
lights | -0.116 |
der | -0.116 |
Token | are |
Token ID | 389 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
lucky | +0.017 |
good | +0.013 |
bye | +0.013 |
dog | +0.013 |
loyal | +0.013 |
Neg logit contributions | |
onna | -0.037 |
alk | -0.036 |
oons | -0.035 |
outage | -0.035 |
ands | -0.034 |
Token | on |
Token ID | 319 |
Feature activation | +3.95e-03 |
Pos logit contributions | |
onna | +0.026 |
oons | +0.025 |
ubs | +0.025 |
outage | +0.025 |
alk | +0.025 |
Neg logit contributions | |
lucky | -0.011 |
great | -0.008 |
reward | -0.008 |
good | -0.008 |
loyal | -0.007 |
Token | tight |
Token ID | 5381 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
onna | +0.008 |
oons | +0.007 |
outage | +0.007 |
der | +0.007 |
alk | +0.007 |
Neg logit contributions | |
lucky | -0.006 |
good | -0.005 |
great | -0.005 |
dog | -0.004 |
little | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
oons | +0.037 |
outage | +0.037 |
lights | +0.036 |
alk | +0.036 |
onna | +0.036 |
Neg logit contributions | |
, | -0.025 |
lucky | -0.023 |
at | -0.022 |
good | -0.021 |
dog | -0.021 |
Token | I |
Token ID | 314 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
lucky | +0.032 |
great | +0.027 |
good | +0.026 |
best | +0.025 |
reward | +0.024 |
Neg logit contributions | |
onna | -0.045 |
der | -0.043 |
outage | -0.042 |
alk | -0.041 |
ubs | -0.040 |
Token | 'm |
Token ID | 1101 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
onna | +0.016 |
outage | +0.015 |
ubs | +0.014 |
oons | +0.014 |
alk | +0.014 |
Neg logit contributions | |
lucky | -0.009 |
bye | -0.007 |
loyal | -0.007 |
dog | -0.007 |
best | -0.007 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
onna | +0.029 |
outage | +0.028 |
ubs | +0.027 |
der | +0.027 |
pan | +0.026 |
Neg logit contributions | |
lucky | -0.016 |
reward | -0.015 |
arrived | -0.015 |
dog | -0.014 |
's | -0.014 |
Token | ," |
Token ID | 553 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
lucky | +0.155 |
great | +0.131 |
good | +0.129 |
reward | +0.127 |
dog | +0.126 |
Neg logit contributions | |
onna | -0.149 |
outage | -0.139 |
ubs | -0.135 |
alk | -0.134 |
oons | -0.132 |
Token | He |
Token ID | 679 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
onna | +0.081 |
oons | +0.079 |
outage | +0.079 |
alk | +0.077 |
der | +0.077 |
Neg logit contributions | |
lucky | -0.038 |
good | -0.029 |
great | -0.029 |
dog | -0.028 |
little | -0.028 |
Token | said |
Token ID | 531 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
onna | +0.054 |
der | +0.053 |
oons | +0.053 |
outage | +0.051 |
ware | +0.050 |
Neg logit contributions | |
lucky | -0.035 |
great | -0.029 |
job | -0.028 |
welcome | -0.028 |
good | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
lucky | +0.022 |
good | +0.018 |
dog | +0.017 |
's | +0.017 |
great | +0.017 |
Neg logit contributions | |
onna | -0.030 |
oons | -0.029 |
outage | -0.029 |
alk | -0.029 |
ubs | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-03 |
Pos logit contributions | |
outage | +0.025 |
oons | +0.025 |
onna | +0.025 |
alk | +0.025 |
ubs | +0.025 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.007 |
dog | -0.006 |
little | -0.006 |
great | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-03 |
Pos logit contributions | |
onna | +0.060 |
outage | +0.057 |
oons | +0.057 |
der | +0.056 |
alk | +0.056 |
Neg logit contributions | |
lucky | -0.030 |
good | -0.023 |
great | -0.023 |
dog | -0.022 |
's | -0.021 |
Token | Mom |
Token ID | 11254 |
Feature activation | +8.27e-03 |
Pos logit contributions | |
onna | +0.003 |
outage | +0.003 |
der | +0.003 |
lights | +0.002 |
pan | +0.002 |
Neg logit contributions | |
lucky | -0.002 |
's | -0.001 |
great | -0.001 |
arrived | -0.001 |
job | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
onna | +0.016 |
oons | +0.015 |
der | +0.015 |
alk | +0.015 |
outage | +0.015 |
Neg logit contributions | |
lucky | -0.012 |
, | -0.010 |
's | -0.010 |
good | -0.010 |
dog | -0.010 |
Token | we |
Token ID | 356 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
lucky | +0.020 |
mis | +0.016 |
job | +0.016 |
arrived | +0.016 |
great | +0.016 |
Neg logit contributions | |
onna | -0.030 |
outage | -0.028 |
der | -0.028 |
pan | -0.027 |
reating | -0.026 |
Token | are |
Token ID | 389 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
lucky | +0.008 |
dog | +0.006 |
loyal | +0.006 |
little | +0.005 |
bye | +0.005 |
Neg logit contributions | |
onna | -0.017 |
outage | -0.016 |
alk | -0.016 |
oons | -0.016 |
ubs | -0.016 |
Token | coming |
Token ID | 2406 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
lucky | +0.027 |
reward | +0.024 |
arrived | +0.023 |
's | +0.023 |
dog | +0.023 |
Neg logit contributions | |
onna | -0.074 |
ubs | -0.071 |
hers | -0.071 |
outage | -0.070 |
pan | -0.069 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
lucky | +0.125 |
good | +0.102 |
great | +0.100 |
dog | +0.098 |
little | +0.097 |
Neg logit contributions | |
onna | -0.183 |
oons | -0.178 |
outage | -0.175 |
der | -0.174 |
alk | -0.173 |
Token | Tom |
Token ID | 4186 |
Feature activation | +8.51e-03 |
Pos logit contributions | |
onna | +0.034 |
oons | +0.032 |
outage | +0.032 |
der | +0.031 |
alk | +0.031 |
Neg logit contributions | |
lucky | -0.020 |
great | -0.016 |
good | -0.016 |
reward | -0.015 |
best | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
onna | +0.021 |
oons | +0.020 |
outage | +0.020 |
alk | +0.020 |
der | +0.020 |
Neg logit contributions | |
lucky | -0.008 |
good | -0.006 |
dog | -0.005 |
's | -0.005 |
great | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
lucky | +0.052 |
great | +0.043 |
best | +0.042 |
good | +0.041 |
's | +0.040 |
Neg logit contributions | |
onna | -0.060 |
der | -0.053 |
outage | -0.053 |
oons | -0.052 |
alk | -0.052 |
Token | said |
Token ID | 531 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
onna | +0.041 |
oons | +0.040 |
outage | +0.039 |
der | +0.039 |
alk | +0.039 |
Neg logit contributions | |
lucky | -0.017 |
good | -0.013 |
great | -0.012 |
dog | -0.011 |
loyal | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | +3.61e-03 |
Pos logit contributions | |
lucky | +0.012 |
dog | +0.008 |
bye | +0.008 |
great | +0.008 |
reward | +0.008 |
Neg logit contributions | |
oons | -0.035 |
onna | -0.035 |
der | -0.035 |
ware | -0.033 |
outage | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
onna | +0.008 |
oons | +0.008 |
alk | +0.008 |
der | +0.008 |
outage | +0.008 |
Neg logit contributions | |
lucky | -0.004 |
dog | -0.003 |
reward | -0.003 |
good | -0.003 |
bye | -0.003 |
Token | cheese |
Token ID | 9891 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
onna | +0.025 |
oons | +0.022 |
ware | +0.022 |
outage | +0.022 |
alk | +0.021 |
Neg logit contributions | |
lucky | -0.010 |
at | -0.008 |
's | -0.008 |
turns | -0.008 |
bye | -0.007 |
Token | sandwich |
Token ID | 20433 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
lucky | +0.008 |
great | +0.006 |
good | +0.006 |
dog | +0.006 |
little | +0.006 |
Neg logit contributions | |
onna | -0.012 |
oons | -0.011 |
outage | -0.011 |
der | -0.011 |
alk | -0.011 |
Token | ." |
Token ID | 526 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
lucky | +0.012 |
great | +0.010 |
good | +0.010 |
dog | +0.009 |
little | +0.009 |
Neg logit contributions | |
onna | -0.018 |
oons | -0.017 |
outage | -0.017 |
der | -0.017 |
alk | -0.017 |
Token | |
Token ID | 220 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
outage | +0.103 |
onna | +0.100 |
lights | +0.097 |
oons | +0.097 |
alk | +0.096 |
Neg logit contributions | |
lucky | -0.036 |
's | -0.029 |
good | -0.027 |
dog | -0.027 |
, | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
outage | +0.180 |
lights | +0.175 |
ands | +0.174 |
onna | +0.174 |
alk | +0.173 |
Neg logit contributions | |
lucky | -0.043 |
's | -0.028 |
good | -0.028 |
little | -0.026 |
great | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
outage | +0.045 |
lights | +0.044 |
der | +0.044 |
onna | +0.043 |
pan | +0.043 |
Neg logit contributions | |
lucky | -0.009 |
's | -0.007 |
good | -0.006 |
little | -0.006 |
great | -0.006 |
Token | Ben |
Token ID | 11696 |
Feature activation | +6.31e-03 |
Pos logit contributions | |
onna | +0.018 |
outage | +0.018 |
alk | +0.017 |
lights | +0.017 |
der | +0.017 |
Neg logit contributions | |
lucky | -0.016 |
's | -0.014 |
good | -0.014 |
great | -0.013 |
little | -0.013 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
onna | +0.015 |
oons | +0.014 |
der | +0.014 |
alk | +0.014 |
outage | +0.014 |
Neg logit contributions | |
lucky | -0.006 |
good | -0.005 |
great | -0.005 |
dog | -0.004 |
reward | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.000 |
great | +0.000 |
dog | +0.000 |
little | +0.000 |
Neg logit contributions | |
onna | -0.004 |
oons | -0.004 |
outage | -0.004 |
der | -0.004 |
alk | -0.004 |
Token | sky |
Token ID | 6766 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
onna | +0.037 |
outage | +0.036 |
oons | +0.036 |
der | +0.035 |
alk | +0.035 |
Neg logit contributions | |
lucky | -0.015 |
's | -0.012 |
great | -0.011 |
good | -0.011 |
reward | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.008 |
great | +0.008 |
dog | +0.008 |
little | +0.007 |
Neg logit contributions | |
onna | -0.049 |
oons | -0.048 |
outage | -0.047 |
der | -0.047 |
alk | -0.047 |
Token | gloomy |
Token ID | 46400 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
onna | +0.063 |
oons | +0.063 |
alk | +0.061 |
outage | +0.061 |
der | +0.061 |
Neg logit contributions | |
lucky | -0.027 |
good | -0.020 |
great | -0.020 |
little | -0.019 |
dog | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -9.49e-04 |
Pos logit contributions | |
onna | +0.079 |
oons | +0.074 |
ands | +0.074 |
alk | +0.074 |
ubs | +0.073 |
Neg logit contributions | |
, | -0.020 |
lucky | -0.019 |
at | -0.016 |
little | -0.016 |
good | -0.015 |
Token | everything |
Token ID | 2279 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.001 |
great | +0.001 |
little | +0.001 |
dog | +0.001 |
Neg logit contributions | |
onna | -0.002 |
oons | -0.002 |
alk | -0.002 |
outage | -0.002 |
ands | -0.002 |
Token | felt |
Token ID | 2936 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.009 |
great | +0.009 |
reward | +0.009 |
dog | +0.009 |
Neg logit contributions | |
onna | -0.033 |
oons | -0.032 |
outage | -0.032 |
lights | -0.032 |
der | -0.031 |
Token | still |
Token ID | 991 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
onna | +0.153 |
oons | +0.148 |
outage | +0.148 |
der | +0.146 |
alk | +0.146 |
Neg logit contributions | |
lucky | -0.067 |
good | -0.050 |
great | -0.049 |
dog | -0.047 |
little | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
onna | +0.059 |
oons | +0.057 |
outage | +0.056 |
alk | +0.056 |
der | +0.055 |
Neg logit contributions | |
lucky | -0.030 |
good | -0.023 |
great | -0.022 |
little | -0.022 |
dog | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
onna | +0.017 |
outage | +0.017 |
oons | +0.016 |
ands | +0.016 |
der | +0.016 |
Neg logit contributions | |
lucky | -0.005 |
little | -0.004 |
's | -0.004 |
dog | -0.004 |
great | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
der | +0.025 |
pan | +0.024 |
ware | +0.024 |
lights | +0.023 |
ands | +0.023 |
Neg logit contributions | |
lucky | -0.001 |
little | -0.000 |
, | -0.000 |
| -0.000 |
great | +0.000 |
Token | One |
Token ID | 3198 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
der | +0.010 |
onna | +0.010 |
lights | +0.009 |
ware | +0.009 |
pan | +0.009 |
Neg logit contributions | |
lucky | -0.011 |
little | -0.010 |
great | -0.010 |
good | -0.009 |
's | -0.009 |
Token | fun |
Token ID | 1257 |
Feature activation | -4.05e-03 |
Pos logit contributions | |
outage | +0.010 |
onna | +0.010 |
oons | +0.010 |
der | +0.010 |
alk | +0.010 |
Neg logit contributions | |
lucky | -0.005 |
good | -0.004 |
great | -0.004 |
, | -0.003 |
fine | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
, | +0.003 |
at | +0.003 |
lucky | +0.003 |
good | +0.002 |
's | +0.002 |
Neg logit contributions | |
alk | -0.010 |
oons | -0.010 |
ands | -0.010 |
lights | -0.010 |
der | -0.010 |
Token | join |
Token ID | 4654 |
Feature activation | +8.91e-03 |
Pos logit contributions | |
lucky | +0.002 |
good | +0.001 |
great | +0.001 |
dog | +0.001 |
little | +0.001 |
Neg logit contributions | |
onna | -0.006 |
oons | -0.006 |
outage | -0.006 |
der | -0.006 |
alk | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
onna | +0.021 |
outage | +0.021 |
oons | +0.021 |
der | +0.021 |
lights | +0.020 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.007 |
great | -0.007 |
little | -0.007 |
dog | -0.007 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
lucky | +0.022 |
, | +0.019 |
at | +0.019 |
good | +0.019 |
great | +0.019 |
Neg logit contributions | |
outage | -0.024 |
oons | -0.024 |
onna | -0.024 |
der | -0.024 |
alk | -0.023 |
Token | |
Token ID | 220 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
onna | +0.123 |
oons | +0.119 |
outage | +0.118 |
alk | +0.118 |
der | +0.118 |
Neg logit contributions | |
lucky | -0.057 |
good | -0.044 |
great | -0.043 |
dog | -0.041 |
little | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
outage | +0.186 |
onna | +0.183 |
ands | +0.181 |
lights | +0.181 |
der | +0.181 |
Neg logit contributions | |
lucky | -0.046 |
's | -0.032 |
good | -0.029 |
little | -0.027 |
great | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
outage | +0.050 |
der | +0.050 |
lights | +0.050 |
onna | +0.049 |
oons | +0.049 |
Neg logit contributions | |
lucky | -0.014 |
good | -0.010 |
little | -0.010 |
's | -0.010 |
great | -0.010 |
Token | But |
Token ID | 1537 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
onna | +0.023 |
oons | +0.022 |
outage | +0.022 |
der | +0.022 |
alk | +0.021 |
Neg logit contributions | |
lucky | -0.017 |
good | -0.014 |
great | -0.014 |
dog | -0.013 |
little | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -9.81e-04 |
Pos logit contributions | |
onna | +0.046 |
der | +0.046 |
pan | +0.043 |
alk | +0.042 |
ubs | +0.042 |
Neg logit contributions | |
lucky | -0.029 |
great | -0.022 |
good | -0.022 |
reward | -0.021 |
turns | -0.021 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
lucky | +0.001 |
's | +0.001 |
great | +0.001 |
reward | +0.001 |
good | +0.001 |
Neg logit contributions | |
der | -0.002 |
outage | -0.002 |
oons | -0.002 |
lights | -0.002 |
onna | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
onna | +0.019 |
oons | +0.018 |
alk | +0.018 |
outage | +0.018 |
der | +0.018 |
Neg logit contributions | |
lucky | -0.012 |
good | -0.010 |
great | -0.010 |
best | -0.009 |
reward | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
der | +0.016 |
lights | +0.015 |
pan | +0.015 |
ands | +0.015 |
ware | +0.015 |
Neg logit contributions | |
lucky | -0.002 |
little | -0.001 |
's | -0.001 |
, | -0.001 |
good | -0.001 |
Token | He |
Token ID | 1544 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
onna | +0.005 |
outage | +0.005 |
der | +0.005 |
oons | +0.005 |
lights | +0.004 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.004 |
great | -0.004 |
little | -0.004 |
's | -0.004 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
onna | +0.028 |
oons | +0.027 |
alk | +0.026 |
der | +0.026 |
outage | +0.026 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.011 |
great | -0.011 |
reward | -0.011 |
best | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
onna | +0.026 |
outage | +0.025 |
oons | +0.025 |
alk | +0.024 |
der | +0.024 |
Neg logit contributions | |
lucky | -0.012 |
good | -0.009 |
little | -0.009 |
great | -0.009 |
dog | -0.008 |
Token | would |
Token ID | 561 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
onna | +0.047 |
oons | +0.046 |
outage | +0.046 |
der | +0.045 |
alk | +0.045 |
Neg logit contributions | |
lucky | -0.019 |
good | -0.014 |
dog | -0.013 |
reward | -0.013 |
bye | -0.013 |
Token | be |
Token ID | 307 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
oons | +0.197 |
lights | +0.190 |
der | +0.188 |
outage | +0.187 |
ud | +0.187 |
Neg logit contributions | |
lucky | -0.021 |
good | -0.010 |
great | -0.009 |
be | -0.004 |
little | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +5.67e-03 |
Pos logit contributions | |
onna | +0.050 |
oons | +0.048 |
outage | +0.048 |
alk | +0.047 |
der | +0.047 |
Neg logit contributions | |
lucky | -0.022 |
dog | -0.017 |
's | -0.016 |
good | -0.016 |
reward | -0.016 |
Token | great |
Token ID | 1049 |
Feature activation | -8.52e-03 |
Pos logit contributions | |
onna | +0.012 |
outage | +0.011 |
rain | +0.010 |
ware | +0.010 |
bench | +0.010 |
Neg logit contributions | |
's | -0.004 |
at | -0.004 |
lucky | -0.004 |
bye | -0.004 |
relieved | -0.003 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
lucky | +0.011 |
's | +0.008 |
relieved | +0.008 |
bye | +0.008 |
arrived | +0.008 |
Neg logit contributions | |
onna | -0.017 |
outage | -0.016 |
alk | -0.016 |
bench | -0.015 |
ubs | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
onna | +0.025 |
outage | +0.024 |
der | +0.024 |
oons | +0.024 |
alk | +0.024 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.012 |
great | -0.012 |
little | -0.011 |
dog | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -4.99e-04 |
Pos logit contributions | |
onna | +0.058 |
oons | +0.056 |
outage | +0.056 |
der | +0.055 |
alk | +0.055 |
Neg logit contributions | |
lucky | -0.025 |
good | -0.019 |
great | -0.019 |
dog | -0.018 |
's | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -7.66e-04 |
Pos logit contributions | |
lucky | +0.000 |
good | +0.000 |
reward | +0.000 |
great | +0.000 |
dog | +0.000 |
Neg logit contributions | |
onna | -0.001 |
oons | -0.001 |
outage | -0.001 |
der | -0.001 |
ubs | -0.001 |
Token | furry |
Token ID | 40857 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
lucky | +0.001 |
bye | +0.001 |
's | +0.001 |
relieved | +0.001 |
arrived | +0.001 |
Neg logit contributions | |
onna | -0.002 |
ware | -0.001 |
outage | -0.001 |
iky | -0.001 |
oons | -0.001 |
Token | cat |
Token ID | 3797 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
onna | +0.012 |
der | +0.011 |
alk | +0.011 |
outage | +0.011 |
oons | +0.011 |
Neg logit contributions | |
lucky | -0.005 |
great | -0.004 |
good | -0.004 |
's | -0.003 |
reward | -0.003 |
Token | named |
Token ID | 3706 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
onna | +0.055 |
oons | +0.054 |
alk | +0.053 |
outage | +0.053 |
der | +0.053 |
Neg logit contributions | |
lucky | -0.018 |
's | -0.014 |
dog | -0.013 |
good | -0.013 |
, | -0.013 |
Token | Mitt |
Token ID | 16627 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
oons | +0.091 |
outage | +0.090 |
lights | +0.090 |
alk | +0.089 |
der | +0.087 |
Neg logit contributions | |
lucky | -0.030 |
little | -0.025 |
dog | -0.024 |
good | -0.023 |
's | -0.022 |
Token | ens |
Token ID | 641 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
onna | +0.110 |
oons | +0.105 |
outage | +0.105 |
alk | +0.103 |
der | +0.103 |
Neg logit contributions | |
lucky | -0.099 |
good | -0.083 |
great | -0.082 |
dog | -0.082 |
's | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
onna | +0.054 |
outage | +0.053 |
oons | +0.053 |
lights | +0.053 |
ubs | +0.052 |
Neg logit contributions | |
lucky | -0.030 |
's | -0.026 |
, | -0.026 |
good | -0.025 |
dog | -0.025 |
Token | One |
Token ID | 1881 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
outage | +0.020 |
ands | +0.019 |
oons | +0.019 |
der | +0.018 |
alk | +0.018 |
Neg logit contributions | |
lucky | -0.010 |
dog | -0.009 |
little | -0.009 |
's | -0.009 |
, | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -3.56e-03 |
Pos logit contributions | |
outage | +0.062 |
onna | +0.060 |
oons | +0.059 |
alk | +0.059 |
ide | +0.059 |
Neg logit contributions | |
lucky | -0.042 |
reward | -0.037 |
Sorry | -0.036 |
thank | -0.035 |
turns | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
lucky | +0.004 |
delivery | +0.003 |
reward | +0.003 |
hero | +0.003 |
surprise | +0.003 |
Neg logit contributions | |
onna | -0.007 |
oons | -0.007 |
ubs | -0.007 |
der | -0.007 |
ud | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
lucky | +0.000 |
little | +0.000 |
great | +0.000 |
's | +0.000 |
good | +0.000 |
Neg logit contributions | |
der | -0.002 |
outage | -0.002 |
lights | -0.002 |
ware | -0.002 |
pan | -0.002 |
Token | As |
Token ID | 1722 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
lucky | +0.005 |
great | +0.004 |
little | +0.004 |
good | +0.004 |
's | +0.004 |
Neg logit contributions | |
onna | -0.006 |
outage | -0.006 |
lights | -0.006 |
der | -0.006 |
oons | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
lucky | +0.024 |
dog | +0.020 |
's | +0.020 |
je | +0.020 |
bye | +0.019 |
Neg logit contributions | |
onna | -0.025 |
lights | -0.024 |
alk | -0.023 |
oons | -0.023 |
der | -0.023 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
lucky | +0.012 |
welcome | +0.010 |
job | +0.009 |
good | +0.009 |
sorry | +0.009 |
Neg logit contributions | |
oons | -0.014 |
ware | -0.014 |
onna | -0.014 |
der | -0.014 |
lights | -0.014 |
Token | around |
Token ID | 1088 |
Feature activation | -6.97e-03 |
Pos logit contributions | |
lucky | +0.044 |
reward | +0.040 |
dog | +0.039 |
Sorry | +0.039 |
job | +0.039 |
Neg logit contributions | |
onna | -0.054 |
der | -0.054 |
lights | -0.054 |
oons | -0.052 |
alk | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
lucky | +0.006 |
good | +0.004 |
loyal | +0.004 |
great | +0.004 |
reward | +0.004 |
Neg logit contributions | |
onna | -0.016 |
alk | -0.016 |
ware | -0.015 |
lights | -0.015 |
oons | -0.015 |
Token | another |
Token ID | 1194 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
der | +0.018 |
onna | +0.018 |
lights | +0.018 |
oons | +0.018 |
alk | +0.018 |
Neg logit contributions | |
lucky | -0.013 |
dog | -0.011 |
bye | -0.011 |
good | -0.011 |
reward | -0.011 |
Token | ot |
Token ID | 30972 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
onna | +0.012 |
der | +0.012 |
outage | +0.012 |
oons | +0.012 |
lights | +0.012 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.003 |
great | -0.003 |
's | -0.003 |
reward | -0.003 |
Token | ter |
Token ID | 353 |
Feature activation | -5.91e-03 |
Pos logit contributions | |
lucky | +0.025 |
great | +0.022 |
good | +0.022 |
fine | +0.021 |
turns | +0.021 |
Neg logit contributions | |
der | -0.016 |
onna | -0.015 |
ware | -0.015 |
outage | -0.015 |
alk | -0.014 |
Token | appeared |
Token ID | 4120 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
lucky | +0.007 |
good | +0.006 |
great | +0.006 |
job | +0.006 |
reward | +0.006 |
Neg logit contributions | |
onna | -0.012 |
der | -0.011 |
alk | -0.011 |
outage | -0.011 |
oons | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
lucky | +0.047 |
good | +0.036 |
great | +0.035 |
dog | +0.034 |
little | +0.034 |
Neg logit contributions | |
onna | -0.100 |
oons | -0.097 |
outage | -0.097 |
alk | -0.095 |
der | -0.094 |
Token | was |
Token ID | 373 |
Feature activation | +2.79e-03 |
Pos logit contributions | |
lucky | +0.027 |
reward | +0.021 |
bye | +0.020 |
good | +0.019 |
job | +0.019 |
Neg logit contributions | |
onna | -0.055 |
oons | -0.055 |
ide | -0.053 |
alk | -0.052 |
ubs | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
onna | +0.007 |
oons | +0.006 |
outage | +0.006 |
alk | +0.006 |
der | +0.006 |
Neg logit contributions | |
lucky | -0.003 |
good | -0.002 |
great | -0.002 |
dog | -0.002 |
's | -0.002 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
arrived | +0.011 |
turns | +0.010 |
lucky | +0.010 |
reward | +0.010 |
's | +0.010 |
Neg logit contributions | |
onna | -0.033 |
iky | -0.030 |
oons | -0.029 |
outage | -0.029 |
ware | -0.029 |
Token | cat |
Token ID | 3797 |
Feature activation | +5.54e-03 |
Pos logit contributions | |
lucky | +0.029 |
great | +0.022 |
's | +0.022 |
good | +0.021 |
turns | +0.021 |
Neg logit contributions | |
onna | -0.057 |
alk | -0.054 |
der | -0.054 |
outage | -0.054 |
ware | -0.053 |
Token | named |
Token ID | 3706 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
onna | +0.015 |
oons | +0.015 |
lights | +0.015 |
alk | +0.015 |
ands | +0.015 |
Neg logit contributions | |
lucky | -0.003 |
, | -0.003 |
's | -0.003 |
dog | -0.002 |
at | -0.002 |
Token | Kitty |
Token ID | 21168 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
onna | +0.042 |
oons | +0.040 |
outage | +0.040 |
alk | +0.039 |
der | +0.039 |
Neg logit contributions | |
lucky | -0.022 |
good | -0.017 |
great | -0.017 |
dog | -0.016 |
reward | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
lights | +0.028 |
oons | +0.028 |
outage | +0.028 |
onna | +0.028 |
alk | +0.028 |
Neg logit contributions | |
lucky | -0.012 |
, | -0.011 |
's | -0.011 |
dog | -0.010 |
little | -0.010 |
Token | Kitty |
Token ID | 21168 |
Feature activation | +2.08e-03 |
Pos logit contributions | |
lucky | +0.007 |
good | +0.006 |
great | +0.006 |
dog | +0.006 |
little | +0.005 |
Neg logit contributions | |
onna | -0.013 |
oons | -0.013 |
outage | -0.013 |
der | -0.013 |
alk | -0.013 |
Token | lived |
Token ID | 5615 |
Feature activation | +9.66e-03 |
Pos logit contributions | |
onna | +0.005 |
oons | +0.005 |
outage | +0.005 |
der | +0.005 |
alk | +0.005 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.002 |
great | -0.002 |
dog | -0.002 |
's | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
onna | +0.026 |
oons | +0.025 |
outage | +0.025 |
der | +0.025 |
alk | +0.025 |
Neg logit contributions | |
lucky | -0.007 |
good | -0.004 |
great | -0.004 |
dog | -0.004 |
little | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
lucky | +0.006 |
reward | +0.005 |
bye | +0.005 |
arrived | +0.005 |
thank | +0.005 |
Neg logit contributions | |
onna | -0.009 |
outage | -0.009 |
ubs | -0.009 |
oons | -0.008 |
alk | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
lucky | +0.004 |
best | +0.003 |
great | +0.003 |
reward | +0.003 |
welcome | +0.003 |
Neg logit contributions | |
onna | -0.006 |
der | -0.006 |
outage | -0.005 |
pan | -0.005 |
heavily | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
onna | +0.028 |
outage | +0.027 |
oons | +0.026 |
der | +0.026 |
alk | +0.026 |
Neg logit contributions | |
lucky | -0.013 |
good | -0.010 |
great | -0.010 |
dog | -0.010 |
reward | -0.009 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
lucky | +0.008 |
reward | +0.008 |
dog | +0.007 |
's | +0.007 |
arrived | +0.007 |
Neg logit contributions | |
onna | -0.017 |
ubs | -0.016 |
outage | -0.016 |
der | -0.015 |
oons | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
onna | +0.027 |
oons | +0.027 |
alk | +0.027 |
ands | +0.026 |
outage | +0.026 |
Neg logit contributions | |
lucky | -0.016 |
good | -0.013 |
, | -0.013 |
at | -0.013 |
little | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
onna | +0.024 |
oons | +0.023 |
outage | +0.023 |
der | +0.023 |
alk | +0.022 |
Neg logit contributions | |
lucky | -0.012 |
good | -0.010 |
great | -0.009 |
dog | -0.009 |
's | -0.009 |
Token | made |
Token ID | 925 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
onna | +0.031 |
der | +0.030 |
outage | +0.030 |
oons | +0.029 |
alk | +0.029 |
Neg logit contributions | |
lucky | -0.017 |
good | -0.013 |
great | -0.013 |
reward | -0.013 |
dog | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -6.89e-04 |
Pos logit contributions | |
onna | +0.054 |
oons | +0.052 |
outage | +0.052 |
alk | +0.051 |
der | +0.051 |
Neg logit contributions | |
lucky | -0.022 |
good | -0.017 |
great | -0.016 |
dog | -0.016 |
little | -0.015 |
Token | promise |
Token ID | 6991 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
lucky | +0.001 |
arrived | +0.001 |
at | +0.001 |
turns | +0.001 |
's | +0.001 |
Neg logit contributions | |
onna | -0.001 |
outage | -0.001 |
der | -0.001 |
alk | -0.001 |
heavily | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
lucky | +0.004 |
great | +0.003 |
good | +0.003 |
little | +0.003 |
dog | +0.003 |
Neg logit contributions | |
onna | -0.007 |
outage | -0.007 |
der | -0.007 |
alk | -0.007 |
oons | -0.007 |
Token | himself |
Token ID | 2241 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
onna | +0.040 |
alk | +0.037 |
ubs | +0.037 |
der | +0.037 |
outage | +0.037 |
Neg logit contributions | |
lucky | -0.018 |
's | -0.014 |
great | -0.014 |
good | -0.013 |
dog | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
onna | +0.031 |
outage | +0.030 |
der | +0.030 |
alk | +0.030 |
ubs | +0.029 |
Neg logit contributions | |
lucky | -0.015 |
great | -0.012 |
dog | -0.012 |
Sorry | -0.012 |
reward | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -2.24e-03 |
Pos logit contributions | |
onna | +0.023 |
outage | +0.023 |
der | +0.023 |
ubs | +0.022 |
alk | +0.022 |
Neg logit contributions | |
lucky | -0.019 |
great | -0.016 |
reward | -0.016 |
little | -0.016 |
good | -0.015 |
Token | be |
Token ID | 307 |
Feature activation | -1.74e-03 |
Pos logit contributions | |
lucky | +0.002 |
dog | +0.002 |
good | +0.002 |
great | +0.002 |
best | +0.002 |
Neg logit contributions | |
onna | -0.005 |
alk | -0.005 |
outage | -0.005 |
ubs | -0.005 |
der | -0.005 |
Token | honest |
Token ID | 5508 |
Feature activation | -6.01e-04 |
Pos logit contributions | |
lucky | +0.002 |
Sorry | +0.002 |
je | +0.001 |
dog | +0.001 |
reward | +0.001 |
Neg logit contributions | |
ubs | -0.003 |
onna | -0.003 |
ands | -0.003 |
outage | -0.003 |
hers | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
lucky | +0.001 |
good | +0.000 |
great | +0.000 |
dog | +0.000 |
little | +0.000 |
Neg logit contributions | |
onna | -0.001 |
oons | -0.001 |
outage | -0.001 |
der | -0.001 |
alk | -0.001 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.43e-04 |
Pos logit contributions | |
lucky | +0.019 |
dog | +0.017 |
great | +0.016 |
little | +0.016 |
je | +0.016 |
Neg logit contributions | |
onna | -0.034 |
outage | -0.032 |
der | -0.032 |
ubs | -0.029 |
alk | -0.029 |
Token | even |
Token ID | 772 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
lucky | +0.000 |
great | +0.000 |
good | +0.000 |
fine | +0.000 |
reward | +0.000 |
Neg logit contributions | |
der | -0.000 |
onna | -0.000 |
outage | -0.000 |
oons | -0.000 |
ubs | -0.000 |
Token | when |
Token ID | 618 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
der | +0.015 |
onna | +0.014 |
outage | +0.014 |
reating | +0.014 |
oons | +0.013 |
Neg logit contributions | |
lucky | -0.016 |
arrived | -0.014 |
dog | -0.014 |
reward | -0.014 |
great | -0.014 |
Token | something |
Token ID | 1223 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
lucky | +0.031 |
good | +0.024 |
great | +0.024 |
dog | +0.023 |
's | +0.023 |
Neg logit contributions | |
onna | -0.056 |
oons | -0.054 |
der | -0.054 |
outage | -0.053 |
alk | -0.053 |
Token | is |
Token ID | 318 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
lucky | +0.034 |
reward | +0.026 |
bye | +0.026 |
dog | +0.026 |
job | +0.025 |
Neg logit contributions | |
onna | -0.078 |
oons | -0.075 |
outage | -0.074 |
der | -0.074 |
alk | -0.072 |
Token | tempting |
Token ID | 29850 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
onna | +0.012 |
outage | +0.012 |
der | +0.012 |
oons | +0.012 |
alk | +0.011 |
Neg logit contributions | |
lucky | -0.007 |
dog | -0.006 |
great | -0.006 |
good | -0.006 |
reward | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
lucky | +0.004 |
good | +0.003 |
great | +0.003 |
dog | +0.003 |
's | +0.003 |
Neg logit contributions | |
onna | -0.006 |
oons | -0.006 |
outage | -0.006 |
alk | -0.006 |
der | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
lucky | +0.008 |
je | +0.007 |
Sorry | +0.007 |
dog | +0.007 |
� | +0.007 |
Neg logit contributions | |
oons | -0.010 |
reating | -0.010 |
ands | -0.010 |
ubs | -0.010 |
lights | -0.010 |
Token | recording |
Token ID | 8296 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
lucky | +0.028 |
Sorry | +0.024 |
bye | +0.023 |
reward | +0.022 |
at | +0.022 |
Neg logit contributions | |
outage | -0.040 |
oons | -0.040 |
ware | -0.037 |
alk | -0.037 |
ands | -0.037 |
Token | home |
Token ID | 1363 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
lucky | +0.032 |
great | +0.025 |
good | +0.024 |
fine | +0.023 |
loyal | +0.023 |
Neg logit contributions | |
oons | -0.045 |
outage | -0.045 |
onna | -0.044 |
alk | -0.044 |
lights | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
onna | +0.023 |
oons | +0.022 |
outage | +0.022 |
lights | +0.022 |
der | +0.022 |
Neg logit contributions | |
lucky | -0.011 |
dog | -0.009 |
great | -0.009 |
good | -0.008 |
reward | -0.008 |
Token | listened |
Token ID | 16399 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
lucky | +0.008 |
great | +0.006 |
dog | +0.006 |
good | +0.006 |
reward | +0.006 |
Neg logit contributions | |
onna | -0.012 |
der | -0.012 |
oons | -0.012 |
outage | -0.012 |
lights | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
onna | +0.032 |
oons | +0.031 |
outage | +0.031 |
alk | +0.030 |
der | +0.030 |
Neg logit contributions | |
lucky | -0.017 |
good | -0.014 |
great | -0.013 |
dog | -0.013 |
little | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
onna | +0.039 |
oons | +0.037 |
der | +0.037 |
alk | +0.037 |
ubs | +0.037 |
Neg logit contributions | |
lucky | -0.025 |
dog | -0.020 |
good | -0.020 |
great | -0.019 |
's | -0.019 |
Token | every |
Token ID | 790 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
onna | +0.012 |
der | +0.012 |
oons | +0.011 |
alk | +0.011 |
outage | +0.011 |
Neg logit contributions | |
lucky | -0.009 |
dog | -0.007 |
good | -0.007 |
great | -0.007 |
reward | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
onna | +0.038 |
outage | +0.038 |
alk | +0.037 |
oons | +0.037 |
der | +0.036 |
Neg logit contributions | |
lucky | -0.016 |
good | -0.011 |
great | -0.011 |
dog | -0.011 |
's | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
onna | +0.004 |
der | +0.004 |
oons | +0.004 |
outage | +0.004 |
alk | +0.004 |
Neg logit contributions | |
lucky | -0.004 |
great | -0.003 |
good | -0.003 |
dog | -0.003 |
reward | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +8.96e-03 |
Pos logit contributions | |
lucky | +0.007 |
good | +0.005 |
little | +0.005 |
great | +0.005 |
's | +0.005 |
Neg logit contributions | |
outage | -0.010 |
onna | -0.010 |
oons | -0.010 |
ands | -0.010 |
lights | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
lucky | +0.053 |
great | +0.046 |
good | +0.043 |
reward | +0.043 |
Sorry | +0.042 |
Neg logit contributions | |
onna | -0.065 |
outage | -0.063 |
oons | -0.061 |
ubs | -0.058 |
ands | -0.058 |
Token | come |
Token ID | 1282 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
onna | +0.006 |
alk | +0.006 |
ands | +0.006 |
ubs | +0.006 |
bench | +0.006 |
Neg logit contributions | |
lucky | -0.004 |
dog | -0.003 |
's | -0.003 |
good | -0.003 |
best | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
lucky | +0.061 |
great | +0.045 |
good | +0.045 |
reward | +0.045 |
dog | +0.044 |
Neg logit contributions | |
onna | -0.127 |
outage | -0.120 |
alk | -0.120 |
ubs | -0.119 |
oons | -0.119 |
Token |
|
Token ID | 198 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
lucky | +0.008 |
great | +0.007 |
good | +0.007 |
reward | +0.007 |
dog | +0.007 |
Neg logit contributions | |
onna | -0.010 |
der | -0.010 |
oons | -0.010 |
alk | -0.010 |
lights | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -9.67e-03 |
Pos logit contributions | |
lucky | +0.004 |
little | +0.002 |
's | +0.002 |
great | +0.002 |
good | +0.002 |
Neg logit contributions | |
der | -0.024 |
pan | -0.023 |
lights | -0.023 |
outage | -0.023 |
onna | -0.023 |
Token | Soon |
Token ID | 28093 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
lucky | +0.014 |
good | +0.012 |
great | +0.012 |
little | +0.011 |
dog | +0.011 |
Neg logit contributions | |
onna | -0.018 |
outage | -0.017 |
oons | -0.017 |
der | -0.017 |
alk | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +2.56e-03 |
Pos logit contributions | |
lucky | +0.022 |
relieved | +0.018 |
delivery | +0.018 |
mis | +0.017 |
Follow | +0.017 |
Neg logit contributions | |
ubs | -0.030 |
lights | -0.028 |
der | -0.028 |
oons | -0.028 |
onna | -0.028 |
Token | many |
Token ID | 867 |
Feature activation | +3.48e-03 |
Pos logit contributions | |
lights | +0.004 |
reating | +0.004 |
der | +0.004 |
onna | +0.004 |
ubs | +0.004 |
Neg logit contributions | |
lucky | -0.003 |
's | -0.003 |
relieved | -0.003 |
loyal | -0.003 |
oc | -0.003 |
Token | people |
Token ID | 661 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
oons | +0.006 |
lights | +0.006 |
ands | +0.006 |
ills | +0.006 |
ubs | +0.006 |
Neg logit contributions | |
lucky | -0.005 |
Sorry | -0.004 |
bye | -0.004 |
job | -0.004 |
reward | -0.004 |
Token | came |
Token ID | 1625 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
lucky | +0.050 |
great | +0.041 |
job | +0.040 |
fine | +0.040 |
reward | +0.039 |
Neg logit contributions | |
outage | -0.081 |
onna | -0.080 |
oons | -0.080 |
ubs | -0.076 |
ide | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
lucky | +0.054 |
reward | +0.046 |
great | +0.042 |
thank | +0.041 |
good | +0.041 |
Neg logit contributions | |
onna | -0.083 |
ubs | -0.081 |
alk | -0.079 |
outage | -0.079 |
der | -0.078 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
lucky | +0.004 |
good | +0.003 |
great | +0.003 |
dog | +0.003 |
's | +0.003 |
Neg logit contributions | |
onna | -0.006 |
oons | -0.006 |
outage | -0.006 |
der | -0.006 |
alk | -0.006 |
Token | my |
Token ID | 1820 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
onna | +0.007 |
oons | +0.007 |
outage | +0.007 |
der | +0.007 |
alk | +0.007 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.004 |
great | -0.003 |
reward | -0.003 |
dog | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
lucky | +0.016 |
welcome | +0.013 |
job | +0.013 |
reward | +0.013 |
good | +0.013 |
Neg logit contributions | |
onna | -0.026 |
oons | -0.025 |
der | -0.025 |
outage | -0.025 |
bars | -0.024 |
Token | red |
Token ID | 2266 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
lucky | +0.023 |
good | +0.017 |
's | +0.017 |
great | +0.017 |
reward | +0.016 |
Neg logit contributions | |
onna | -0.044 |
outage | -0.043 |
lights | -0.043 |
der | -0.043 |
oons | -0.043 |
Token | car |
Token ID | 1097 |
Feature activation | -9.69e-03 |
Pos logit contributions | |
lucky | +0.021 |
good | +0.015 |
great | +0.015 |
dog | +0.014 |
little | +0.013 |
Neg logit contributions | |
onna | -0.049 |
oons | -0.048 |
outage | -0.047 |
der | -0.047 |
alk | -0.047 |
Token | zoom |
Token ID | 19792 |
Feature activation | +2.12e-04 |
Pos logit contributions | |
lucky | +0.009 |
great | +0.006 |
good | +0.006 |
reward | +0.006 |
welcome | +0.006 |
Neg logit contributions | |
onna | -0.023 |
oons | -0.022 |
der | -0.022 |
outage | -0.022 |
lights | -0.022 |
Token | ed |
Token ID | 276 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
onna | +0.000 |
oons | +0.000 |
outage | +0.000 |
der | +0.000 |
alk | +0.000 |
Neg logit contributions | |
lucky | -0.000 |
good | -0.000 |
great | -0.000 |
dog | -0.000 |
little | -0.000 |
Token | ahead |
Token ID | 4058 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
lucky | +0.010 |
reward | +0.008 |
dog | +0.007 |
great | +0.007 |
good | +0.007 |
Neg logit contributions | |
onna | -0.017 |
der | -0.016 |
lights | -0.016 |
oons | -0.016 |
outage | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
onna | +0.050 |
oons | +0.048 |
outage | +0.048 |
der | +0.047 |
alk | +0.047 |
Neg logit contributions | |
lucky | -0.027 |
good | -0.021 |
great | -0.021 |
dog | -0.021 |
little | -0.020 |
Token | but |
Token ID | 475 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
onna | +0.041 |
der | +0.039 |
outage | +0.037 |
lights | +0.037 |
ubs | +0.036 |
Neg logit contributions | |
lucky | -0.030 |
reward | -0.026 |
great | -0.025 |
good | -0.025 |
dog | -0.024 |
Token | then |
Token ID | 788 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
lucky | +0.008 |
reward | +0.006 |
great | +0.006 |
good | +0.006 |
welcome | +0.006 |
Neg logit contributions | |
lights | -0.010 |
der | -0.010 |
onna | -0.010 |
outage | -0.009 |
pan | -0.009 |
Token | from |
Token ID | 422 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
oons | +0.022 |
ands | +0.021 |
ubs | +0.021 |
bench | +0.021 |
reating | +0.021 |
Neg logit contributions | |
lucky | -0.016 |
bye | -0.013 |
dog | -0.013 |
reward | -0.013 |
relieved | -0.013 |
Token | one |
Token ID | 530 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
lucky | +0.015 |
good | +0.012 |
great | +0.011 |
dog | +0.011 |
little | +0.011 |
Neg logit contributions | |
onna | -0.029 |
oons | -0.028 |
outage | -0.028 |
der | -0.028 |
alk | -0.028 |
Token | place |
Token ID | 1295 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
outage | +0.048 |
reating | +0.048 |
lights | +0.047 |
alk | +0.047 |
oons | +0.046 |
Neg logit contributions | |
lucky | -0.035 |
relieved | -0.030 |
bye | -0.028 |
turns | -0.027 |
arrived | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -7.83e-04 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.010 |
great | +0.010 |
dog | +0.010 |
's | +0.010 |
Neg logit contributions | |
onna | -0.020 |
oons | -0.020 |
outage | -0.020 |
alk | -0.019 |
der | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
lucky | +0.001 |
dog | +0.001 |
's | +0.001 |
best | +0.001 |
good | +0.001 |
Neg logit contributions | |
onna | -0.002 |
alk | -0.002 |
ubs | -0.002 |
oons | -0.002 |
ands | -0.002 |
Token | next |
Token ID | 1306 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
lucky | +0.006 |
relieved | +0.005 |
turns | +0.005 |
bye | +0.005 |
good | +0.004 |
Neg logit contributions | |
reating | -0.007 |
hers | -0.007 |
der | -0.007 |
onna | -0.007 |
ands | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e-03 |
Pos logit contributions | |
lucky | +0.031 |
great | +0.022 |
good | +0.022 |
relieved | +0.022 |
's | +0.021 |
Neg logit contributions | |
onna | -0.055 |
alk | -0.054 |
outage | -0.054 |
oons | -0.052 |
lights | -0.052 |
Token | One |
Token ID | 1881 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
onna | +0.004 |
oons | +0.004 |
outage | +0.004 |
der | +0.004 |
alk | +0.004 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.001 |
great | -0.001 |
dog | -0.001 |
little | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
outage | +0.019 |
ide | +0.018 |
oons | +0.017 |
aghetti | +0.017 |
ock | +0.016 |
Neg logit contributions | |
Sorry | -0.026 |
turns | -0.026 |
hi | -0.024 |
Sur | -0.024 |
lucky | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -2.90e-03 |
Pos logit contributions | |
lucky | +0.017 |
promise | +0.015 |
natural | +0.014 |
relieved | +0.014 |
loyal | +0.013 |
Neg logit contributions | |
oons | -0.019 |
onna | -0.018 |
der | -0.018 |
ubs | -0.017 |
ware | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
lucky | +0.004 |
promise | +0.004 |
's | +0.004 |
welcome | +0.004 |
best | +0.003 |
Neg logit contributions | |
heavily | -0.004 |
der | -0.004 |
ware | -0.004 |
onna | -0.004 |
lights | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
onna | +0.016 |
outage | +0.015 |
alk | +0.015 |
oons | +0.015 |
ubs | +0.015 |
Neg logit contributions | |
lucky | -0.009 |
good | -0.008 |
great | -0.007 |
little | -0.007 |
, | -0.007 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
lucky | +0.011 |
good | +0.008 |
great | +0.008 |
reward | +0.008 |
dog | +0.008 |
Neg logit contributions | |
onna | -0.021 |
der | -0.020 |
oons | -0.020 |
alk | -0.019 |
outage | -0.019 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
onna | +0.094 |
der | +0.093 |
outage | +0.093 |
lights | +0.091 |
ands | +0.091 |
Neg logit contributions | |
lucky | -0.023 |
good | -0.016 |
's | -0.016 |
dog | -0.015 |
great | -0.015 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
lucky | +0.020 |
good | +0.016 |
great | +0.016 |
little | +0.016 |
dog | +0.016 |
Neg logit contributions | |
onna | -0.024 |
outage | -0.023 |
oons | -0.023 |
der | -0.023 |
alk | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
lucky | +0.002 |
little | +0.001 |
good | +0.001 |
great | +0.001 |
's | +0.001 |
Neg logit contributions | |
onna | -0.013 |
lights | -0.013 |
outage | -0.013 |
alk | -0.013 |
oons | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
lucky | +0.053 |
good | +0.039 |
great | +0.038 |
dog | +0.037 |
little | +0.036 |
Neg logit contributions | |
onna | -0.131 |
oons | -0.127 |
outage | -0.127 |
der | -0.125 |
alk | -0.125 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
lucky | +0.029 |
reward | +0.022 |
dog | +0.018 |
job | +0.018 |
delivery | +0.018 |
Neg logit contributions | |
onna | -0.095 |
oons | -0.090 |
alk | -0.090 |
ide | -0.089 |
ubs | -0.088 |
Token | there |
Token ID | 612 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
lucky | +0.020 |
reward | +0.019 |
bye | +0.017 |
thank | +0.017 |
job | +0.017 |
Neg logit contributions | |
onna | -0.030 |
oons | -0.029 |
alk | -0.028 |
ide | -0.028 |
outage | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
lucky | +0.026 |
reward | +0.020 |
bye | +0.019 |
good | +0.018 |
loyal | +0.018 |
Neg logit contributions | |
onna | -0.054 |
oons | -0.053 |
ide | -0.051 |
alk | -0.050 |
ubs | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
onna | +0.005 |
oons | +0.005 |
outage | +0.005 |
alk | +0.005 |
der | +0.005 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.002 |
great | -0.002 |
dog | -0.002 |
reward | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
turns | +0.012 |
arrived | +0.012 |
lucky | +0.011 |
's | +0.011 |
reward | +0.011 |
Neg logit contributions | |
onna | -0.036 |
oons | -0.033 |
iky | -0.032 |
ware | -0.032 |
der | -0.032 |
Token | upon |
Token ID | 2402 |
Feature activation | +5.90e-04 |
Pos logit contributions | |
lucky | +0.013 |
good | +0.010 |
little | +0.010 |
great | +0.010 |
's | +0.010 |
Neg logit contributions | |
onna | -0.017 |
outage | -0.016 |
der | -0.016 |
ands | -0.016 |
oons | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
onna | +0.002 |
lights | +0.002 |
outage | +0.002 |
alk | +0.002 |
oons | +0.002 |
Neg logit contributions | |
lucky | -0.000 |
little | -0.000 |
good | -0.000 |
great | -0.000 |
's | -0.000 |
Token | time |
Token ID | 640 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
lucky | +0.057 |
dog | +0.042 |
good | +0.042 |
reward | +0.041 |
great | +0.040 |
Neg logit contributions | |
onna | -0.117 |
oons | -0.113 |
alk | -0.110 |
outage | -0.109 |
der | -0.109 |
Token | there |
Token ID | 612 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
lucky | +0.026 |
reward | +0.021 |
delivery | +0.018 |
job | +0.018 |
dog | +0.018 |
Neg logit contributions | |
onna | -0.084 |
ide | -0.079 |
oons | -0.079 |
alk | -0.079 |
outage | -0.078 |
Token | was |
Token ID | 373 |
Feature activation | -3.23e-04 |
Pos logit contributions | |
lucky | +0.024 |
reward | +0.018 |
bye | +0.017 |
good | +0.017 |
job | +0.016 |
Neg logit contributions | |
onna | -0.053 |
oons | -0.052 |
outage | -0.050 |
ide | -0.050 |
alk | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
lucky | +0.000 |
good | +0.000 |
great | +0.000 |
dog | +0.000 |
little | +0.000 |
Neg logit contributions | |
onna | -0.001 |
oons | -0.001 |
outage | -0.001 |
der | -0.001 |
alk | -0.001 |
Token | teacher |
Token ID | 4701 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
lucky | +0.015 |
arrived | +0.014 |
reward | +0.013 |
turns | +0.013 |
's | +0.013 |
Neg logit contributions | |
onna | -0.052 |
oons | -0.048 |
iky | -0.047 |
outage | -0.047 |
ubs | -0.047 |
Token | named |
Token ID | 3706 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
onna | +0.025 |
outage | +0.025 |
oons | +0.025 |
der | +0.024 |
alk | +0.024 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.012 |
great | -0.012 |
dog | -0.011 |
reward | -0.011 |
Token | Miss |
Token ID | 4544 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
onna | +0.036 |
oons | +0.034 |
outage | +0.034 |
alk | +0.033 |
der | +0.033 |
Neg logit contributions | |
lucky | -0.025 |
good | -0.020 |
great | -0.019 |
dog | -0.019 |
reward | -0.019 |
Token | Joyce |
Token ID | 25936 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
lucky | +0.002 |
good | +0.002 |
dog | +0.002 |
great | +0.002 |
's | +0.002 |
Neg logit contributions | |
onna | -0.003 |
oons | -0.003 |
outage | -0.003 |
alk | -0.003 |
der | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
onna | +0.011 |
der | +0.011 |
oons | +0.011 |
outage | +0.011 |
alk | +0.010 |
Neg logit contributions | |
lucky | -0.010 |
great | -0.009 |
good | -0.009 |
reward | -0.009 |
dog | -0.008 |
Token | before |
Token ID | 878 |
Feature activation | +9.26e-03 |
Pos logit contributions | |
lucky | +0.061 |
great | +0.050 |
dog | +0.049 |
good | +0.049 |
's | +0.048 |
Neg logit contributions | |
onna | -0.083 |
der | -0.077 |
outage | -0.077 |
alk | -0.076 |
oons | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
onna | +0.020 |
oons | +0.019 |
outage | +0.019 |
ands | +0.019 |
alk | +0.019 |
Neg logit contributions | |
lucky | -0.012 |
good | -0.010 |
, | -0.010 |
great | -0.009 |
little | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
lucky | +0.007 |
good | +0.006 |
great | +0.005 |
dog | +0.005 |
little | +0.005 |
Neg logit contributions | |
onna | -0.015 |
oons | -0.015 |
outage | -0.014 |
der | -0.014 |
alk | -0.014 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
onna | +0.093 |
outage | +0.091 |
der | +0.090 |
oons | +0.090 |
lights | +0.088 |
Neg logit contributions | |
lucky | -0.033 |
good | -0.024 |
dog | -0.023 |
great | -0.023 |
's | -0.023 |
Token | upon |
Token ID | 2402 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
lucky | +0.026 |
good | +0.021 |
great | +0.021 |
dog | +0.021 |
little | +0.020 |
Neg logit contributions | |
onna | -0.030 |
oons | -0.029 |
outage | -0.029 |
der | -0.028 |
alk | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
lucky | +0.003 |
little | +0.002 |
good | +0.001 |
great | +0.001 |
's | +0.001 |
Neg logit contributions | |
onna | -0.017 |
outage | -0.017 |
lights | -0.017 |
alk | -0.016 |
oons | -0.016 |
Token | time |
Token ID | 640 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
lucky | +0.054 |
good | +0.040 |
great | +0.039 |
dog | +0.038 |
's | +0.037 |
Neg logit contributions | |
onna | -0.131 |
oons | -0.126 |
outage | -0.126 |
alk | -0.124 |
der | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
lucky | +0.032 |
reward | +0.027 |
job | +0.023 |
delivery | +0.023 |
dog | +0.023 |
Neg logit contributions | |
onna | -0.090 |
ide | -0.086 |
alk | -0.084 |
oons | -0.084 |
outage | -0.082 |
Token | there |
Token ID | 612 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
lucky | +0.020 |
reward | +0.018 |
bye | +0.017 |
job | +0.016 |
dog | +0.016 |
Neg logit contributions | |
onna | -0.034 |
oons | -0.033 |
alk | -0.032 |
outage | -0.032 |
ide | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
lucky | +0.024 |
reward | +0.018 |
bye | +0.017 |
good | +0.017 |
job | +0.016 |
Neg logit contributions | |
onna | -0.054 |
oons | -0.053 |
ide | -0.050 |
alk | -0.050 |
outage | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
onna | +0.011 |
oons | +0.011 |
outage | +0.011 |
der | +0.011 |
alk | +0.011 |
Neg logit contributions | |
lucky | -0.004 |
good | -0.003 |
great | -0.003 |
dog | -0.003 |
little | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
lucky | +0.005 |
good | +0.004 |
great | +0.004 |
bye | +0.004 |
arrived | +0.004 |
Neg logit contributions | |
onna | -0.013 |
outage | -0.012 |
lights | -0.012 |
der | -0.012 |
oons | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
onna | +0.006 |
oons | +0.005 |
outage | +0.005 |
alk | +0.005 |
der | +0.005 |
Neg logit contributions | |
lucky | -0.003 |
good | -0.003 |
great | -0.003 |
dog | -0.003 |
reward | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
lucky | +0.003 |
good | +0.002 |
little | +0.002 |
great | +0.002 |
's | +0.001 |
Neg logit contributions | |
der | -0.015 |
lights | -0.014 |
outage | -0.014 |
ware | -0.014 |
onna | -0.014 |
Token | When |
Token ID | 2215 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
lucky | +0.010 |
good | +0.009 |
great | +0.009 |
dog | +0.008 |
little | +0.008 |
Neg logit contributions | |
onna | -0.012 |
oons | -0.012 |
outage | -0.011 |
der | -0.011 |
alk | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
lucky | +0.060 |
promise | +0.052 |
welcome | +0.051 |
's | +0.050 |
opt | +0.049 |
Neg logit contributions | |
heavily | -0.041 |
lights | -0.040 |
ulk | -0.039 |
onna | -0.039 |
pan | -0.036 |
Token | arrived |
Token ID | 5284 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
lucky | +0.019 |
job | +0.018 |
best | +0.018 |
loyal | +0.017 |
Sorry | +0.017 |
Neg logit contributions | |
onna | -0.020 |
ill | -0.020 |
ware | -0.018 |
oons | -0.018 |
ud | -0.017 |
Token | home |
Token ID | 1363 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
lucky | +0.051 |
reward | +0.051 |
par | +0.050 |
Sorry | +0.050 |
great | +0.049 |
Neg logit contributions | |
ubs | -0.097 |
onna | -0.094 |
der | -0.094 |
lights | -0.091 |
oons | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
lucky | +0.026 |
great | +0.021 |
reward | +0.020 |
turns | +0.020 |
dog | +0.020 |
Neg logit contributions | |
onna | -0.077 |
lights | -0.073 |
outage | -0.073 |
oons | -0.072 |
ubs | -0.071 |
Token | his |
Token ID | 465 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
lucky | +0.006 |
reward | +0.006 |
turns | +0.006 |
's | +0.005 |
arrived | +0.005 |
Neg logit contributions | |
lights | -0.007 |
onna | -0.006 |
bars | -0.006 |
ubs | -0.006 |
heavily | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.74e-04 |
Pos logit contributions | |
lucky | +0.027 |
's | +0.022 |
arrived | +0.022 |
rescued | +0.020 |
good | +0.020 |
Neg logit contributions | |
lights | -0.053 |
onna | -0.053 |
oons | -0.051 |
outage | -0.050 |
der | -0.050 |
Token | was |
Token ID | 373 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
onna | +0.001 |
oons | +0.001 |
outage | +0.001 |
ubs | +0.001 |
der | +0.001 |
Neg logit contributions | |
lucky | -0.001 |
job | -0.001 |
good | -0.001 |
great | -0.001 |
bye | -0.001 |
Token | together |
Token ID | 1978 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
lucky | +0.007 |
good | +0.005 |
great | +0.005 |
dog | +0.005 |
's | +0.005 |
Neg logit contributions | |
onna | -0.018 |
oons | -0.017 |
outage | -0.017 |
der | -0.017 |
alk | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
onna | +0.025 |
oons | +0.024 |
outage | +0.024 |
alk | +0.024 |
der | +0.024 |
Neg logit contributions | |
lucky | -0.015 |
good | -0.012 |
great | -0.011 |
dog | -0.011 |
's | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
lucky | +0.015 |
good | +0.012 |
great | +0.011 |
dog | +0.011 |
reward | +0.011 |
Neg logit contributions | |
onna | -0.032 |
oons | -0.030 |
outage | -0.030 |
der | -0.030 |
alk | -0.030 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
onna | +0.088 |
outage | +0.085 |
oons | +0.085 |
der | +0.084 |
alk | +0.083 |
Neg logit contributions | |
lucky | -0.033 |
good | -0.024 |
great | -0.023 |
dog | -0.023 |
's | -0.023 |
Token | upon |
Token ID | 2402 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
lucky | +0.027 |
good | +0.022 |
great | +0.022 |
little | +0.022 |
dog | +0.021 |
Neg logit contributions | |
onna | -0.033 |
outage | -0.032 |
oons | -0.032 |
der | -0.032 |
alk | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
lucky | +0.003 |
little | +0.002 |
good | +0.002 |
great | +0.002 |
's | +0.001 |
Neg logit contributions | |
onna | -0.018 |
alk | -0.018 |
lights | -0.017 |
outage | -0.017 |
oons | -0.017 |
Token | time |
Token ID | 640 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
lucky | +0.054 |
good | +0.040 |
dog | +0.040 |
reward | +0.039 |
great | +0.038 |
Neg logit contributions | |
onna | -0.116 |
oons | -0.112 |
outage | -0.110 |
alk | -0.109 |
der | -0.109 |
Token | there |
Token ID | 612 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
lucky | +0.030 |
reward | +0.024 |
job | +0.020 |
dog | +0.020 |
delivery | +0.020 |
Neg logit contributions | |
onna | -0.087 |
ide | -0.082 |
oons | -0.082 |
alk | -0.082 |
outage | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
lucky | +0.023 |
reward | +0.017 |
good | +0.016 |
bye | +0.016 |
job | +0.016 |
Neg logit contributions | |
onna | -0.052 |
oons | -0.050 |
outage | -0.049 |
ide | -0.048 |
alk | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
onna | +0.007 |
outage | +0.007 |
oons | +0.007 |
der | +0.007 |
lights | +0.006 |
Neg logit contributions | |
lucky | -0.002 |
good | -0.001 |
great | -0.001 |
little | -0.001 |
dog | -0.001 |
Token | nice |
Token ID | 3621 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
lucky | +0.013 |
arrived | +0.012 |
turns | +0.012 |
's | +0.012 |
reward | +0.011 |
Neg logit contributions | |
onna | -0.045 |
outage | -0.041 |
oons | -0.041 |
iky | -0.041 |
der | -0.040 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
lucky | +0.015 |
arrived | +0.014 |
reward | +0.014 |
dog | +0.013 |
's | +0.013 |
Neg logit contributions | |
onna | -0.050 |
ubs | -0.048 |
lights | -0.047 |
hers | -0.047 |
outage | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
lucky | +0.058 |
good | +0.049 |
dog | +0.047 |
little | +0.046 |
great | +0.046 |
Neg logit contributions | |
onna | -0.083 |
oons | -0.082 |
outage | -0.081 |
alk | -0.080 |
ubs | -0.078 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
lucky | +0.028 |
great | +0.021 |
good | +0.021 |
reward | +0.021 |
dog | +0.021 |
Neg logit contributions | |
onna | -0.049 |
oons | -0.047 |
outage | -0.046 |
der | -0.046 |
alk | -0.046 |
Token | M |
Token ID | 44 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
onna | +0.073 |
outage | +0.071 |
der | +0.071 |
lights | +0.070 |
oons | +0.069 |
Neg logit contributions | |
lucky | -0.026 |
good | -0.020 |
dog | -0.020 |
's | -0.019 |
great | -0.019 |
Token | ia |
Token ID | 544 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
onna | +0.029 |
oons | +0.028 |
outage | +0.027 |
alk | +0.027 |
der | +0.027 |
Neg logit contributions | |
lucky | -0.020 |
good | -0.016 |
great | -0.016 |
dog | -0.016 |
's | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
lucky | +0.008 |
good | +0.006 |
great | +0.006 |
dog | +0.005 |
little | +0.005 |
Neg logit contributions | |
onna | -0.024 |
oons | -0.023 |
outage | -0.023 |
der | -0.023 |
alk | -0.023 |
Token | Leo |
Token ID | 19632 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
lucky | +0.072 |
great | +0.058 |
good | +0.057 |
reward | +0.056 |
best | +0.055 |
Neg logit contributions | |
onna | -0.104 |
alk | -0.101 |
ubs | -0.098 |
der | -0.096 |
oons | -0.096 |
Token | love |
Token ID | 1842 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
lucky | +0.024 |
little | +0.016 |
loyal | +0.016 |
good | +0.016 |
great | +0.016 |
Neg logit contributions | |
onna | -0.058 |
oons | -0.056 |
alk | -0.055 |
ands | -0.054 |
ubs | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -3.02e-03 |
Pos logit contributions | |
onna | +0.009 |
oons | +0.009 |
outage | +0.009 |
alk | +0.009 |
der | +0.009 |
Neg logit contributions | |
lucky | -0.005 |
great | -0.004 |
good | -0.004 |
's | -0.004 |
dog | -0.004 |
Token | play |
Token ID | 711 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
lucky | +0.002 |
great | +0.001 |
good | +0.001 |
little | +0.001 |
dog | +0.001 |
Neg logit contributions | |
outage | -0.008 |
der | -0.008 |
oons | -0.008 |
onna | -0.008 |
lights | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
onna | +0.034 |
outage | +0.034 |
oons | +0.032 |
ubs | +0.032 |
der | +0.032 |
Neg logit contributions | |
lucky | -0.008 |
good | -0.006 |
great | -0.006 |
at | -0.006 |
dog | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
lucky | +0.027 |
good | +0.022 |
great | +0.022 |
dog | +0.021 |
's | +0.021 |
Neg logit contributions | |
onna | -0.034 |
oons | -0.033 |
outage | -0.032 |
alk | -0.032 |
der | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
lucky | +0.004 |
good | +0.003 |
great | +0.003 |
dog | +0.003 |
reward | +0.003 |
Neg logit contributions | |
onna | -0.007 |
oons | -0.007 |
der | -0.007 |
alk | -0.007 |
outage | -0.007 |
Token | animals |
Token ID | 4695 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
lucky | +0.003 |
bye | +0.003 |
Sorry | +0.003 |
arrived | +0.003 |
's | +0.003 |
Neg logit contributions | |
der | -0.004 |
ands | -0.004 |
hers | -0.004 |
ware | -0.004 |
oons | -0.004 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
lucky | +0.037 |
job | +0.032 |
great | +0.031 |
reward | +0.031 |
good | +0.030 |
Neg logit contributions | |
der | -0.052 |
oons | -0.050 |
alk | -0.050 |
ide | -0.050 |
onna | -0.049 |
Token | in |
Token ID | 287 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
reward | +0.018 |
job | +0.016 |
Sorry | +0.016 |
delivery | +0.015 |
ha | +0.015 |
Neg logit contributions | |
ubs | -0.024 |
der | -0.024 |
onna | -0.023 |
lights | -0.023 |
ills | -0.022 |
Token | amaz |
Token ID | 40642 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
onna | +0.024 |
der | +0.023 |
lights | +0.023 |
alk | +0.023 |
ubs | +0.022 |
Neg logit contributions | |
lucky | -0.015 |
's | -0.013 |
job | -0.012 |
Sorry | -0.012 |
je | -0.011 |
Token | ement |
Token ID | 972 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
lucky | +0.108 |
good | +0.094 |
great | +0.093 |
dog | +0.092 |
's | +0.091 |
Neg logit contributions | |
onna | -0.071 |
oons | -0.068 |
der | -0.067 |
outage | -0.067 |
lights | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
lucky | +0.043 |
good | +0.033 |
great | +0.033 |
dog | +0.032 |
reward | +0.031 |
Neg logit contributions | |
onna | -0.085 |
der | -0.083 |
oons | -0.082 |
outage | -0.082 |
alk | -0.081 |
Token |
|
Token ID | 198 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
lucky | +0.009 |
good | +0.007 |
great | +0.007 |
dog | +0.007 |
reward | +0.007 |
Neg logit contributions | |
onna | -0.013 |
oons | -0.013 |
alk | -0.013 |
outage | -0.013 |
der | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
lucky | +0.005 |
great | +0.003 |
good | +0.002 |
, | +0.002 |
little | +0.002 |
Neg logit contributions | |
der | -0.036 |
lights | -0.035 |
bars | -0.035 |
ware | -0.034 |
reating | -0.034 |
Token | They |
Token ID | 2990 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
lucky | +0.016 |
good | +0.013 |
great | +0.013 |
little | +0.013 |
's | +0.012 |
Neg logit contributions | |
onna | -0.023 |
outage | -0.022 |
der | -0.022 |
oons | -0.022 |
alk | -0.022 |