TOP ACTIVATIONS
MAX = 7.749

to side on the cur vy branch and was soon high
He told the lady bug the sad story of how
. The Moral : Always respect other creatures '
. M oral : Being brave is important ,
. M oral : Being respectful and gentle is
. M oral : Be prepared for any surprises
. M oral : Hon esty , generosity and
. M oral : Do not be selfish and
M oral : It 's better to be
. M oral : Do not touch or open
This story has a moral : never take things that belong
. M oral : Sharing is caring . Being
M oral of the story : We should not take risks
. M oral : Sharing is caring ! When
." M oral : It is important to listen
M oral Value : Remember that you can always
. M oral : Sharing is caring , and
M oral of the story : Hard work and care can
M oral of the story : Be careful what you write
M oral of the story : You should be careful and

MIN ACTIVATIONS
MIN = -5.369

, but only with our supervision . And maybe you can
" No , Ben . Leave me alone . You are
sh oo , raven . Leave me alone . You are
. You are mean . Leave us alone ."
Go away , shark ! Leave the red fish alone !"
" Ar rr ! Leave my sister alone , you
You are bothering me . Leave me alone ," he says
't pick too many . Leave some for the birds and
points can hurt you . Leave the c actus alone ."
" Stop , stop . Leave me alone . These are
Go away , bear ! Leave my children alone !"
" Steven ! Leave the trophy and come to
" No , Ben . Leave me alone . You are
, Tom . You are no fun ." L
" Hey , dog ! Leave my brother 's ball alone
he was caught red - handed . But he didn 't
's our snow man ! Leave him alone !" Anna says
Go away , Leo . Leave me alone ," Mia says
are not welcome here . Leave the seeds for the other
or chard and fill his wagon with juicy red apples .

INTERVAL 4.469 - 7.749
CONTAINS 0.018%

and the owl told him : " A frog who never
. The Moral : Always respect other creatures '
moral of the story is : Don 't jump to conclusions
them a very useful lesson : that it 's always important
It says : " Warning : Do not touch . This

INTERVAL 1.190 - 4.469
CONTAINS 11.498%

much ." Sara says , proudly . " Wow
ummy . This is icky ." Ben said , "
had never gone on that adventurous hike . <|endoftext|> Once upon
to help - so the turtle and all the animals raced
washed the windows and made sure all of the dirt was

INTERVAL -2.090 - 1.190
CONTAINS 85.916%

his yellow pants so they could go to the park .
But Tom does not care . He keeps running
friends again . From then on , they always found creative
He reaches the top and looks around . He sees the
boat on the water and pushed it with a stick .

INTERVAL -5.369 - -2.090
CONTAINS 2.568%

is a good baker ." Tom compliments . They
not take care of their toys . They break them ,
top . " Look , our tower is very
of your tasty banana ?" Jack smiled and
my home . I feel safe and cozy here . Do
Token to
Token ID284
Feature activation-1.13e-01

Pos logit contributions
iest+0.206
hy+0.189
bars+0.184
mm+0.173
hetically+0.167
Neg logit contributions
mary-0.087
 watered-0.073
ashing-0.065
dy-0.061
uggets-0.058
Token side
Token ID1735
Feature activation-2.45e+00

Pos logit contributions
iest+0.008
hy+0.008
bars+0.007
mm+0.007
iness+0.007
Neg logit contributions
mary-0.004
 watered-0.004
 over-0.004
dy-0.003
ashing-0.003
Token on
Token ID319
Feature activation+2.76e-01

Pos logit contributions
iest+0.178
hy+0.163
bars+0.158
mm+0.151
iness+0.143
Neg logit contributions
mary-0.096
 watered-0.082
ashing-0.076
dy-0.072
uggets-0.069
Token the
Token ID262
Feature activation+5.78e-01

Pos logit contributions
mary+0.010
 watered+0.009
 over+0.008
dy+0.008
 raining+0.007
Neg logit contributions
iest-0.020
hy-0.019
bars-0.018
mm-0.017
iness-0.017
Token cur
Token ID1090
Feature activation+3.26e+00

Pos logit contributions
mary+0.029
 watered+0.027
dy+0.025
ashing+0.023
 raining+0.023
Neg logit contributions
iest-0.035
hy-0.031
bars-0.030
mm-0.029
iness-0.029
Tokenvy
Token ID7670
Feature activation+6.42e+00

Pos logit contributions
mary+0.163
 watered+0.154
uggets+0.146
ashing+0.139
dy+0.138
Neg logit contributions
iest-0.202
hy-0.174
bars-0.173
rob-0.154
 course-0.152
Token branch
Token ID8478
Feature activation+6.71e-01

Pos logit contributions
mary+0.354
 watered+0.319
ashing+0.299
dy+0.290
uggets+0.280
Neg logit contributions
iest-0.366
hy-0.322
bars-0.311
mm-0.288
iness-0.273
Token and
Token ID290
Feature activation+1.41e-01

Pos logit contributions
mary+0.026
 watered+0.022
ashing+0.020
dy+0.019
bugs+0.018
Neg logit contributions
iest-0.050
hy-0.045
bars-0.044
mm-0.043
rob-0.040
Token was
Token ID373
Feature activation-3.41e-01

Pos logit contributions
mary+0.007
 watered+0.006
ashing+0.006
dy+0.005
uggets+0.005
Neg logit contributions
iest-0.009
hy-0.008
bars-0.008
mm-0.007
hetically-0.007
Token soon
Token ID2582
Feature activation+4.53e-02

Pos logit contributions
iest+0.022
hy+0.021
bars+0.019
 elbow+0.018
 click+0.017
Neg logit contributions
mary-0.016
 watered-0.014
ashing-0.013
uggets-0.012
dy-0.012
Token high
Token ID1029
Feature activation-5.68e-01

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
uggets+0.002
rig+0.002
Neg logit contributions
iest-0.003
hy-0.003
bars-0.003
ance-0.002
 elbow-0.002
Token
Token ID26391
Feature activation+2.56e+00

Pos logit contributions
mary+0.056
ashing+0.048
rig+0.048
 watered+0.048
dy+0.047
Neg logit contributions
iest-0.047
bars-0.039
hy-0.037
 elbow-0.034
iness-0.032
Token He
Token ID679
Feature activation-1.28e+00

Pos logit contributions
mary+0.123
 watered+0.115
ashing+0.103
uggets+0.098
dy+0.097
Neg logit contributions
iest-0.156
hy-0.149
bars-0.138
mm-0.134
 course-0.122
Token told
Token ID1297
Feature activation+7.49e-01

Pos logit contributions
iest+0.086
hy+0.079
bars+0.075
mm+0.070
iness+0.067
Neg logit contributions
mary-0.056
 watered-0.049
ashing-0.047
uggets-0.044
dy-0.043
Token the
Token ID262
Feature activation+1.29e+00

Pos logit contributions
mary+0.032
 over+0.025
dy+0.025
 watered+0.024
 to+0.022
Neg logit contributions
iest-0.052
bars-0.046
hy-0.045
mm-0.043
 elbow-0.042
Token lady
Token ID10846
Feature activation+3.09e+00

Pos logit contributions
mary+0.073
 watered+0.066
ashing+0.062
dy+0.060
uggets+0.059
Neg logit contributions
iest-0.072
hy-0.064
bars-0.061
mm-0.056
iness-0.053
Tokenbug
Token ID25456
Feature activation+6.40e+00

Pos logit contributions
mary+0.151
 watered+0.133
ashing+0.123
dy+0.120
bugs+0.116
Neg logit contributions
iest-0.195
hy-0.175
bars-0.170
mm-0.159
hetically-0.151
Token the
Token ID262
Feature activation+8.79e-01

Pos logit contributions
mary+0.301
 watered+0.265
dy+0.239
ashing+0.234
bugs+0.228
Neg logit contributions
iest-0.413
hy-0.376
bars-0.368
mm-0.343
rob-0.334
Token sad
Token ID6507
Feature activation+2.68e+00

Pos logit contributions
mary+0.047
 watered+0.042
ashing+0.039
dy+0.038
uggets+0.037
Neg logit contributions
iest-0.052
hy-0.045
bars-0.045
mm-0.041
iness-0.039
Token story
Token ID1621
Feature activation+2.92e+00

Pos logit contributions
mary+0.140
 watered+0.125
ashing+0.116
dy+0.114
uggets+0.109
Neg logit contributions
iest-0.159
hy-0.141
bars-0.139
mm-0.129
hetically-0.125
Token of
Token ID286
Feature activation+7.53e-01

Pos logit contributions
mary+0.122
 watered+0.106
ashing+0.090
 over+0.088
dy+0.087
Neg logit contributions
iest-0.200
hy-0.182
bars-0.179
mm-0.172
 elbow-0.166
Token how
Token ID703
Feature activation-1.05e+00

Pos logit contributions
mary+0.031
 watered+0.027
dy+0.023
 over+0.022
 raining+0.022
Neg logit contributions
iest-0.053
bars-0.048
hy-0.048
mm-0.043
hetically-0.043
Token.
Token ID13
Feature activation+3.56e-01

Pos logit contributions
iest+0.154
hy+0.146
bars+0.139
mm+0.136
 elbow+0.132
Neg logit contributions
mary-0.055
 watered-0.045
ashing-0.038
dy-0.036
 over-0.035
Token
Token ID198
Feature activation+4.77e-01

Pos logit contributions
mary+0.017
 watered+0.015
ashing+0.014
dy+0.013
uggets+0.013
Neg logit contributions
iest-0.023
hy-0.021
bars-0.020
mm-0.019
iness-0.018
Token
Token ID198
Feature activation+4.09e-01

Pos logit contributions
mary+0.021
 watered+0.018
ashing+0.018
uggets+0.016
dy+0.015
Neg logit contributions
iest-0.032
hy-0.030
bars-0.027
 course-0.027
mm-0.027
TokenThe
Token ID464
Feature activation-3.55e-01

Pos logit contributions
mary+0.026
 watered+0.024
ashing+0.024
uggets+0.022
dy+0.022
Neg logit contributions
iest-0.020
hy-0.017
bars-0.016
 course-0.015
mm-0.015
Token Moral
Token ID39020
Feature activation+2.46e+00

Pos logit contributions
iest+0.023
hy+0.021
bars+0.020
mm+0.018
 course+0.018
Neg logit contributions
mary-0.017
 watered-0.015
ashing-0.014
uggets-0.014
dy-0.013
Token:
Token ID25
Feature activation+6.29e+00

Pos logit contributions
mary+0.115
 watered+0.103
bugs+0.092
ashing+0.092
 over+0.089
Neg logit contributions
iest-0.151
hy-0.138
bars-0.137
hetically-0.131
 elbow-0.130
Token Always
Token ID16622
Feature activation+6.70e-01

Pos logit contributions
mary+0.347
 watered+0.312
ashing+0.294
dy+0.281
uggets+0.277
Neg logit contributions
iest-0.354
hy-0.317
bars-0.306
mm-0.282
 course-0.267
Token respect
Token ID2461
Feature activation-2.03e+00

Pos logit contributions
mary+0.033
 watered+0.032
dy+0.029
ashing+0.028
 over+0.027
Neg logit contributions
iest-0.042
hy-0.039
bars-0.038
rob-0.035
mm-0.034
Token other
Token ID584
Feature activation-2.59e+00

Pos logit contributions
iest+0.135
hy+0.122
bars+0.117
mm+0.110
iness+0.105
Neg logit contributions
mary-0.092
 watered-0.081
ashing-0.076
dy-0.072
uggets-0.070
Token creatures
Token ID8109
Feature activation+6.34e-01

Pos logit contributions
iest+0.148
hy+0.132
bars+0.126
mm+0.116
iness+0.110
Neg logit contributions
mary-0.142
 watered-0.128
ashing-0.121
dy-0.116
uggets-0.114
Token'
Token ID6
Feature activation+1.57e+00

Pos logit contributions
mary+0.024
 watered+0.021
ashing+0.019
dy+0.018
bugs+0.017
Neg logit contributions
iest-0.046
hy-0.043
bars-0.042
mm-0.040
rob-0.038
Token.
Token ID13
Feature activation+5.94e-02

Pos logit contributions
iest+0.061
bars+0.058
hy+0.056
mm+0.056
 elbow+0.054
Neg logit contributions
mary-0.035
 watered-0.029
ashing-0.027
 over-0.025
dy-0.024
Token
Token ID198
Feature activation+4.08e-01

Pos logit contributions
mary+0.003
 watered+0.003
ashing+0.002
dy+0.002
uggets+0.002
Neg logit contributions
iest-0.004
hy-0.003
bars-0.003
mm-0.003
 course-0.003
Token
Token ID198
Feature activation+3.70e-01

Pos logit contributions
mary+0.018
 watered+0.017
ashing+0.016
dy+0.015
uggets+0.014
Neg logit contributions
iest-0.026
hy-0.024
bars-0.023
mm-0.022
 course-0.022
TokenM
Token ID44
Feature activation+1.29e+00

Pos logit contributions
mary+0.022
 watered+0.020
ashing+0.019
dy+0.018
uggets+0.018
Neg logit contributions
iest-0.020
hy-0.017
bars-0.016
mm-0.015
 course-0.014
Tokenoral
Token ID6864
Feature activation+3.11e+00

Pos logit contributions
mary+0.051
 watered+0.043
ashing+0.042
rig+0.040
dy+0.038
Neg logit contributions
iest-0.091
hy-0.082
bars-0.080
 elbow-0.074
rob-0.074
Token:
Token ID25
Feature activation+6.27e+00

Pos logit contributions
mary+0.132
 watered+0.112
ashing+0.103
rig+0.101
 over+0.100
Neg logit contributions
iest-0.206
hy-0.186
 elbow-0.185
bars-0.185
hetically-0.180
Token Being
Token ID11204
Feature activation+1.69e+00

Pos logit contributions
mary+0.363
 watered+0.333
ashing+0.309
dy+0.300
rig+0.294
Neg logit contributions
iest-0.323
hy-0.295
bars-0.293
mm-0.263
ance-0.249
Token brave
Token ID14802
Feature activation+3.85e-01

Pos logit contributions
mary+0.094
ashing+0.081
 watered+0.080
uggets+0.079
dy+0.075
Neg logit contributions
iest-0.093
hy-0.079
bars-0.074
ance-0.070
 course-0.069
Token is
Token ID318
Feature activation+2.07e+00

Pos logit contributions
mary+0.017
 watered+0.014
ashing+0.014
dy+0.014
 over+0.013
Neg logit contributions
iest-0.025
hy-0.023
bars-0.022
mm-0.022
rob-0.021
Token important
Token ID1593
Feature activation+1.44e+00

Pos logit contributions
mary+0.102
ashing+0.091
 watered+0.090
uggets+0.089
dy+0.086
Neg logit contributions
iest-0.127
hy-0.108
 course-0.100
ance-0.099
 temptation-0.098
Token,
Token ID11
Feature activation+3.51e-01

Pos logit contributions
mary+0.037
 watered+0.030
ashing+0.025
dy+0.023
uggets+0.021
Neg logit contributions
iest-0.124
hy-0.116
bars-0.113
mm-0.108
hetically-0.104
Token.
Token ID13
Feature activation+5.95e-01

Pos logit contributions
mary+0.003
 watered+0.003
ashing+0.003
dy+0.003
uggets+0.002
Neg logit contributions
iest-0.005
hy-0.005
bars-0.005
mm-0.005
rob-0.004
Token
Token ID198
Feature activation+3.28e-01

Pos logit contributions
mary+0.032
 watered+0.029
ashing+0.027
dy+0.026
uggets+0.026
Neg logit contributions
iest-0.034
hy-0.031
bars-0.029
mm-0.027
 course-0.025
Token
Token ID198
Feature activation+2.61e-01

Pos logit contributions
mary+0.016
 watered+0.014
ashing+0.013
uggets+0.012
bugs+0.012
Neg logit contributions
iest-0.019
hy-0.019
bars-0.017
 course-0.017
mm-0.017
TokenM
Token ID44
Feature activation+1.21e+00

Pos logit contributions
mary+0.015
 watered+0.013
ashing+0.012
dy+0.012
uggets+0.012
Neg logit contributions
iest-0.014
hy-0.013
bars-0.012
mm-0.011
 course-0.011
Tokenoral
Token ID6864
Feature activation+2.94e+00

Pos logit contributions
mary+0.064
 watered+0.057
ashing+0.054
dy+0.051
uggets+0.050
Neg logit contributions
iest-0.073
hy-0.065
bars-0.062
mm-0.058
iness-0.055
Token:
Token ID25
Feature activation+6.22e+00

Pos logit contributions
mary+0.126
 watered+0.109
 over+0.099
 to+0.098
rig+0.097
Neg logit contributions
iest-0.186
 elbow-0.173
hy-0.172
bars-0.170
hetically-0.166
Token Being
Token ID11204
Feature activation+5.63e-01

Pos logit contributions
mary+0.366
 watered+0.336
ashing+0.313
dy+0.299
rig+0.298
Neg logit contributions
iest-0.313
hy-0.286
bars-0.283
mm-0.258
ance-0.244
Token respectful
Token ID25923
Feature activation-4.15e-01

Pos logit contributions
mary+0.030
 watered+0.026
ashing+0.026
uggets+0.024
dy+0.024
Neg logit contributions
iest-0.033
hy-0.029
bars-0.028
ance-0.025
mm-0.025
Token and
Token ID290
Feature activation+5.80e-01

Pos logit contributions
iest+0.029
hy+0.027
bars+0.026
mm+0.024
hetically+0.023
Neg logit contributions
mary-0.017
 watered-0.015
ashing-0.014
dy-0.013
uggets-0.012
Token gentle
Token ID10296
Feature activation-9.77e-01

Pos logit contributions
mary+0.029
 watered+0.027
ashing+0.025
dy+0.024
uggets+0.023
Neg logit contributions
iest-0.036
hy-0.032
bars-0.031
mm-0.029
rob-0.027
Token is
Token ID318
Feature activation+6.01e-01

Pos logit contributions
iest+0.065
hy+0.061
bars+0.058
mm+0.055
rob+0.053
Neg logit contributions
mary-0.044
 watered-0.038
ashing-0.035
dy-0.034
bugs-0.033
Token.
Token ID13
Feature activation+2.57e-01

Pos logit contributions
iest+0.010
hy+0.009
bars+0.009
mm+0.009
rob+0.008
Neg logit contributions
mary-0.006
 watered-0.005
ashing-0.005
dy-0.004
bugs-0.004
Token
Token ID198
Feature activation+4.29e-01

Pos logit contributions
mary+0.015
 watered+0.015
ashing+0.012
dy+0.012
uggets+0.012
Neg logit contributions
hy-0.012
iest-0.012
mm-0.011
bars-0.011
 course-0.010
Token
Token ID198
Feature activation+3.81e-01

Pos logit contributions
mary+0.023
 watered+0.021
ashing+0.020
bugs+0.019
flies+0.019
Neg logit contributions
iest-0.022
hy-0.021
he-0.020
 course-0.020
mm-0.019
TokenM
Token ID44
Feature activation+1.30e+00

Pos logit contributions
mary+0.027
 watered+0.025
ashing+0.025
uggets+0.024
dy+0.023
Neg logit contributions
iest-0.014
 course-0.013
hy-0.011
he-0.011
mm-0.011
Tokenoral
Token ID6864
Feature activation+3.15e+00

Pos logit contributions
mary+0.056
 watered+0.049
ashing+0.046
dy+0.043
uggets+0.042
Neg logit contributions
iest-0.090
hy-0.082
bars-0.079
mm-0.074
hetically-0.071
Token:
Token ID25
Feature activation+6.20e+00

Pos logit contributions
mary+0.140
 watered+0.117
ashing+0.112
 over+0.111
rig+0.109
Neg logit contributions
iest-0.197
 elbow-0.185
hy-0.179
bars-0.179
hetically-0.179
Token Be
Token ID1355
Feature activation+3.74e+00

Pos logit contributions
mary+0.360
 watered+0.327
ashing+0.306
dy+0.294
uggets+0.289
Neg logit contributions
iest-0.329
hy-0.293
bars-0.286
mm-0.259
ance-0.245
Token prepared
Token ID5597
Feature activation+1.33e+00

Pos logit contributions
mary+0.179
 watered+0.155
ashing+0.149
dy+0.137
bugs+0.135
Neg logit contributions
iest-0.243
hy-0.215
bars-0.205
mm-0.193
 course-0.188
Token for
Token ID329
Feature activation+1.71e+00

Pos logit contributions
mary+0.038
 watered+0.031
ashing+0.027
dy+0.025
bugs+0.023
Neg logit contributions
iest-0.111
hy-0.102
bars-0.099
mm-0.094
ance-0.091
Token any
Token ID597
Feature activation-8.08e-01

Pos logit contributions
mary+0.076
 watered+0.071
dy+0.061
ashing+0.060
uggets+0.060
Neg logit contributions
iest-0.115
hy-0.106
bars-0.104
mm-0.093
hetically-0.092
Token surprises
Token ID24072
Feature activation+1.22e+00

Pos logit contributions
iest+0.048
hy+0.045
bars+0.042
mm+0.040
hetically+0.038
Neg logit contributions
mary-0.041
 watered-0.038
ashing-0.035
dy-0.034
rig-0.033
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
mary+0.081
 watered+0.074
ashing+0.072
uggets+0.072
die+0.069
Neg logit contributions
iest-0.057
hy-0.047
bars-0.041
chair-0.038
mm-0.036
Token
Token ID198
Feature activation+1.95e-01

Pos logit contributions
mary+0.005
 watered+0.005
ashing+0.004
dy+0.004
uggets+0.004
Neg logit contributions
iest-0.007
hy-0.007
mm-0.007
bars-0.006
 course-0.006
Token
Token ID198
Feature activation+1.62e-01

Pos logit contributions
mary+0.010
ashing+0.009
 watered+0.008
uggets+0.008
dy+0.008
Neg logit contributions
iest-0.011
hy-0.010
 course-0.010
aid-0.010
mm-0.009
TokenM
Token ID44
Feature activation+1.16e+00

Pos logit contributions
mary+0.010
ashing+0.009
 watered+0.009
dy+0.009
uggets+0.009
Neg logit contributions
iest-0.008
hy-0.007
 course-0.007
mm-0.006
bars-0.006
Tokenoral
Token ID6864
Feature activation+3.03e+00

Pos logit contributions
mary+0.037
ashing+0.031
 watered+0.030
rig+0.027
 upon+0.026
Neg logit contributions
iest-0.088
hy-0.079
bars-0.078
hetically-0.074
bike-0.073
Token:
Token ID25
Feature activation+6.18e+00

Pos logit contributions
mary+0.158
 watered+0.144
 over+0.131
ashing+0.129
 to+0.124
Neg logit contributions
iest-0.168
bars-0.152
hetically-0.151
hy-0.149
 elbow-0.146
Token Hon
Token ID8835
Feature activation+1.84e+00

Pos logit contributions
mary+0.386
 watered+0.364
ashing+0.334
rig+0.330
dy+0.321
Neg logit contributions
iest-0.271
hy-0.260
bars-0.251
mm-0.236
ance-0.212
Tokenesty
Token ID9673
Feature activation+5.80e-01

Pos logit contributions
mary+0.105
 watered+0.098
ashing+0.087
 raining+0.086
uggets+0.085
Neg logit contributions
iest-0.090
hy-0.087
bars-0.077
bye-0.076
eness-0.076
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
mary+0.031
 watered+0.027
ashing+0.025
dy+0.025
bugs+0.024
Neg logit contributions
iest-0.034
hy-0.031
bars-0.030
mm-0.028
hetically-0.027
Token generosity
Token ID31569
Feature activation-9.48e-01

Pos logit contributions
mary+0.061
 watered+0.052
ashing+0.050
dy+0.048
uggets+0.046
Neg logit contributions
iest-0.070
hy-0.063
bars-0.061
mm-0.059
 course-0.059
Token and
Token ID290
Feature activation+1.23e+00

Pos logit contributions
iest+0.071
hy+0.067
bars+0.065
hetically+0.065
mm+0.064
Neg logit contributions
mary-0.029
 to-0.024
 watered-0.024
 for-0.023
dy-0.022
Token.
Token ID13
Feature activation+7.44e-02

Pos logit contributions
mary+0.066
 watered+0.061
ashing+0.058
uggets+0.057
die+0.055
Neg logit contributions
iest-0.052
hy-0.047
bars-0.040
chair-0.037
 click-0.036
Token
Token ID198
Feature activation+2.51e-01

Pos logit contributions
mary+0.003
 watered+0.003
ashing+0.002
dy+0.002
uggets+0.002
Neg logit contributions
iest-0.005
hy-0.005
bars-0.005
mm-0.004
iness-0.004
Token
Token ID198
Feature activation+2.38e-01

Pos logit contributions
mary+0.011
ashing+0.010
 watered+0.010
dy+0.009
 raining+0.009
Neg logit contributions
iest-0.016
hy-0.015
aid-0.014
mm-0.013
 course-0.013
TokenM
Token ID44
Feature activation+1.18e+00

Pos logit contributions
mary+0.014
ashing+0.013
 watered+0.013
dy+0.012
uggets+0.012
Neg logit contributions
iest-0.012
hy-0.011
mm-0.010
bars-0.010
 course-0.009
Tokenoral
Token ID6864
Feature activation+2.91e+00

Pos logit contributions
mary+0.043
 watered+0.035
ashing+0.033
 upon+0.030
uggets+0.030
Neg logit contributions
iest-0.086
hy-0.080
bars-0.078
bike-0.076
hing-0.076
Token:
Token ID25
Feature activation+6.13e+00

Pos logit contributions
mary+0.129
 watered+0.116
 over+0.110
 to+0.106
ashing+0.100
Neg logit contributions
iest-0.179
hetically-0.166
 elbow-0.163
bars-0.162
hy-0.161
Token Do
Token ID2141
Feature activation-1.88e-01

Pos logit contributions
mary+0.367
 watered+0.341
ashing+0.318
dy+0.305
rig+0.302
Neg logit contributions
iest-0.296
hy-0.276
bars-0.271
mm-0.247
ance-0.228
Token not
Token ID407
Feature activation+1.27e+00

Pos logit contributions
iest+0.014
hy+0.013
bars+0.012
mm+0.012
 course+0.011
Neg logit contributions
mary-0.007
 watered-0.006
ashing-0.006
dy-0.005
uggets-0.005
Token be
Token ID307
Feature activation+1.12e+00

Pos logit contributions
mary+0.070
 watered+0.064
ashing+0.060
dy+0.058
uggets+0.057
Neg logit contributions
iest-0.072
hy-0.064
bars-0.061
mm-0.057
hetically-0.054
Token selfish
Token ID20363
Feature activation+4.54e-01

Pos logit contributions
mary+0.056
 watered+0.051
ashing+0.045
dy+0.044
uggets+0.044
Neg logit contributions
iest-0.067
hy-0.063
bars-0.059
aid-0.053
 yourself-0.052
Token and
Token ID290
Feature activation+5.60e-01

Pos logit contributions
mary+0.014
 watered+0.012
ashing+0.012
dy+0.010
 over+0.010
Neg logit contributions
iest-0.036
hy-0.033
bars-0.031
mm-0.031
hetically-0.030
Token
Token ID220
Feature activation-2.00e+00

Pos logit contributions
mary+0.008
 watered+0.008
ashing+0.007
uggets+0.007
dy+0.007
Neg logit contributions
iest-0.009
hy-0.008
bars-0.008
mm-0.007
 course-0.007
Token
Token ID198
Feature activation+5.46e-02

Pos logit contributions
iest+0.131
hy+0.120
bars+0.118
mm+0.114
ance+0.108
Neg logit contributions
mary-0.088
 watered-0.080
ashing-0.071
uggets-0.065
dy-0.064
Token
Token ID198
Feature activation+1.91e-01

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
uggets+0.002
dy+0.002
Neg logit contributions
iest-0.004
hy-0.003
mm-0.003
bars-0.003
 course-0.003
TokenM
Token ID44
Feature activation+1.22e+00

Pos logit contributions
mary+0.012
 watered+0.011
ashing+0.011
uggets+0.011
 raining+0.010
Neg logit contributions
iest-0.009
hy-0.007
mm-0.007
 course-0.007
bars-0.007
Tokenoral
Token ID6864
Feature activation+2.99e+00

Pos logit contributions
mary+0.052
 watered+0.045
ashing+0.042
dy+0.040
rig+0.039
Neg logit contributions
iest-0.084
hy-0.077
bars-0.075
mm-0.068
 elbow-0.067
Token:
Token ID25
Feature activation+6.12e+00

Pos logit contributions
mary+0.122
 watered+0.102
ashing+0.092
rig+0.091
 over+0.089
Neg logit contributions
iest-0.205
hy-0.187
bars-0.184
 elbow-0.182
mm-0.175
Token It
Token ID632
Feature activation+2.69e+00

Pos logit contributions
mary+0.327
 watered+0.296
ashing+0.274
dy+0.262
rig+0.258
Neg logit contributions
iest-0.341
bars-0.310
hy-0.308
mm-0.284
 course-0.270
Token's
Token ID338
Feature activation+2.91e+00

Pos logit contributions
mary+0.135
 watered+0.119
ashing+0.116
uggets+0.109
dy+0.107
Neg logit contributions
iest-0.166
hy-0.147
bars-0.142
mm-0.133
iness-0.126
Token better
Token ID1365
Feature activation+2.53e+00

Pos logit contributions
mary+0.142
ashing+0.127
 watered+0.122
bugs+0.116
rig+0.108
Neg logit contributions
iest-0.182
mm-0.152
hy-0.147
bars-0.145
 course-0.145
Token to
Token ID284
Feature activation+1.53e+00

Pos logit contributions
mary+0.072
 watered+0.051
ashing+0.046
bugs+0.043
rig+0.042
Neg logit contributions
iest-0.214
hy-0.193
bars-0.189
mm-0.180
ance-0.178
Token be
Token ID307
Feature activation+1.36e+00

Pos logit contributions
mary+0.081
 watered+0.077
dy+0.065
 printed+0.064
 over+0.063
Neg logit contributions
iest-0.093
bars-0.085
hy-0.083
rob-0.078
mm-0.073
Token.
Token ID13
Feature activation+1.58e-01

Pos logit contributions
mary+0.073
 watered+0.066
ashing+0.064
uggets+0.063
die+0.059
Neg logit contributions
iest-0.056
hy-0.049
bars-0.042
chair-0.040
 click-0.037
Token
Token ID198
Feature activation+2.78e-01

Pos logit contributions
mary+0.007
 watered+0.007
ashing+0.006
dy+0.006
uggets+0.005
Neg logit contributions
iest-0.010
hy-0.010
mm-0.009
bars-0.009
 course-0.008
Token
Token ID198
Feature activation+2.48e-01

Pos logit contributions
mary+0.014
ashing+0.013
 watered+0.012
uggets+0.011
dy+0.011
Neg logit contributions
iest-0.015
hy-0.015
aid-0.014
 course-0.014
he-0.013
TokenM
Token ID44
Feature activation+1.18e+00

Pos logit contributions
mary+0.016
ashing+0.015
 watered+0.015
dy+0.014
uggets+0.014
Neg logit contributions
iest-0.011
hy-0.010
 course-0.009
mm-0.009
aid-0.009
Tokenoral
Token ID6864
Feature activation+2.99e+00

Pos logit contributions
mary+0.045
 watered+0.039
ashing+0.035
dy+0.033
uggets+0.032
Neg logit contributions
iest-0.089
hy-0.082
bars-0.079
mm-0.075
iness-0.072
Token:
Token ID25
Feature activation+6.08e+00

Pos logit contributions
mary+0.135
 watered+0.122
 over+0.113
 to+0.109
ashing+0.105
Neg logit contributions
iest-0.182
bars-0.168
hetically-0.167
hy-0.164
 elbow-0.164
Token Do
Token ID2141
Feature activation-2.30e-01

Pos logit contributions
mary+0.374
 watered+0.349
ashing+0.327
rig+0.312
dy+0.311
Neg logit contributions
iest-0.280
hy-0.263
bars-0.257
mm-0.235
ance-0.218
Token not
Token ID407
Feature activation+1.21e+00

Pos logit contributions
iest+0.016
hy+0.014
mm+0.014
bars+0.013
 course+0.013
Neg logit contributions
mary-0.010
 watered-0.008
ashing-0.008
dy-0.007
rig-0.007
Token touch
Token ID3638
Feature activation-8.72e-01

Pos logit contributions
mary+0.068
 watered+0.062
ashing+0.058
dy+0.056
uggets+0.055
Neg logit contributions
iest-0.067
hy-0.060
bars-0.057
mm-0.052
iness-0.049
Token or
Token ID393
Feature activation-5.18e-01

Pos logit contributions
iest+0.054
hy+0.049
bars+0.047
mm+0.043
hetically+0.041
Neg logit contributions
mary-0.044
 watered-0.039
ashing-0.037
dy-0.035
uggets-0.034
Token open
Token ID1280
Feature activation+7.88e-01

Pos logit contributions
iest+0.029
hy+0.026
bars+0.024
mm+0.022
iness+0.021
Neg logit contributions
mary-0.029
 watered-0.026
ashing-0.025
dy-0.024
uggets-0.024
TokenThis
Token ID1212
Feature activation-1.03e-01

Pos logit contributions
mary+0.006
 watered+0.006
ashing+0.005
dy+0.005
uggets+0.005
Neg logit contributions
iest-0.007
hy-0.006
bars-0.006
mm-0.005
 course-0.005
Token story
Token ID1621
Feature activation+2.10e+00

Pos logit contributions
iest+0.006
hy+0.006
bars+0.006
mm+0.005
hetically+0.005
Neg logit contributions
mary-0.005
 watered-0.005
ashing-0.004
dy-0.004
bugs-0.004
Token has
Token ID468
Feature activation+2.12e+00

Pos logit contributions
mary+0.120
 watered+0.108
ashing+0.103
dy+0.099
uggets+0.098
Neg logit contributions
iest-0.117
hy-0.104
bars-0.099
mm-0.091
iness-0.086
Token a
Token ID257
Feature activation+6.70e-01

Pos logit contributions
mary+0.092
 watered+0.082
ashing+0.074
dy+0.071
uggets+0.069
Neg logit contributions
iest-0.145
hy-0.131
bars-0.128
mm-0.120
hetically-0.116
Token moral
Token ID6573
Feature activation+3.55e+00

Pos logit contributions
mary+0.038
ashing+0.034
 watered+0.033
uggets+0.032
bugs+0.032
Neg logit contributions
iest-0.034
hy-0.033
 helmet-0.029
 course-0.029
 temptation-0.028
Token:
Token ID25
Feature activation+6.03e+00

Pos logit contributions
mary+0.146
 watered+0.129
 to+0.126
 over+0.114
 prints+0.113
Neg logit contributions
iest-0.228
hetically-0.213
 elbow-0.210
bars-0.206
hy-0.206
Token never
Token ID1239
Feature activation+5.51e-02

Pos logit contributions
mary+0.347
 watered+0.316
ashing+0.297
dy+0.285
rig+0.278
Neg logit contributions
iest-0.322
hy-0.291
bars-0.281
mm-0.256
 course-0.240
Token take
Token ID1011
Feature activation-7.75e-01

Pos logit contributions
mary+0.003
 watered+0.003
ashing+0.002
dy+0.002
bugs+0.002
Neg logit contributions
iest-0.003
hy-0.003
bars-0.003
mm-0.003
hetically-0.003
Token things
Token ID1243
Feature activation-1.36e+00

Pos logit contributions
iest+0.040
hy+0.036
bars+0.032
mm+0.030
ance+0.030
Neg logit contributions
mary-0.046
 watered-0.042
ashing-0.041
rig-0.038
dy-0.038
Token that
Token ID326
Feature activation+3.03e-01

Pos logit contributions
iest+0.096
hy+0.088
bars+0.086
mm+0.081
rob+0.080
Neg logit contributions
mary-0.056
 watered-0.048
ashing-0.045
dy-0.041
uggets-0.041
Token belong
Token ID5594
Feature activation+1.02e+00

Pos logit contributions
mary+0.016
 watered+0.015
ashing+0.013
 to+0.013
 prints+0.013
Neg logit contributions
iest-0.017
bars-0.015
hy-0.015
rob-0.014
hetically-0.014
Token.
Token ID13
Feature activation+1.78e-01

Pos logit contributions
mary+0.075
 watered+0.069
uggets+0.067
ashing+0.066
die+0.063
Neg logit contributions
iest-0.046
hy-0.038
chair-0.032
bars-0.031
mm-0.028
Token
Token ID198
Feature activation+1.32e-01

Pos logit contributions
mary+0.009
 watered+0.008
ashing+0.008
dy+0.008
rig+0.007
Neg logit contributions
hy-0.010
iest-0.010
mm-0.010
bars-0.009
 course-0.009
Token
Token ID198
Feature activation+1.00e-01

Pos logit contributions
mary+0.007
ashing+0.007
 watered+0.006
dy+0.006
flies+0.006
Neg logit contributions
iest-0.007
hy-0.006
 course-0.006
he-0.006
aid-0.006
TokenM
Token ID44
Feature activation+1.12e+00

Pos logit contributions
mary+0.007
ashing+0.006
 watered+0.006
dy+0.006
uggets+0.006
Neg logit contributions
iest-0.004
 course-0.004
hy-0.004
mm-0.003
he-0.003
Tokenoral
Token ID6864
Feature activation+2.96e+00

Pos logit contributions
mary+0.046
 watered+0.040
ashing+0.038
dy+0.035
uggets+0.034
Neg logit contributions
iest-0.079
hy-0.072
bars-0.070
mm-0.064
hetically-0.063
Token:
Token ID25
Feature activation+6.02e+00

Pos logit contributions
mary+0.134
 watered+0.119
 over+0.111
ashing+0.106
 to+0.105
Neg logit contributions
iest-0.183
bars-0.166
hetically-0.165
hy-0.165
 elbow-0.163
Token Sharing
Token ID36644
Feature activation+1.68e+00

Pos logit contributions
mary+0.377
 watered+0.354
ashing+0.324
rig+0.319
dy+0.313
Neg logit contributions
iest-0.265
hy-0.250
bars-0.247
mm-0.230
ance-0.207
Token is
Token ID318
Feature activation+1.58e+00

Pos logit contributions
mary+0.107
 watered+0.095
ashing+0.095
uggets+0.090
dy+0.088
Neg logit contributions
iest-0.082
hy-0.068
bars-0.067
mm-0.062
 course-0.061
Token caring
Token ID18088
Feature activation+1.40e+00

Pos logit contributions
mary+0.096
ashing+0.088
uggets+0.081
bugs+0.081
 watered+0.081
Neg logit contributions
iest-0.074
 course-0.064
aid-0.061
hy-0.061
 temptation-0.060
Token.
Token ID13
Feature activation+4.72e-01

Pos logit contributions
mary+0.063
 watered+0.055
ashing+0.051
dy+0.049
uggets+0.048
Neg logit contributions
iest-0.095
hy-0.086
bars-0.083
mm-0.077
hetically-0.074
Token Being
Token ID11204
Feature activation+5.70e-02

Pos logit contributions
mary+0.023
 watered+0.020
ashing+0.019
dy+0.018
uggets+0.018
Neg logit contributions
iest-0.030
hy-0.027
bars-0.026
mm-0.024
iness-0.023
TokenM
Token ID44
Feature activation+1.43e+00

Pos logit contributions
mary+0.034
 watered+0.032
ashing+0.029
uggets+0.029
flies+0.028
Neg logit contributions
iest-0.023
 course-0.019
hy-0.019
mm-0.017
Fine-0.017
Tokenoral
Token ID6864
Feature activation+3.28e+00

Pos logit contributions
mary+0.072
 watered+0.064
ashing+0.060
dy+0.057
uggets+0.056
Neg logit contributions
iest-0.089
hy-0.080
bars-0.077
mm-0.072
iness-0.068
Token of
Token ID286
Feature activation+3.20e+00

Pos logit contributions
mary+0.136
 watered+0.112
ashing+0.105
rig+0.100
 over+0.100
Neg logit contributions
iest-0.224
hy-0.204
bars-0.203
 elbow-0.198
hetically-0.194
Token the
Token ID262
Feature activation+2.64e+00

Pos logit contributions
mary+0.162
 watered+0.144
ashing+0.141
dy+0.129
uggets+0.127
Neg logit contributions
iest-0.199
hy-0.174
bars-0.167
mm-0.157
 course-0.156
Token story
Token ID1621
Feature activation+4.19e+00

Pos logit contributions
mary+0.141
 watered+0.127
ashing+0.120
dy+0.114
uggets+0.113
Neg logit contributions
iest-0.158
hy-0.141
bars-0.134
mm-0.126
 course-0.119
Token:
Token ID25
Feature activation+5.99e+00

Pos logit contributions
mary+0.109
 watered+0.086
ashing+0.074
dy+0.067
uggets+0.063
Neg logit contributions
iest-0.361
hy-0.335
bars-0.326
mm-0.309
iness-0.299
Token We
Token ID775
Feature activation+1.22e+00

Pos logit contributions
mary+0.344
 watered+0.316
ashing+0.293
dy+0.284
rig+0.279
Neg logit contributions
iest-0.314
hy-0.284
bars-0.279
mm-0.255
ance-0.239
Token should
Token ID815
Feature activation+1.14e+00

Pos logit contributions
mary+0.063
 watered+0.057
ashing+0.052
dy+0.050
uggets+0.048
Neg logit contributions
iest-0.075
hy-0.067
bars-0.065
mm-0.060
hetically-0.057
Token not
Token ID407
Feature activation+1.45e+00

Pos logit contributions
mary+0.041
 watered+0.037
dy+0.032
ashing+0.030
 qu+0.030
Neg logit contributions
iest-0.088
bars-0.082
hy-0.080
rob-0.077
hetically-0.072
Token take
Token ID1011
Feature activation-1.13e+00

Pos logit contributions
mary+0.085
 watered+0.077
ashing+0.073
dy+0.070
uggets+0.069
Neg logit contributions
iest-0.078
hy-0.069
bars-0.066
mm-0.060
hetically-0.057
Token risks
Token ID7476
Feature activation-7.87e-01

Pos logit contributions
iest+0.066
hy+0.059
bars+0.056
mm+0.052
iness+0.049
Neg logit contributions
mary-0.061
 watered-0.055
ashing-0.052
dy-0.050
uggets-0.049
Token.
Token ID13
Feature activation+4.57e-01

Pos logit contributions
mary+0.070
rig+0.064
die+0.061
dy+0.061
ashing+0.061
Neg logit contributions
iest-0.050
hy-0.045
 course-0.043
mm-0.037
 goodness-0.036
Token
Token ID198
Feature activation+4.31e-01

Pos logit contributions
 watered+0.025
mary+0.025
uggets+0.022
 printed+0.021
ashing+0.021
Neg logit contributions
mm-0.020
 course-0.019
iest-0.019
hy-0.019
 goodness-0.018
Token
Token ID198
Feature activation+3.49e-01

Pos logit contributions
mary+0.024
 watered+0.022
ashing+0.021
uggets+0.020
flies+0.020
Neg logit contributions
iest-0.021
he-0.019
 course-0.018
mm-0.017
hy-0.017
TokenM
Token ID44
Feature activation+1.32e+00

Pos logit contributions
mary+0.022
ashing+0.021
 watered+0.020
uggets+0.020
 prints+0.019
Neg logit contributions
iest-0.015
 course-0.013
No-0.012
mm-0.012
he-0.012
Tokenoral
Token ID6864
Feature activation+3.00e+00

Pos logit contributions
mary+0.061
 watered+0.055
ashing+0.050
uggets+0.048
dy+0.047
Neg logit contributions
iest-0.092
mm-0.078
hy-0.077
bars-0.074
iness-0.071
Token:
Token ID25
Feature activation+5.96e+00

Pos logit contributions
mary+0.136
 watered+0.117
ashing+0.109
rig+0.104
 over+0.103
Neg logit contributions
iest-0.192
hy-0.174
bars-0.173
 elbow-0.169
hetically-0.166
Token Sharing
Token ID36644
Feature activation+1.83e+00

Pos logit contributions
mary+0.360
 watered+0.331
ashing+0.304
rig+0.303
dy+0.294
Neg logit contributions
iest-0.273
bars-0.255
hy-0.247
mm-0.235
 course-0.224
Token is
Token ID318
Feature activation+1.70e+00

Pos logit contributions
mary+0.110
 watered+0.098
ashing+0.097
uggets+0.092
dy+0.090
Neg logit contributions
iest-0.095
hy-0.080
bars-0.078
mm-0.072
 course-0.071
Token caring
Token ID18088
Feature activation+1.40e+00

Pos logit contributions
mary+0.098
ashing+0.091
uggets+0.083
 watered+0.082
bugs+0.081
Neg logit contributions
iest-0.089
 course-0.074
hy-0.068
 temptation-0.068
ance-0.067
Token!
Token ID0
Feature activation+9.29e-01

Pos logit contributions
mary+0.062
 watered+0.054
ashing+0.050
dy+0.047
uggets+0.047
Neg logit contributions
iest-0.097
hy-0.086
bars-0.083
mm-0.078
iness-0.076
Token When
Token ID1649
Feature activation+5.71e-01

Pos logit contributions
mary+0.042
 watered+0.039
ashing+0.036
dy+0.032
rig+0.030
Neg logit contributions
iest-0.061
hy-0.056
bars-0.054
mm-0.053
 course-0.050
Token."
Token ID526
Feature activation-1.42e-01

Pos logit contributions
iest+0.236
hy+0.218
bars+0.207
mm+0.197
rob+0.189
Neg logit contributions
mary-0.150
 watered-0.131
ashing-0.122
dy-0.117
uggets-0.112
Token
Token ID198
Feature activation+1.56e-02

Pos logit contributions
iest+0.011
hy+0.010
bars+0.009
mm+0.009
iness+0.008
Neg logit contributions
mary-0.006
 watered-0.005
ashing-0.004
dy-0.004
uggets-0.004
Token
Token ID198
Feature activation+1.41e-01

Pos logit contributions
mary+0.001
 watered+0.001
ashing+0.001
uggets+0.000
dy+0.000
Neg logit contributions
iest-0.001
hy-0.001
bars-0.001
mm-0.001
 course-0.001
TokenM
Token ID44
Feature activation+9.89e-01

Pos logit contributions
mary+0.007
 watered+0.006
dy+0.006
ashing+0.006
rig+0.006
Neg logit contributions
iest-0.009
hy-0.008
bars-0.008
mm-0.007
iness-0.007
Tokenoral
Token ID6864
Feature activation+2.81e+00

Pos logit contributions
mary+0.044
 watered+0.040
dy+0.039
ashing+0.038
rig+0.036
Neg logit contributions
iest-0.064
hy-0.058
bars-0.055
rob-0.053
hing-0.050
Token:
Token ID25
Feature activation+5.93e+00

Pos logit contributions
mary+0.113
 watered+0.093
 over+0.089
 to+0.087
rig+0.086
Neg logit contributions
iest-0.187
 elbow-0.176
hy-0.170
bars-0.169
hetically-0.166
Token It
Token ID632
Feature activation+2.33e+00

Pos logit contributions
mary+0.329
 watered+0.299
ashing+0.280
dy+0.268
rig+0.262
Neg logit contributions
iest-0.325
hy-0.292
bars-0.287
mm-0.263
 course-0.247
Token is
Token ID318
Feature activation+1.68e+00

Pos logit contributions
mary+0.116
 watered+0.103
ashing+0.099
uggets+0.094
dy+0.091
Neg logit contributions
iest-0.145
hy-0.129
bars-0.125
mm-0.116
hetically-0.111
Token important
Token ID1593
Feature activation+1.13e+00

Pos logit contributions
mary+0.081
ashing+0.074
 watered+0.072
bugs+0.071
uggets+0.068
Neg logit contributions
iest-0.102
hy-0.086
 temptation-0.082
 course-0.081
bars-0.081
Token to
Token ID284
Feature activation+4.32e-01

Pos logit contributions
mary+0.025
 watered+0.019
ashing+0.016
dy+0.013
uggets+0.013
Neg logit contributions
iest-0.103
hy-0.095
bars-0.093
mm-0.088
ance-0.086
Token listen
Token ID6004
Feature activation+1.38e+00

Pos logit contributions
mary+0.020
 watered+0.019
dy+0.017
 qu+0.016
ashing+0.016
Neg logit contributions
iest-0.029
bars-0.026
hy-0.026
rob-0.023
mm-0.023
Token
Token ID198
Feature activation+5.88e-01

Pos logit contributions
mary+0.024
 watered+0.022
ashing+0.020
dy+0.020
uggets+0.019
Neg logit contributions
iest-0.024
hy-0.021
bars-0.021
mm-0.019
ance-0.018
Token
Token ID198
Feature activation+5.21e-01

Pos logit contributions
mary+0.026
 watered+0.023
ashing+0.022
uggets+0.020
dy+0.020
Neg logit contributions
iest-0.038
hy-0.036
 course-0.033
mm-0.033
bars-0.033
TokenM
Token ID44
Feature activation+1.42e+00

Pos logit contributions
mary+0.033
 watered+0.031
ashing+0.030
uggets+0.028
dy+0.028
Neg logit contributions
iest-0.025
hy-0.022
bars-0.020
mm-0.019
 course-0.019
Tokenoral
Token ID6864
Feature activation+3.17e+00

Pos logit contributions
mary+0.066
 watered+0.058
ashing+0.054
dy+0.051
rig+0.050
Neg logit contributions
iest-0.093
hy-0.085
bars-0.082
rob-0.074
mm-0.074
Token Value
Token ID11052
Feature activation+4.22e+00

Pos logit contributions
mary+0.133
 watered+0.111
ashing+0.103
 over+0.101
rig+0.101
Neg logit contributions
iest-0.210
 elbow-0.193
hy-0.192
bars-0.188
hetically-0.187
Token:
Token ID25
Feature activation+5.90e+00

Pos logit contributions
mary+0.133
 watered+0.110
ashing+0.095
dy+0.091
uggets+0.084
Neg logit contributions
iest-0.340
hy-0.319
bars-0.308
mm-0.292
 elbow-0.281
Token Remember
Token ID11436
Feature activation+1.97e+00

Pos logit contributions
mary+0.339
 watered+0.308
ashing+0.289
dy+0.279
uggets+0.273
Neg logit contributions
iest-0.317
hy-0.282
bars-0.275
mm-0.249
ance-0.234
Token that
Token ID326
Feature activation+1.22e+00

Pos logit contributions
mary+0.048
 watered+0.037
ashing+0.032
dy+0.028
uggets+0.026
Neg logit contributions
iest-0.173
hy-0.161
bars-0.156
mm-0.149
hetically-0.144
Token you
Token ID345
Feature activation+1.60e+00

Pos logit contributions
mary+0.059
 watered+0.053
ashing+0.049
dy+0.047
uggets+0.045
Neg logit contributions
iest-0.077
hy-0.071
bars-0.067
mm-0.063
hetically-0.060
Token can
Token ID460
Feature activation+5.74e-01

Pos logit contributions
mary+0.086
 watered+0.079
ashing+0.072
dy+0.071
bugs+0.068
Neg logit contributions
iest-0.092
hy-0.083
bars-0.080
mm-0.074
rob-0.070
Token always
Token ID1464
Feature activation+1.23e+00

Pos logit contributions
mary+0.026
 watered+0.023
 over+0.021
dy+0.021
 to+0.021
Neg logit contributions
iest-0.037
hy-0.035
bars-0.033
mm-0.031
rob-0.030
Token.
Token ID13
Feature activation+5.59e-02

Pos logit contributions
mary+0.069
 watered+0.064
ashing+0.059
uggets+0.058
dy+0.055
Neg logit contributions
iest-0.061
hy-0.054
bars-0.047
mm-0.044
 temptation-0.043
Token
Token ID198
Feature activation+4.07e-02

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
dy+0.002
uggets+0.002
Neg logit contributions
iest-0.004
hy-0.004
bars-0.003
mm-0.003
 course-0.003
Token
Token ID198
Feature activation+6.13e-02

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
uggets+0.002
dy+0.001
Neg logit contributions
iest-0.002
hy-0.002
 course-0.002
aid-0.002
bars-0.002
TokenM
Token ID44
Feature activation+1.11e+00

Pos logit contributions
mary+0.004
 watered+0.003
ashing+0.003
uggets+0.003
dy+0.003
Neg logit contributions
iest-0.003
hy-0.003
bars-0.003
 course-0.003
mm-0.003
Tokenoral
Token ID6864
Feature activation+2.72e+00

Pos logit contributions
mary+0.045
 watered+0.039
ashing+0.036
dy+0.034
uggets+0.033
Neg logit contributions
iest-0.079
hy-0.072
bars-0.070
mm-0.065
hetically-0.063
Token:
Token ID25
Feature activation+5.89e+00

Pos logit contributions
mary+0.109
 watered+0.095
 over+0.090
 to+0.088
ashing+0.083
Neg logit contributions
iest-0.180
 elbow-0.165
hetically-0.165
hy-0.163
bars-0.163
Token Sharing
Token ID36644
Feature activation+1.55e+00

Pos logit contributions
mary+0.370
 watered+0.347
ashing+0.320
rig+0.311
dy+0.309
Neg logit contributions
iest-0.260
bars-0.244
hy-0.243
mm-0.223
ance-0.205
Token is
Token ID318
Feature activation+1.47e+00

Pos logit contributions
mary+0.096
 watered+0.086
ashing+0.084
uggets+0.080
dy+0.079
Neg logit contributions
iest-0.078
hy-0.067
bars-0.065
mm-0.059
 course-0.058
Token caring
Token ID18088
Feature activation+1.24e+00

Pos logit contributions
mary+0.086
ashing+0.077
 watered+0.072
uggets+0.072
bugs+0.070
Neg logit contributions
iest-0.074
 course-0.063
hy-0.063
 temptation-0.060
ance-0.058
Token,
Token ID11
Feature activation+3.03e-01

Pos logit contributions
mary+0.055
 watered+0.049
ashing+0.045
dy+0.043
uggets+0.042
Neg logit contributions
iest-0.084
hy-0.077
bars-0.074
mm-0.069
hetically-0.066
Token and
Token ID290
Feature activation+5.76e-01

Pos logit contributions
mary+0.015
 watered+0.012
ashing+0.012
uggets+0.011
dy+0.011
Neg logit contributions
iest-0.018
mm-0.016
bars-0.016
hy-0.016
 course-0.016
TokenM
Token ID44
Feature activation+9.88e-01

Pos logit contributions
mary+0.006
 watered+0.006
ashing+0.006
dy+0.005
uggets+0.005
Neg logit contributions
iest-0.005
hy-0.004
bars-0.004
mm-0.004
 course-0.004
Tokenoral
Token ID6864
Feature activation+3.01e+00

Pos logit contributions
mary+0.049
 watered+0.044
ashing+0.041
dy+0.039
uggets+0.038
Neg logit contributions
iest-0.062
hy-0.056
bars-0.054
mm-0.049
rob-0.048
Token of
Token ID286
Feature activation+2.94e+00

Pos logit contributions
mary+0.128
 watered+0.108
 over+0.099
rig+0.098
 to+0.097
Neg logit contributions
iest-0.195
 elbow-0.183
hy-0.178
bars-0.176
hetically-0.174
Token the
Token ID262
Feature activation+2.16e+00

Pos logit contributions
mary+0.151
 watered+0.132
ashing+0.131
dy+0.120
rig+0.117
Neg logit contributions
iest-0.183
hy-0.158
bars-0.151
mm-0.144
 course-0.144
Token story
Token ID1621
Feature activation+3.97e+00

Pos logit contributions
mary+0.124
 watered+0.115
ashing+0.112
uggets+0.106
dy+0.102
Neg logit contributions
iest-0.120
hy-0.103
bars-0.097
mm-0.094
 course-0.090
Token:
Token ID25
Feature activation+5.87e+00

Pos logit contributions
mary+0.088
 watered+0.063
ashing+0.051
dy+0.049
uggets+0.042
Neg logit contributions
iest-0.356
hy-0.331
bars-0.322
mm-0.305
 elbow-0.301
Token Hard
Token ID6912
Feature activation+8.95e-02

Pos logit contributions
mary+0.323
 watered+0.292
ashing+0.275
dy+0.264
uggets+0.259
Neg logit contributions
iest-0.337
hy-0.299
bars-0.285
mm-0.262
iness-0.249
Token work
Token ID670
Feature activation+1.96e+00

Pos logit contributions
mary+0.003
ashing+0.003
 watered+0.003
 for+0.002
 raining+0.002
Neg logit contributions
iest-0.007
hy-0.006
rob-0.006
bars-0.006
robat-0.006
Token and
Token ID290
Feature activation+1.20e+00

Pos logit contributions
mary+0.074
 watered+0.066
ashing+0.057
 over+0.056
dy+0.054
Neg logit contributions
iest-0.138
hy-0.133
bars-0.122
mm-0.122
rob-0.120
Token care
Token ID1337
Feature activation-7.12e-01

Pos logit contributions
mary+0.059
 watered+0.058
ashing+0.048
dy+0.048
 over+0.048
Neg logit contributions
iest-0.074
hy-0.070
bars-0.062
rob-0.060
mm-0.058
Token can
Token ID460
Feature activation+3.49e-01

Pos logit contributions
iest+0.060
hy+0.057
bars+0.055
mm+0.053
rob+0.053
Neg logit contributions
mary-0.018
 watered-0.015
ashing-0.014
dy-0.012
 upon-0.012
TokenM
Token ID44
Feature activation+1.13e+00

Pos logit contributions
mary+0.006
 watered+0.006
ashing+0.005
uggets+0.005
dy+0.005
Neg logit contributions
iest-0.006
hy-0.005
bars-0.005
mm-0.005
 course-0.004
Tokenoral
Token ID6864
Feature activation+3.08e+00

Pos logit contributions
mary+0.046
 watered+0.040
ashing+0.037
dy+0.035
rig+0.034
Neg logit contributions
iest-0.080
hy-0.073
bars-0.071
rob-0.065
bike-0.065
Token of
Token ID286
Feature activation+2.97e+00

Pos logit contributions
mary+0.146
 watered+0.128
ashing+0.118
 over+0.117
rig+0.113
Neg logit contributions
iest-0.188
bars-0.172
hy-0.167
 elbow-0.164
hetically-0.161
Token the
Token ID262
Feature activation+2.21e+00

Pos logit contributions
mary+0.161
ashing+0.143
 watered+0.140
dy+0.128
rig+0.128
Neg logit contributions
iest-0.176
hy-0.152
 course-0.141
bars-0.139
mm-0.136
Token story
Token ID1621
Feature activation+4.01e+00

Pos logit contributions
mary+0.132
 watered+0.121
ashing+0.118
uggets+0.111
bugs+0.108
Neg logit contributions
iest-0.120
hy-0.105
mm-0.095
bars-0.094
 course-0.091
Token:
Token ID25
Feature activation+5.86e+00

Pos logit contributions
mary+0.120
 watered+0.101
ashing+0.089
uggets+0.078
dy+0.077
Neg logit contributions
iest-0.331
hy-0.309
bars-0.297
mm-0.283
iness-0.274
Token Be
Token ID1355
Feature activation+3.08e+00

Pos logit contributions
mary+0.360
 watered+0.327
ashing+0.312
dy+0.301
rig+0.297
Neg logit contributions
iest-0.283
hy-0.257
bars-0.247
mm-0.224
 course-0.211
Token careful
Token ID8161
Feature activation-2.65e+00

Pos logit contributions
mary+0.167
ashing+0.141
 watered+0.141
rig+0.131
bugs+0.129
Neg logit contributions
iest-0.183
hy-0.159
bars-0.146
mm-0.139
 course-0.139
Token what
Token ID644
Feature activation+3.05e-01

Pos logit contributions
iest+0.201
hy+0.185
bars+0.179
mm+0.170
rob+0.162
Neg logit contributions
mary-0.097
 watered-0.082
ashing-0.075
dy-0.071
uggets-0.068
Token you
Token ID345
Feature activation+1.26e+00

Pos logit contributions
mary+0.018
ashing+0.016
 watered+0.016
uggets+0.016
rig+0.015
Neg logit contributions
iest-0.017
hy-0.013
bars-0.013
mm-0.012
iness-0.012
Token write
Token ID3551
Feature activation+1.12e+00

Pos logit contributions
mary+0.072
 watered+0.067
ashing+0.062
dy+0.060
rig+0.058
Neg logit contributions
iest-0.070
hy-0.061
bars-0.060
mm-0.055
hetically-0.051
TokenM
Token ID44
Feature activation+1.25e+00

Pos logit contributions
mary+0.024
 watered+0.021
ashing+0.021
uggets+0.020
dy+0.020
Neg logit contributions
iest-0.012
hy-0.010
bars-0.009
 course-0.008
mm-0.008
Tokenoral
Token ID6864
Feature activation+3.11e+00

Pos logit contributions
mary+0.050
 watered+0.044
ashing+0.041
dy+0.038
rig+0.038
Neg logit contributions
iest-0.088
hy-0.080
bars-0.077
mm-0.071
 elbow-0.071
Token of
Token ID286
Feature activation+2.94e+00

Pos logit contributions
mary+0.128
 watered+0.111
 over+0.103
rig+0.100
ashing+0.097
Neg logit contributions
iest-0.205
 elbow-0.191
bars-0.188
hy-0.186
hetically-0.183
Token the
Token ID262
Feature activation+2.30e+00

Pos logit contributions
mary+0.147
 watered+0.130
ashing+0.124
dy+0.117
uggets+0.114
Neg logit contributions
iest-0.184
hy-0.165
bars-0.158
mm-0.147
 course-0.142
Token story
Token ID1621
Feature activation+4.05e+00

Pos logit contributions
mary+0.124
 watered+0.112
ashing+0.106
uggets+0.100
dy+0.100
Neg logit contributions
iest-0.136
hy-0.122
bars-0.116
mm-0.109
 course-0.103
Token:
Token ID25
Feature activation+5.85e+00

Pos logit contributions
mary+0.098
 watered+0.075
ashing+0.063
dy+0.058
uggets+0.052
Neg logit contributions
iest-0.355
hy-0.329
bars-0.321
mm-0.305
hetically-0.297
Token You
Token ID921
Feature activation+1.81e+00

Pos logit contributions
mary+0.331
 watered+0.300
ashing+0.283
dy+0.272
uggets+0.267
Neg logit contributions
iest-0.324
hy-0.288
bars-0.276
mm-0.253
iness-0.238
Token should
Token ID815
Feature activation+1.19e+00

Pos logit contributions
mary+0.093
 watered+0.085
ashing+0.076
dy+0.075
bugs+0.073
Neg logit contributions
iest-0.110
hy-0.099
bars-0.096
mm-0.088
hetically-0.085
Token be
Token ID307
Feature activation+1.05e+00

Pos logit contributions
mary+0.044
 watered+0.039
dy+0.034
 over+0.032
ashing+0.031
Neg logit contributions
iest-0.091
bars-0.084
hy-0.081
rob-0.079
hetically-0.076
Token careful
Token ID8161
Feature activation-3.36e+00

Pos logit contributions
mary+0.055
 watered+0.049
ashing+0.046
uggets+0.044
dy+0.044
Neg logit contributions
iest-0.063
hy-0.056
bars-0.053
mm-0.049
 course-0.048
Token and
Token ID290
Feature activation+2.88e-01

Pos logit contributions
iest+0.270
hy+0.252
bars+0.240
mm+0.235
rob+0.231
Neg logit contributions
mary-0.104
 watered-0.087
ashing-0.080
dy-0.076
 over-0.069
Token,
Token ID11
Feature activation+7.88e-01

Pos logit contributions
iest+0.148
bars+0.144
hy+0.142
hing+0.135
hetically+0.133
Neg logit contributions
mary-0.077
 watered-0.066
 to-0.063
dy-0.062
 for-0.060
Token but
Token ID475
Feature activation+5.82e-01

Pos logit contributions
mary+0.050
 watered+0.046
ashing+0.044
dy+0.042
uggets+0.041
Neg logit contributions
iest-0.039
hy-0.033
bars-0.032
mm-0.030
 course-0.028
Token only
Token ID691
Feature activation+1.16e+00

Pos logit contributions
mary+0.030
 watered+0.027
ashing+0.025
dy+0.025
uggets+0.024
Neg logit contributions
iest-0.035
hy-0.032
bars-0.030
mm-0.027
rob-0.027
Token with
Token ID351
Feature activation-1.23e-01

Pos logit contributions
mary+0.048
 watered+0.043
ashing+0.039
dy+0.037
uggets+0.036
Neg logit contributions
iest-0.082
hy-0.075
bars-0.072
mm-0.068
hetically-0.065
Token our
Token ID674
Feature activation-2.07e-01

Pos logit contributions
iest+0.008
hy+0.007
bars+0.007
mm+0.007
rob+0.007
Neg logit contributions
mary-0.006
 watered-0.005
dy-0.004
 raining-0.004
uggets-0.004
Token supervision
Token ID20865
Feature activation-5.37e+00

Pos logit contributions
iest+0.012
hy+0.011
bars+0.010
mm+0.009
rob+0.009
Neg logit contributions
mary-0.011
 watered-0.011
ashing-0.009
dy-0.009
uggets-0.009
Token.
Token ID13
Feature activation+1.60e-01

Pos logit contributions
iest+0.405
hy+0.375
bars+0.348
mm+0.336
rob+0.331
Neg logit contributions
mary-0.191
 watered-0.166
dy-0.156
ashing-0.145
bugs-0.143
Token And
Token ID843
Feature activation+2.58e-01

Pos logit contributions
mary+0.008
ashing+0.006
uggets+0.006
bugs+0.006
dy+0.006
Neg logit contributions
iest-0.011
hy-0.009
bars-0.009
rob-0.008
iness-0.008
Token maybe
Token ID3863
Feature activation+1.03e-01

Pos logit contributions
mary+0.013
 watered+0.012
ashing+0.011
dy+0.011
uggets+0.011
Neg logit contributions
iest-0.016
hy-0.014
bars-0.013
rob-0.013
iness-0.012
Token you
Token ID345
Feature activation+8.67e-01

Pos logit contributions
mary+0.005
 watered+0.005
dy+0.004
 raining+0.004
uggets+0.004
Neg logit contributions
iest-0.006
hy-0.006
bars-0.005
hetically-0.005
hing-0.005
Token can
Token ID460
Feature activation+3.46e-01

Pos logit contributions
mary+0.053
 watered+0.048
ashing+0.047
uggets+0.045
dy+0.045
Neg logit contributions
iest-0.043
hy-0.039
bars-0.036
mm-0.032
ance-0.031
Token "
Token ID366
Feature activation+1.59e+00

Pos logit contributions
mary+0.029
 watered+0.025
ashing+0.023
rig+0.022
dy+0.021
Neg logit contributions
iest-0.064
hy-0.060
bars-0.058
mm-0.055
hetically-0.053
TokenNo
Token ID2949
Feature activation-2.52e+00

Pos logit contributions
mary+0.093
 watered+0.084
ashing+0.078
dy+0.078
 qu+0.077
Neg logit contributions
iest-0.086
bars-0.075
hy-0.074
iness-0.065
eness-0.063
Token,
Token ID11
Feature activation-2.92e-01

Pos logit contributions
iest+0.175
hy+0.166
bars+0.158
hing+0.145
hetically+0.143
Neg logit contributions
mary-0.101
dy-0.087
 watered-0.083
ashing-0.080
 raining-0.079
Token Ben
Token ID3932
Feature activation-6.64e-01

Pos logit contributions
iest+0.021
hy+0.019
bars+0.019
rob+0.017
eness+0.017
Neg logit contributions
mary-0.012
 watered-0.010
dy-0.009
ashing-0.009
bugs-0.008
Token.
Token ID13
Feature activation-2.24e-01

Pos logit contributions
iest+0.050
bars+0.047
hy+0.045
mm+0.042
hetically+0.042
Neg logit contributions
mary-0.025
 watered-0.020
dy-0.020
ashing-0.018
bugs-0.017
Token Leave
Token ID17446
Feature activation-5.37e+00

Pos logit contributions
iest+0.013
bars+0.010
hy+0.010
rob+0.009
iness+0.009
Neg logit contributions
mary-0.013
uggets-0.011
bugs-0.011
ashing-0.011
dy-0.011
Token me
Token ID502
Feature activation-1.71e+00

Pos logit contributions
iest+0.311
 course+0.267
hy+0.255
mm+0.251
 temptation+0.242
Neg logit contributions
mary-0.295
 watered-0.262
ashing-0.260
rig-0.248
uggets-0.231
Token alone
Token ID3436
Feature activation-3.15e+00

Pos logit contributions
iest+0.104
hy+0.093
bars+0.091
mm+0.087
rob+0.082
Neg logit contributions
mary-0.086
 watered-0.077
ashing-0.076
dy-0.070
bugs-0.069
Token.
Token ID13
Feature activation-6.34e-01

Pos logit contributions
iest+0.211
hy+0.191
bars+0.184
mm+0.172
iness+0.164
Neg logit contributions
mary-0.143
 watered-0.126
ashing-0.117
dy-0.111
uggets-0.108
Token You
Token ID921
Feature activation+2.77e-01

Pos logit contributions
iest+0.041
bars+0.031
iness+0.029
rob+0.029
robat+0.028
Neg logit contributions
mary-0.033
uggets-0.030
bugs-0.029
ashing-0.028
bug-0.027
Token are
Token ID389
Feature activation-1.57e+00

Pos logit contributions
mary+0.018
 watered+0.017
ashing+0.016
dy+0.015
bugs+0.015
Neg logit contributions
iest-0.013
hy-0.011
bars-0.011
mm-0.010
hetically-0.009
Token sh
Token ID427
Feature activation+2.65e-02

Pos logit contributions
iest+0.049
bars+0.044
hy+0.043
mm+0.038
eness+0.038
Neg logit contributions
mary-0.041
 watered-0.036
ashing-0.033
dy-0.033
bugs-0.032
Tokenoo
Token ID2238
Feature activation+1.37e+00

Pos logit contributions
mary+0.002
 watered+0.001
ashing+0.001
dy+0.001
rig+0.001
Neg logit contributions
iest-0.001
bars-0.001
hy-0.001
mm-0.001
 elbow-0.001
Token,
Token ID11
Feature activation-8.25e-01

Pos logit contributions
mary+0.066
dy+0.054
 watered+0.053
ashing+0.052
bugs+0.047
Neg logit contributions
iest-0.088
bars-0.082
hy-0.077
mm-0.071
 ignition-0.069
Token raven
Token ID37735
Feature activation+1.41e+00

Pos logit contributions
iest+0.052
bars+0.045
hy+0.044
mm+0.040
rob+0.040
Neg logit contributions
mary-0.041
 watered-0.036
ashing-0.034
dy-0.033
 qu-0.032
Token.
Token ID13
Feature activation-4.46e-01

Pos logit contributions
mary+0.075
 watered+0.067
ashing+0.063
dy+0.060
uggets+0.059
Neg logit contributions
iest-0.084
hy-0.075
bars-0.072
mm-0.066
hetically-0.063
Token Leave
Token ID17446
Feature activation-5.28e+00

Pos logit contributions
iest+0.031
rob+0.026
bars+0.026
robat+0.026
hetically+0.025
Neg logit contributions
mary-0.019
 qu-0.015
ectar-0.015
bugs-0.015
ashing-0.015
Token me
Token ID502
Feature activation-1.60e+00

Pos logit contributions
iest+0.335
hy+0.300
bars+0.281
mm+0.270
 course+0.261
Neg logit contributions
mary-0.260
 watered-0.231
ashing-0.221
dy-0.206
uggets-0.204
Token alone
Token ID3436
Feature activation-3.09e+00

Pos logit contributions
iest+0.095
hy+0.083
bars+0.083
mm+0.077
hetically+0.073
Neg logit contributions
mary-0.084
 watered-0.077
ashing-0.072
dy-0.069
bugs-0.068
Token.
Token ID13
Feature activation-4.13e-01

Pos logit contributions
iest+0.179
hy+0.160
bars+0.154
mm+0.142
hetically+0.134
Neg logit contributions
mary-0.168
 watered-0.151
ashing-0.142
dy-0.137
uggets-0.133
Token You
Token ID921
Feature activation+4.02e-01

Pos logit contributions
iest+0.029
bars+0.024
hetically+0.023
rob+0.023
robat+0.023
Neg logit contributions
mary-0.018
bugs-0.015
 qu-0.015
 raining-0.014
bug-0.014
Token are
Token ID389
Feature activation-1.49e+00

Pos logit contributions
mary+0.025
 watered+0.023
bugs+0.021
ashing+0.021
 qu+0.021
Neg logit contributions
iest-0.020
bars-0.017
hy-0.016
mm-0.016
hetically-0.015
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
iest+0.036
hy+0.033
bars+0.032
mm+0.030
hetically+0.029
Neg logit contributions
mary-0.023
 watered-0.020
ashing-0.019
dy-0.018
uggets-0.017
Token You
Token ID921
Feature activation+6.59e-01

Pos logit contributions
iest+0.008
bars+0.006
hy+0.006
iness+0.006
hetically+0.006
Neg logit contributions
mary-0.007
 watered-0.006
uggets-0.006
dy-0.006
bugs-0.006
Token are
Token ID389
Feature activation-1.30e+00

Pos logit contributions
mary+0.037
 watered+0.034
ashing+0.032
dy+0.031
bugs+0.030
Neg logit contributions
iest-0.037
hy-0.032
bars-0.031
mm-0.029
hetically-0.028
Token mean
Token ID1612
Feature activation-1.14e+00

Pos logit contributions
hy+0.065
iest+0.063
 yourself+0.056
 temptation+0.052
 ha+0.052
Neg logit contributions
mary-0.076
ashing-0.073
rig-0.068
 watered-0.067
dy-0.063
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
iest+0.077
hy+0.069
bars+0.067
mm+0.062
iness+0.061
Neg logit contributions
mary-0.052
 watered-0.046
ashing-0.042
dy-0.040
uggets-0.039
Token Leave
Token ID17446
Feature activation-5.28e+00

Pos logit contributions
iest+0.007
bars+0.006
hy+0.006
hetically+0.006
iness+0.005
Neg logit contributions
mary-0.009
 watered-0.008
uggets-0.008
bugs-0.008
dy-0.007
Token us
Token ID514
Feature activation-1.59e+00

Pos logit contributions
iest+0.313
hy+0.279
 course+0.258
bars+0.255
mm+0.254
Neg logit contributions
mary-0.280
 watered-0.252
ashing-0.245
rig-0.234
dy-0.225
Token alone
Token ID3436
Feature activation-3.05e+00

Pos logit contributions
iest+0.092
hy+0.081
bars+0.079
mm+0.074
hetically+0.069
Neg logit contributions
mary-0.086
 watered-0.079
ashing-0.074
dy-0.071
uggets-0.069
Token."
Token ID526
Feature activation-8.07e-01

Pos logit contributions
iest+0.176
hy+0.154
bars+0.146
mm+0.134
iness+0.131
Neg logit contributions
mary-0.168
 watered-0.150
ashing-0.141
dy-0.135
uggets-0.135
Token
Token ID198
Feature activation-5.16e-01

Pos logit contributions
iest+0.059
hy+0.054
bars+0.053
mm+0.050
hetically+0.047
Neg logit contributions
mary-0.032
 watered-0.027
ashing-0.025
dy-0.023
uggets-0.023
Token
Token ID198
Feature activation-3.55e-01

Pos logit contributions
iest+0.036
hy+0.034
bars+0.032
mm+0.031
 course+0.029
Neg logit contributions
mary-0.021
 watered-0.019
ashing-0.017
dy-0.016
uggets-0.016
TokenGo
Token ID5247
Feature activation+2.37e-01

Pos logit contributions
iest+0.031
hy+0.027
bars+0.027
mm+0.024
iness+0.024
Neg logit contributions
mary-0.028
 watered-0.025
ashing-0.023
dy-0.022
bugs-0.022
Token away
Token ID1497
Feature activation-2.66e+00

Pos logit contributions
mary+0.013
 watered+0.012
ashing+0.011
dy+0.010
uggets+0.010
Neg logit contributions
iest-0.014
hy-0.012
bars-0.012
mm-0.011
iness-0.010
Token,
Token ID11
Feature activation+3.90e-02

Pos logit contributions
iest+0.147
hy+0.125
bars+0.117
mm+0.111
iness+0.106
Neg logit contributions
mary-0.157
 watered-0.143
ashing-0.135
uggets-0.127
rig-0.126
Token shark
Token ID21027
Feature activation+4.39e-01

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
rig+0.002
uggets+0.002
Neg logit contributions
iest-0.002
hy-0.002
bars-0.002
mm-0.002
 course-0.002
Token!
Token ID0
Feature activation+6.07e-01

Pos logit contributions
mary+0.024
 watered+0.022
ashing+0.021
dy+0.020
uggets+0.020
Neg logit contributions
iest-0.025
hy-0.022
bars-0.021
mm-0.020
iness-0.018
Token Leave
Token ID17446
Feature activation-5.28e+00

Pos logit contributions
mary+0.033
ashing+0.030
dy+0.029
uggets+0.029
bugs+0.028
Neg logit contributions
iest-0.036
bars-0.029
hy-0.028
rob-0.027
robat-0.026
Token the
Token ID262
Feature activation-1.93e+00

Pos logit contributions
iest+0.291
 course+0.249
hy+0.247
mm+0.228
rob+0.221
Neg logit contributions
mary-0.301
 watered-0.270
ashing-0.269
rig-0.260
uggets-0.245
Token red
Token ID2266
Feature activation-9.73e-01

Pos logit contributions
iest+0.105
hy+0.082
bars+0.078
 helmet+0.076
 temptation+0.076
Neg logit contributions
mary-0.116
 watered-0.103
rig-0.099
bugs-0.096
ashing-0.096
Token fish
Token ID5916
Feature activation-2.74e-01

Pos logit contributions
iest+0.060
hy+0.052
bars+0.051
mm+0.047
iness+0.046
Neg logit contributions
mary-0.051
 watered-0.045
ashing-0.042
rig-0.040
dy-0.040
Token alone
Token ID3436
Feature activation-2.56e+00

Pos logit contributions
iest+0.015
hy+0.014
bars+0.013
mm+0.012
 course+0.011
Neg logit contributions
mary-0.015
 watered-0.014
ashing-0.013
uggets-0.012
dy-0.012
Token!"
Token ID2474
Feature activation-1.24e+00

Pos logit contributions
iest+0.147
hy+0.130
bars+0.125
mm+0.115
iness+0.109
Neg logit contributions
mary-0.141
 watered-0.127
ashing-0.119
dy-0.114
uggets-0.113
Token
Token ID198
Feature activation+9.33e-02

Pos logit contributions
mary+0.007
 watered+0.006
ashing+0.006
uggets+0.005
dy+0.005
Neg logit contributions
iest-0.010
hy-0.009
bars-0.009
mm-0.008
 course-0.008
Token"
Token ID1
Feature activation-2.92e-01

Pos logit contributions
mary+0.004
 watered+0.004
ashing+0.003
dy+0.003
uggets+0.003
Neg logit contributions
iest-0.006
hy-0.006
bars-0.006
mm-0.005
iness-0.005
TokenAr
Token ID3163
Feature activation-3.63e-01

Pos logit contributions
iest+0.017
bars+0.015
hy+0.015
mm+0.013
iness+0.013
Neg logit contributions
mary-0.015
 watered-0.015
dy-0.013
ashing-0.013
 printed-0.013
Tokenrr
Token ID21062
Feature activation+4.92e-01

Pos logit contributions
iest+0.024
bars+0.024
hy+0.023
bike+0.022
mm+0.021
Neg logit contributions
mary-0.012
ashing-0.011
uggets-0.011
bugs-0.010
 upon-0.010
Token!
Token ID0
Feature activation+5.44e-01

Pos logit contributions
mary+0.023
dy+0.020
 watered+0.020
ashing+0.019
bugs+0.018
Neg logit contributions
iest-0.031
bars-0.028
hy-0.028
mm-0.026
hetically-0.025
Token Leave
Token ID17446
Feature activation-5.26e+00

Pos logit contributions
mary+0.026
dy+0.023
 upon+0.023
ashing+0.023
uggets+0.023
Neg logit contributions
iest-0.033
bars-0.028
hy-0.027
iness-0.026
hetically-0.026
Token my
Token ID616
Feature activation-1.85e+00

Pos logit contributions
iest+0.325
hy+0.292
 course+0.269
bars+0.263
mm+0.261
Neg logit contributions
mary-0.268
 watered-0.238
ashing-0.232
rig-0.216
uggets-0.214
Token sister
Token ID6621
Feature activation-1.61e+00

Pos logit contributions
iest+0.106
hy+0.094
bars+0.090
mm+0.083
hetically+0.078
Neg logit contributions
mary-0.102
 watered-0.093
ashing-0.087
dy-0.084
uggets-0.082
Token alone
Token ID3436
Feature activation-2.64e+00

Pos logit contributions
iest+0.100
hy+0.089
bars+0.087
mm+0.082
hetically+0.078
Neg logit contributions
mary-0.078
 watered-0.071
ashing-0.066
dy-0.064
bugs-0.061
Token,
Token ID11
Feature activation-7.94e-01

Pos logit contributions
iest+0.148
hy+0.132
bars+0.125
mm+0.115
iness+0.109
Neg logit contributions
mary-0.149
 watered-0.134
ashing-0.127
dy-0.121
uggets-0.120
Token you
Token ID345
Feature activation-2.94e-01

Pos logit contributions
iest+0.047
hy+0.041
bars+0.040
mm+0.037
hetically+0.035
Neg logit contributions
mary-0.042
 watered-0.038
ashing-0.036
dy-0.035
uggets-0.033
Token You
Token ID921
Feature activation+8.05e-01

Pos logit contributions
mary+0.003
uggets+0.003
bugs+0.003
 raining+0.003
ashing+0.003
Neg logit contributions
iest-0.005
rob-0.004
hetically-0.003
iness-0.003
robat-0.003
Token are
Token ID389
Feature activation-1.14e+00

Pos logit contributions
mary+0.049
 watered+0.046
bugs+0.042
 qu+0.042
 prints+0.041
Neg logit contributions
iest-0.040
bars-0.034
hetically-0.032
mm-0.032
hy-0.032
Token bothering
Token ID41656
Feature activation+6.68e-02

Pos logit contributions
hy+0.060
iest+0.059
 yourself+0.051
 temptation+0.049
bars+0.048
Neg logit contributions
mary-0.064
ashing-0.057
 watered-0.056
rig-0.053
uggets-0.051
Token me
Token ID502
Feature activation+1.14e-01

Pos logit contributions
mary+0.003
 watered+0.003
ashing+0.003
dy+0.003
uggets+0.003
Neg logit contributions
iest-0.004
hy-0.004
bars-0.004
mm-0.003
hetically-0.003
Token.
Token ID13
Feature activation-1.86e-01

Pos logit contributions
mary+0.005
 watered+0.004
ashing+0.004
dy+0.004
bugs+0.004
Neg logit contributions
iest-0.008
hy-0.007
bars-0.007
mm-0.007
rob-0.007
Token Leave
Token ID17446
Feature activation-5.26e+00

Pos logit contributions
iest+0.011
hetically+0.009
iness+0.008
bars+0.008
rob+0.008
Neg logit contributions
mary-0.010
bugs-0.009
uggets-0.009
 raining-0.009
ashing-0.009
Token me
Token ID502
Feature activation-1.68e+00

Pos logit contributions
iest+0.328
hy+0.295
bars+0.284
mm+0.263
iness+0.250
Neg logit contributions
mary-0.263
 watered-0.235
ashing-0.220
dy-0.210
uggets-0.205
Token alone
Token ID3436
Feature activation-3.14e+00

Pos logit contributions
iest+0.102
bars+0.089
hy+0.088
mm+0.084
hetically+0.079
Neg logit contributions
mary-0.086
 watered-0.078
ashing-0.075
dy-0.070
bugs-0.069
Token,"
Token ID553
Feature activation-1.62e+00

Pos logit contributions
iest+0.200
hy+0.181
bars+0.174
mm+0.162
hetically+0.154
Neg logit contributions
mary-0.151
 watered-0.135
ashing-0.125
dy-0.120
uggets-0.117
Token he
Token ID339
Feature activation-1.90e+00

Pos logit contributions
iest+0.106
bars+0.084
iness+0.083
eness+0.082
hy+0.082
Neg logit contributions
mary-0.080
 watered-0.073
 to-0.068
 qu-0.067
bugs-0.067
Token says
Token ID1139
Feature activation-7.96e-01

Pos logit contributions
iest+0.087
hy+0.081
bars+0.075
mm+0.066
 course+0.064
Neg logit contributions
mary-0.120
 watered-0.110
ashing-0.109
uggets-0.108
dy-0.100
Token't
Token ID470
Feature activation+3.85e-02

Pos logit contributions
iest+0.039
hy+0.034
bars+0.031
mm+0.027
hetically+0.026
Neg logit contributions
mary-0.063
 watered-0.058
ashing-0.055
dy-0.053
rig-0.052
Token pick
Token ID2298
Feature activation-1.88e-01

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
dy+0.002
uggets+0.002
Neg logit contributions
iest-0.002
hy-0.002
bars-0.002
mm-0.002
hetically-0.002
Token too
Token ID1165
Feature activation+2.29e+00

Pos logit contributions
iest+0.012
hy+0.010
bars+0.010
mm+0.009
 course+0.009
Neg logit contributions
mary-0.009
 watered-0.009
ashing-0.008
rig-0.008
uggets-0.007
Token many
Token ID867
Feature activation-1.64e+00

Pos logit contributions
mary+0.106
 watered+0.095
ashing+0.089
dy+0.084
uggets+0.084
Neg logit contributions
iest-0.151
hy-0.135
bars-0.131
mm-0.121
 course-0.116
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
iest+0.102
hy+0.089
bars+0.087
mm+0.081
 course+0.077
Neg logit contributions
mary-0.084
 watered-0.075
ashing-0.072
dy-0.067
uggets-0.067
Token Leave
Token ID17446
Feature activation-5.26e+00

Pos logit contributions
mary+0.008
 watered+0.006
ashing+0.006
uggets+0.006
dy+0.006
Neg logit contributions
iest-0.009
hy-0.007
bars-0.007
iness-0.006
hetically-0.006
Token some
Token ID617
Feature activation-1.80e+00

Pos logit contributions
iest+0.293
hy+0.252
 course+0.250
mm+0.230
bars+0.223
Neg logit contributions
mary-0.285
ashing-0.268
 watered-0.258
rig-0.257
dy-0.241
Token for
Token ID329
Feature activation-1.66e-01

Pos logit contributions
iest+0.109
hy+0.094
bars+0.092
 course+0.083
mm+0.083
Neg logit contributions
mary-0.095
 watered-0.085
ashing-0.081
dy-0.078
rig-0.076
Token the
Token ID262
Feature activation-5.35e-01

Pos logit contributions
iest+0.010
hy+0.009
bars+0.009
mm+0.008
 course+0.008
Neg logit contributions
mary-0.008
 watered-0.007
ashing-0.007
dy-0.007
rig-0.006
Token birds
Token ID10087
Feature activation+6.34e-01

Pos logit contributions
iest+0.034
hy+0.030
bars+0.029
mm+0.027
 course+0.027
Neg logit contributions
mary-0.026
 watered-0.023
ashing-0.022
rig-0.021
uggets-0.020
Token and
Token ID290
Feature activation-2.11e-01

Pos logit contributions
mary+0.026
 watered+0.023
ashing+0.021
dy+0.020
rig+0.020
Neg logit contributions
iest-0.044
hy-0.040
bars-0.038
mm-0.035
iness-0.035
Token points
Token ID2173
Feature activation+1.01e+00

Pos logit contributions
iest+0.034
bars+0.031
hy+0.030
mm+0.027
hetically+0.027
Neg logit contributions
mary-0.029
 watered-0.026
dy-0.023
ashing-0.023
uggets-0.022
Token can
Token ID460
Feature activation-5.50e-02

Pos logit contributions
mary+0.048
 watered+0.042
ashing+0.039
dy+0.037
uggets+0.036
Neg logit contributions
iest-0.065
hy-0.060
bars-0.057
mm-0.054
hetically-0.052
Token hurt
Token ID5938
Feature activation-1.02e-01

Pos logit contributions
iest+0.003
hy+0.003
bars+0.003
mm+0.003
rob+0.002
Neg logit contributions
mary-0.003
 watered-0.003
ashing-0.003
dy-0.002
uggets-0.002
Token you
Token ID345
Feature activation-4.86e-01

Pos logit contributions
iest+0.006
hy+0.006
bars+0.005
mm+0.005
hetically+0.005
Neg logit contributions
mary-0.005
 watered-0.005
ashing-0.004
dy-0.004
uggets-0.004
Token.
Token ID13
Feature activation-3.05e-02

Pos logit contributions
iest+0.032
hy+0.029
bars+0.028
mm+0.026
iness+0.025
Neg logit contributions
mary-0.022
 watered-0.020
ashing-0.018
dy-0.018
uggets-0.017
Token Leave
Token ID17446
Feature activation-5.25e+00

Pos logit contributions
iest+0.002
bars+0.002
hy+0.002
rob+0.002
iness+0.001
Neg logit contributions
mary-0.002
 watered-0.001
uggets-0.001
ashing-0.001
bugs-0.001
Token the
Token ID262
Feature activation-1.93e+00

Pos logit contributions
iest+0.280
 course+0.232
hy+0.231
mm+0.211
 temptation+0.209
Neg logit contributions
mary-0.306
ashing-0.281
 watered-0.271
rig-0.271
uggets-0.254
Token c
Token ID269
Feature activation-1.36e-01

Pos logit contributions
iest+0.120
hy+0.108
bars+0.101
mm+0.095
 course+0.091
Neg logit contributions
mary-0.097
 watered-0.086
ashing-0.083
rig-0.078
dy-0.078
Tokenactus
Token ID34144
Feature activation+1.01e+00

Pos logit contributions
iest+0.007
hy+0.006
bars+0.006
mm+0.005
iness+0.005
Neg logit contributions
mary-0.008
 watered-0.008
dy-0.007
ashing-0.007
die-0.007
Token alone
Token ID3436
Feature activation-2.76e+00

Pos logit contributions
mary+0.056
 watered+0.051
ashing+0.048
dy+0.046
uggets+0.046
Neg logit contributions
iest-0.057
hy-0.050
bars-0.048
mm-0.044
iness-0.042
Token."
Token ID526
Feature activation-2.58e-01

Pos logit contributions
iest+0.171
hy+0.152
bars+0.146
mm+0.135
iness+0.131
Neg logit contributions
mary-0.139
 watered-0.123
ashing-0.116
dy-0.111
uggets-0.110
Token "
Token ID366
Feature activation+1.56e+00

Pos logit contributions
mary+0.041
 watered+0.036
ashing+0.034
rig+0.034
dy+0.033
Neg logit contributions
iest-0.072
hy-0.070
bars-0.067
mm-0.063
hetically-0.061
TokenStop
Token ID19485
Feature activation-2.06e+00

Pos logit contributions
mary+0.091
 watered+0.078
ashing+0.076
 upon+0.071
dy+0.070
Neg logit contributions
iest-0.090
hy-0.076
bars-0.072
iness-0.068
eness-0.065
Token,
Token ID11
Feature activation-9.74e-01

Pos logit contributions
iest+0.128
hy+0.114
bars+0.111
mm+0.102
hetically+0.098
Neg logit contributions
mary-0.104
 watered-0.092
ashing-0.087
dy-0.085
uggets-0.081
Token stop
Token ID2245
Feature activation-7.85e-01

Pos logit contributions
iest+0.067
bars+0.059
rob+0.056
hy+0.056
eness+0.055
Neg logit contributions
mary-0.039
 qu-0.033
 watered-0.033
 upon-0.032
ashing-0.032
Token.
Token ID13
Feature activation-3.62e-01

Pos logit contributions
iest+0.051
hy+0.046
bars+0.044
mm+0.041
hetically+0.039
Neg logit contributions
mary-0.038
 watered-0.033
ashing-0.031
dy-0.031
uggets-0.029
Token Leave
Token ID17446
Feature activation-5.25e+00

Pos logit contributions
iest+0.025
rob+0.019
iness+0.018
robat+0.018
bars+0.018
Neg logit contributions
mary-0.018
bugs-0.016
bug-0.015
uggets-0.015
 raining-0.015
Token me
Token ID502
Feature activation-1.58e+00

Pos logit contributions
iest+0.343
hy+0.310
bars+0.304
mm+0.277
hetically+0.271
Neg logit contributions
mary-0.248
 watered-0.217
ashing-0.199
dy-0.194
uggets-0.189
Token alone
Token ID3436
Feature activation-3.24e+00

Pos logit contributions
iest+0.104
bars+0.092
mm+0.091
hy+0.091
rob+0.084
Neg logit contributions
mary-0.070
 watered-0.063
ashing-0.063
 over-0.060
dy-0.058
Token.
Token ID13
Feature activation-5.32e-01

Pos logit contributions
iest+0.221
hy+0.201
bars+0.195
mm+0.182
hetically+0.174
Neg logit contributions
mary-0.143
 watered-0.126
ashing-0.117
dy-0.111
uggets-0.107
Token These
Token ID2312
Feature activation-6.05e-01

Pos logit contributions
iest+0.038
rob+0.029
iness+0.029
robat+0.028
hetically+0.028
Neg logit contributions
mary-0.024
bugs-0.021
 over-0.020
uggets-0.020
 raining-0.020
Token are
Token ID389
Feature activation-1.07e+00

Pos logit contributions
hetically+0.028
iest+0.026
bike+0.026
person+0.026
hy+0.025
Neg logit contributions
 prints-0.032
mary-0.030
 upon-0.030
 for-0.030
 watered-0.030
TokenGo
Token ID5247
Feature activation+2.41e-01

Pos logit contributions
mary+0.025
 watered+0.023
ashing+0.021
 qu+0.020
dy+0.020
Neg logit contributions
iest-0.029
bars-0.025
hy-0.025
iness-0.023
mm-0.022
Token away
Token ID1497
Feature activation-2.63e+00

Pos logit contributions
mary+0.012
 watered+0.011
ashing+0.010
dy+0.010
uggets+0.010
Neg logit contributions
iest-0.015
hy-0.013
bars-0.013
mm-0.012
iness-0.011
Token,
Token ID11
Feature activation+1.32e-01

Pos logit contributions
iest+0.146
hy+0.126
bars+0.117
mm+0.112
iness+0.105
Neg logit contributions
mary-0.152
 watered-0.140
ashing-0.131
uggets-0.124
dy-0.122
Token bear
Token ID6842
Feature activation+6.25e-01

Pos logit contributions
mary+0.006
dy+0.005
 upon+0.005
 qu+0.005
 watered+0.005
Neg logit contributions
iest-0.009
bars-0.008
hy-0.008
eness-0.007
rob-0.007
Token!
Token ID0
Feature activation+8.70e-01

Pos logit contributions
mary+0.031
 watered+0.028
ashing+0.026
dy+0.025
uggets+0.024
Neg logit contributions
iest-0.039
hy-0.035
bars-0.034
mm-0.031
hetically-0.030
Token Leave
Token ID17446
Feature activation-5.24e+00

Pos logit contributions
mary+0.046
ashing+0.041
bugs+0.040
dy+0.040
 raining+0.040
Neg logit contributions
iest-0.052
bars-0.041
hetically-0.038
rob-0.038
iness-0.038
Token my
Token ID616
Feature activation-1.84e+00

Pos logit contributions
iest+0.309
hy+0.275
 course+0.255
bars+0.249
mm+0.247
Neg logit contributions
mary-0.277
 watered-0.249
ashing-0.242
rig-0.227
uggets-0.223
Token children
Token ID1751
Feature activation-1.30e+00

Pos logit contributions
iest+0.112
hy+0.099
bars+0.093
mm+0.088
 elbow+0.084
Neg logit contributions
mary-0.096
 watered-0.086
ashing-0.082
dy-0.076
rig-0.076
Token alone
Token ID3436
Feature activation-2.71e+00

Pos logit contributions
iest+0.077
hy+0.069
bars+0.066
mm+0.061
iness+0.058
Neg logit contributions
mary-0.069
 watered-0.062
ashing-0.058
dy-0.056
uggets-0.055
Token!"
Token ID2474
Feature activation-3.75e-01

Pos logit contributions
iest+0.154
hy+0.134
bars+0.126
mm+0.116
iness+0.113
Neg logit contributions
mary-0.153
 watered-0.137
ashing-0.129
uggets-0.124
dy-0.122
Token
Token ID198
Feature activation-2.68e-01

Pos logit contributions
iest+0.031
hy+0.028
bars+0.027
mm+0.025
iness+0.025
Neg logit contributions
mary-0.012
 watered-0.010
ashing-0.008
dy-0.008
uggets-0.008
Token
Token ID198
Feature activation-9.69e-03

Pos logit contributions
iest+0.012
hy+0.010
bars+0.010
mm+0.009
iness+0.009
Neg logit contributions
mary-0.011
 watered-0.009
ashing-0.009
dy-0.009
 over-0.008
Token
Token ID198
Feature activation-5.29e-02

Pos logit contributions
iest+0.001
hy+0.001
bars+0.001
mm+0.001
 course+0.001
Neg logit contributions
mary-0.000
 watered-0.000
ashing-0.000
dy-0.000
uggets-0.000
Token"
Token ID1
Feature activation-4.73e-01

Pos logit contributions
iest+0.003
hy+0.003
bars+0.003
mm+0.003
iness+0.003
Neg logit contributions
mary-0.003
 watered-0.002
ashing-0.002
dy-0.002
rig-0.002
TokenSteven
Token ID28292
Feature activation-1.22e+00

Pos logit contributions
iest+0.029
hy+0.026
bars+0.025
mm+0.024
 elbow+0.022
Neg logit contributions
mary-0.023
 watered-0.022
die-0.019
dy-0.019
 upon-0.019
Token!
Token ID0
Feature activation-1.77e-01

Pos logit contributions
iest+0.070
hy+0.062
bars+0.060
mm+0.055
iness+0.052
Neg logit contributions
mary-0.067
 watered-0.060
ashing-0.056
dy-0.054
uggets-0.053
Token Leave
Token ID17446
Feature activation-5.24e+00

Pos logit contributions
iest+0.010
bars+0.008
hy+0.008
rob+0.008
iness+0.007
Neg logit contributions
mary-0.010
dy-0.009
uggets-0.009
ashing-0.009
bugs-0.008
Token the
Token ID262
Feature activation-2.00e+00

Pos logit contributions
iest+0.327
hy+0.297
bars+0.290
mm+0.266
hetically+0.255
Neg logit contributions
mary-0.257
 watered-0.232
ashing-0.214
dy-0.209
uggets-0.199
Token trophy
Token ID16383
Feature activation-1.56e+00

Pos logit contributions
iest+0.122
hy+0.110
bars+0.104
mm+0.097
iness+0.092
Neg logit contributions
mary-0.104
 watered-0.094
ashing-0.087
dy-0.083
uggets-0.083
Token and
Token ID290
Feature activation-7.45e-01

Pos logit contributions
iest+0.100
hy+0.092
bars+0.088
mm+0.085
rob+0.080
Neg logit contributions
mary-0.070
 watered-0.064
ashing-0.059
dy-0.057
bugs-0.054
Token come
Token ID1282
Feature activation+1.40e-01

Pos logit contributions
iest+0.043
hy+0.036
bars+0.034
mm+0.034
rob+0.033
Neg logit contributions
mary-0.038
 watered-0.038
 over-0.036
 upon-0.034
 to-0.034
Token to
Token ID284
Feature activation-5.41e-01

Pos logit contributions
mary+0.006
 watered+0.005
ashing+0.004
dy+0.004
rig+0.004
Neg logit contributions
iest-0.010
hy-0.009
bars-0.009
mm-0.008
ance-0.008
Token "
Token ID366
Feature activation+1.70e+00

Pos logit contributions
mary+0.034
 watered+0.028
ashing+0.026
rig+0.025
dy+0.025
Neg logit contributions
iest-0.074
hy-0.069
bars-0.066
mm-0.063
hetically-0.061
TokenNo
Token ID2949
Feature activation-2.40e+00

Pos logit contributions
mary+0.101
 watered+0.091
ashing+0.085
dy+0.085
 qu+0.083
Neg logit contributions
iest-0.091
bars-0.080
hy-0.079
iness-0.069
eness-0.066
Token,
Token ID11
Feature activation-1.30e-01

Pos logit contributions
iest+0.163
hy+0.154
bars+0.146
hing+0.132
hetically+0.131
Neg logit contributions
mary-0.101
dy-0.086
 watered-0.085
ashing-0.081
 raining-0.079
Token Ben
Token ID3932
Feature activation-5.61e-01

Pos logit contributions
iest+0.009
hy+0.009
bars+0.008
mm+0.008
rob+0.008
Neg logit contributions
mary-0.005
 watered-0.004
ashing-0.004
dy-0.004
bugs-0.004
Token.
Token ID13
Feature activation-1.09e-01

Pos logit contributions
iest+0.042
bars+0.039
hy+0.038
mm+0.035
hetically+0.035
Neg logit contributions
mary-0.021
 watered-0.017
dy-0.017
ashing-0.015
bugs-0.015
Token Leave
Token ID17446
Feature activation-5.23e+00

Pos logit contributions
iest+0.006
bars+0.005
hy+0.005
rob+0.004
iness+0.004
Neg logit contributions
mary-0.007
uggets-0.006
bugs-0.006
ashing-0.006
 watered-0.005
Token me
Token ID502
Feature activation-1.55e+00

Pos logit contributions
iest+0.306
 course+0.260
hy+0.249
mm+0.247
 temptation+0.238
Neg logit contributions
mary-0.286
 watered-0.254
ashing-0.251
rig-0.239
uggets-0.223
Token alone
Token ID3436
Feature activation-2.95e+00

Pos logit contributions
iest+0.094
hy+0.083
bars+0.081
mm+0.077
rob+0.073
Neg logit contributions
mary-0.079
 watered-0.071
ashing-0.070
dy-0.065
bugs-0.064
Token.
Token ID13
Feature activation-5.06e-01

Pos logit contributions
iest+0.196
hy+0.176
bars+0.170
mm+0.158
iness+0.152
Neg logit contributions
mary-0.137
 watered-0.121
ashing-0.112
dy-0.107
uggets-0.105
Token You
Token ID921
Feature activation+4.73e-01

Pos logit contributions
iest+0.032
bars+0.024
rob+0.023
iness+0.023
robat+0.022
Neg logit contributions
mary-0.027
uggets-0.024
bugs-0.023
ashing-0.023
bug-0.022
Token are
Token ID389
Feature activation-1.36e+00

Pos logit contributions
mary+0.032
 watered+0.029
ashing+0.028
dy+0.027
bugs+0.027
Neg logit contributions
iest-0.021
hy-0.018
bars-0.017
mm-0.016
hetically-0.014
Token,
Token ID11
Feature activation-7.88e-01

Pos logit contributions
iest+0.084
hy+0.075
bars+0.072
mm+0.066
iness+0.064
Neg logit contributions
mary-0.069
 watered-0.061
ashing-0.058
dy-0.054
uggets-0.054
Token Tom
Token ID4186
Feature activation-1.35e+00

Pos logit contributions
iest+0.046
hy+0.042
bars+0.040
mm+0.037
 course+0.035
Neg logit contributions
mary-0.042
 watered-0.038
ashing-0.036
dy-0.034
uggets-0.034
Token.
Token ID13
Feature activation+1.62e-01

Pos logit contributions
iest+0.090
hy+0.081
bars+0.079
mm+0.073
hetically+0.070
Neg logit contributions
mary-0.063
 watered-0.055
ashing-0.051
dy-0.050
bugs-0.047
Token You
Token ID921
Feature activation+6.23e-01

Pos logit contributions
mary+0.007
 over+0.006
bugs+0.006
 raining+0.006
uggets+0.006
Neg logit contributions
iest-0.012
iness-0.009
bars-0.009
rob-0.009
robat-0.009
Token are
Token ID389
Feature activation-1.37e+00

Pos logit contributions
mary+0.038
 watered+0.036
ashing+0.032
bugs+0.032
 printed+0.031
Neg logit contributions
iest-0.032
bars-0.027
hy-0.026
mm-0.024
hetically-0.024
Token no
Token ID645
Feature activation-5.22e+00

Pos logit contributions
hy+0.067
iest+0.065
 yourself+0.058
 brake+0.056
 course+0.053
Neg logit contributions
mary-0.084
ashing-0.077
 watered-0.072
rig-0.072
uggets-0.068
Token fun
Token ID1257
Feature activation-4.59e-01

Pos logit contributions
iest+0.392
hy+0.363
bars+0.358
hetically+0.340
mm+0.339
Neg logit contributions
mary-0.175
 watered-0.168
ashing-0.147
dy-0.141
 raining-0.135
Token."
Token ID526
Feature activation-4.58e-01

Pos logit contributions
iest+0.025
hy+0.021
bars+0.019
iness+0.018
eness+0.018
Neg logit contributions
mary-0.028
 watered-0.025
rig-0.023
ashing-0.023
dy-0.023
Token
Token ID198
Feature activation-3.01e-01

Pos logit contributions
iest+0.038
hy+0.034
bars+0.034
iness+0.031
eness+0.031
Neg logit contributions
mary-0.014
 watered-0.011
ashing-0.010
dy-0.009
uggets-0.009
Token
Token ID198
Feature activation-1.86e-01

Pos logit contributions
iest+0.022
hy+0.020
bars+0.020
mm+0.019
hetically+0.018
Neg logit contributions
mary-0.012
 watered-0.010
ashing-0.009
dy-0.008
uggets-0.008
TokenL
Token ID43
Feature activation+4.76e-02

Pos logit contributions
iest+0.011
hy+0.009
bars+0.009
iness+0.008
eness+0.008
Neg logit contributions
mary-0.010
 watered-0.009
ashing-0.009
dy-0.009
bugs-0.008
Token "
Token ID366
Feature activation+1.81e+00

Pos logit contributions
mary+0.064
 watered+0.058
ashing+0.053
uggets+0.053
rig+0.052
Neg logit contributions
hy-0.105
iest-0.104
bars-0.098
hetically-0.090
 click-0.090
TokenHey
Token ID10814
Feature activation+5.57e-02

Pos logit contributions
mary+0.116
 watered+0.105
ashing+0.103
dy+0.098
rig+0.096
Neg logit contributions
iest-0.089
hy-0.071
bars-0.068
iness-0.064
mm-0.063
Token,
Token ID11
Feature activation-2.96e-01

Pos logit contributions
mary+0.003
 watered+0.003
ashing+0.003
uggets+0.003
dy+0.003
Neg logit contributions
iest-0.003
hy-0.003
bars-0.003
mm-0.002
 course-0.002
Token dog
Token ID3290
Feature activation-8.50e-01

Pos logit contributions
iest+0.017
bars+0.015
hy+0.014
mm+0.013
eness+0.013
Neg logit contributions
mary-0.016
 watered-0.014
ashing-0.014
dy-0.013
 qu-0.013
Token!
Token ID0
Feature activation+6.96e-01

Pos logit contributions
iest+0.050
hy+0.045
bars+0.042
mm+0.039
 course+0.038
Neg logit contributions
mary-0.045
 watered-0.042
ashing-0.038
uggets-0.037
dy-0.036
Token Leave
Token ID17446
Feature activation-5.21e+00

Pos logit contributions
mary+0.039
ashing+0.034
dy+0.034
 over+0.033
bugs+0.033
Neg logit contributions
iest-0.041
iness-0.030
bars-0.030
eness-0.029
hy-0.028
Token my
Token ID616
Feature activation-1.94e+00

Pos logit contributions
iest+0.283
hy+0.256
 course+0.244
bars+0.225
mm+0.222
Neg logit contributions
mary-0.304
 watered-0.271
ashing-0.262
uggets-0.247
rig-0.247
Token brother
Token ID3956
Feature activation-1.70e+00

Pos logit contributions
iest+0.111
hy+0.099
bars+0.094
mm+0.087
iness+0.082
Neg logit contributions
mary-0.107
 watered-0.097
ashing-0.091
dy-0.087
uggets-0.086
Token's
Token ID338
Feature activation+2.81e-01

Pos logit contributions
iest+0.105
hy+0.094
bars+0.090
mm+0.084
hetically+0.080
Neg logit contributions
mary-0.085
 watered-0.076
ashing-0.072
dy-0.069
uggets-0.067
Token ball
Token ID2613
Feature activation-2.49e+00

Pos logit contributions
mary+0.015
 watered+0.014
ashing+0.013
dy+0.013
uggets+0.012
Neg logit contributions
iest-0.016
hy-0.014
bars-0.014
mm-0.013
iness-0.012
Token alone
Token ID3436
Feature activation-1.96e+00

Pos logit contributions
iest+0.159
hy+0.145
bars+0.138
 course+0.125
mm+0.124
Neg logit contributions
mary-0.122
 watered-0.107
ashing-0.098
uggets-0.095
dy-0.094
Token he
Token ID339
Feature activation+4.52e-01

Pos logit contributions
mary+0.009
 watered+0.008
dy+0.007
ashing+0.007
 over+0.007
Neg logit contributions
iest-0.008
hy-0.008
bars-0.007
mm-0.007
eness-0.006
Token was
Token ID373
Feature activation+8.18e-01

Pos logit contributions
mary+0.018
 watered+0.016
ashing+0.015
uggets+0.014
dy+0.014
Neg logit contributions
iest-0.033
hy-0.030
bars-0.029
mm-0.027
iness-0.026
Token caught
Token ID4978
Feature activation+1.36e+00

Pos logit contributions
mary+0.047
 watered+0.040
rig+0.038
ashing+0.038
dy+0.035
Neg logit contributions
iest-0.047
hy-0.044
 temptation-0.037
 yourself-0.036
bars-0.036
Token red
Token ID2266
Feature activation-1.17e+00

Pos logit contributions
mary+0.047
 watered+0.040
ashing+0.035
dy+0.034
uggets+0.032
Neg logit contributions
iest-0.105
hy-0.097
bars-0.095
mm-0.090
hetically-0.086
Token-
Token ID12
Feature activation+1.88e+00

Pos logit contributions
iest+0.090
hy+0.083
bars+0.081
mm+0.081
rob+0.077
Neg logit contributions
mary-0.039
 watered-0.031
ashing-0.028
dy-0.027
uggets-0.026
Tokenhanded
Token ID13638
Feature activation-5.19e+00

Pos logit contributions
mary+0.104
 watered+0.087
ashing+0.083
uggets+0.081
bugs+0.081
Neg logit contributions
iest-0.107
hy-0.095
bars-0.095
mm-0.091
 elbow-0.089
Token.
Token ID13
Feature activation-3.97e-01

Pos logit contributions
iest+0.349
hy+0.315
bars+0.304
mm+0.282
iness+0.272
Neg logit contributions
mary-0.235
 watered-0.207
ashing-0.191
dy-0.180
uggets-0.177
Token But
Token ID887
Feature activation-1.49e+00

Pos logit contributions
iest+0.021
hy+0.019
bars+0.018
mm+0.016
hetically+0.015
Neg logit contributions
mary-0.023
 watered-0.021
ashing-0.020
dy-0.019
uggets-0.019
Token he
Token ID339
Feature activation-8.63e-01

Pos logit contributions
iest+0.089
hy+0.080
bars+0.076
mm+0.070
hetically+0.067
Neg logit contributions
mary-0.078
 watered-0.071
ashing-0.067
dy-0.064
uggets-0.062
Token didn
Token ID1422
Feature activation+1.35e+00

Pos logit contributions
iest+0.044
hy+0.040
bars+0.035
 course+0.035
bike+0.034
Neg logit contributions
mary-0.049
uggets-0.045
ashing-0.044
rig-0.040
 watered-0.040
Token't
Token ID470
Feature activation+5.67e-02

Pos logit contributions
mary+0.083
 watered+0.073
 over+0.071
ashing+0.069
rig+0.069
Neg logit contributions
iest-0.067
hy-0.057
bars-0.054
iness-0.049
mm-0.048
Token's
Token ID338
Feature activation+1.35e+00

Pos logit contributions
iest+0.050
hy+0.047
bars+0.047
mm+0.044
iness+0.043
Neg logit contributions
mary-0.024
dy-0.021
 watered-0.020
die-0.017
 over-0.017
Token our
Token ID674
Feature activation-1.65e-01

Pos logit contributions
mary+0.084
 watered+0.077
ashing+0.076
uggets+0.069
bugs+0.068
Neg logit contributions
iest-0.066
hy-0.063
mm-0.054
bars-0.053
 course-0.053
Token snow
Token ID6729
Feature activation-3.17e-01

Pos logit contributions
iest+0.009
hy+0.008
bars+0.008
mm+0.007
hetically+0.007
Neg logit contributions
mary-0.009
 watered-0.008
ashing-0.008
dy-0.008
uggets-0.007
Tokenman
Token ID805
Feature activation+1.17e-01

Pos logit contributions
iest+0.020
hy+0.019
bars+0.018
mm+0.016
ance+0.016
Neg logit contributions
mary-0.015
 watered-0.013
dy-0.012
ashing-0.012
uggets-0.011
Token!
Token ID0
Feature activation+5.49e-01

Pos logit contributions
mary+0.005
 watered+0.005
dy+0.004
ashing+0.004
bugs+0.004
Neg logit contributions
iest-0.008
bars-0.007
hy-0.007
mm-0.006
hetically-0.006
Token Leave
Token ID17446
Feature activation-5.18e+00

Pos logit contributions
mary+0.027
dy+0.025
ashing+0.024
o+0.024
uggets+0.024
Neg logit contributions
iest-0.033
bars-0.026
iness-0.026
hetically-0.025
robat-0.025
Token him
Token ID683
Feature activation-2.62e+00

Pos logit contributions
iest+0.341
hy+0.307
bars+0.292
mm+0.276
 course+0.266
Neg logit contributions
mary-0.245
 watered-0.215
ashing-0.203
dy-0.190
uggets-0.187
Token alone
Token ID3436
Feature activation-3.11e+00

Pos logit contributions
iest+0.158
hy+0.141
bars+0.138
mm+0.130
eness+0.121
Neg logit contributions
mary-0.132
 watered-0.120
ashing-0.113
dy-0.110
bugs-0.103
Token!"
Token ID2474
Feature activation-1.20e+00

Pos logit contributions
iest+0.183
hy+0.163
bars+0.157
mm+0.145
hetically+0.137
Neg logit contributions
mary-0.166
 watered-0.149
ashing-0.140
dy-0.135
uggets-0.132
Token Anna
Token ID11735
Feature activation-1.52e-01

Pos logit contributions
iest+0.072
bars+0.061
hy+0.061
mm+0.056
iness+0.055
Neg logit contributions
mary-0.063
 watered-0.056
ashing-0.051
dy-0.051
bugs-0.051
Token says
Token ID1139
Feature activation-9.42e-01

Pos logit contributions
iest+0.007
hy+0.007
bars+0.006
mm+0.005
hetically+0.005
Neg logit contributions
mary-0.010
 watered-0.009
ashing-0.008
uggets-0.008
dy-0.008
Token Go
Token ID1514
Feature activation+1.09e-01

Pos logit contributions
iest+0.011
rob+0.009
bars+0.009
hy+0.009
iness+0.008
Neg logit contributions
mary-0.012
uggets-0.010
dy-0.010
bugs-0.010
 watered-0.010
Token away
Token ID1497
Feature activation-2.10e+00

Pos logit contributions
mary+0.005
 watered+0.005
ashing+0.005
dy+0.004
 over+0.004
Neg logit contributions
iest-0.007
hy-0.006
bars-0.006
mm-0.006
hetically-0.005
Token,
Token ID11
Feature activation+1.04e-01

Pos logit contributions
iest+0.124
hy+0.115
bars+0.110
mm+0.101
hetically+0.098
Neg logit contributions
mary-0.110
 watered-0.098
dy-0.091
ashing-0.091
uggets-0.086
Token Leo
Token ID19632
Feature activation+7.84e-01

Pos logit contributions
mary+0.006
 watered+0.006
ashing+0.006
uggets+0.005
dy+0.005
Neg logit contributions
iest-0.005
hy-0.005
bars-0.004
mm-0.004
 course-0.004
Token.
Token ID13
Feature activation+4.22e-02

Pos logit contributions
mary+0.035
 watered+0.031
dy+0.028
ashing+0.028
bugs+0.026
Neg logit contributions
iest-0.053
hy-0.048
bars-0.047
mm-0.044
hetically-0.042
Token Leave
Token ID17446
Feature activation-5.18e+00

Pos logit contributions
mary+0.002
uggets+0.002
dy+0.002
bugs+0.002
ashing+0.002
Neg logit contributions
iest-0.003
rob-0.002
bars-0.002
iness-0.002
robat-0.002
Token me
Token ID502
Feature activation-1.57e+00

Pos logit contributions
iest+0.307
hy+0.262
 course+0.246
mm+0.243
bars+0.241
Neg logit contributions
mary-0.281
 watered-0.247
ashing-0.246
rig-0.230
uggets-0.223
Token alone
Token ID3436
Feature activation-3.04e+00

Pos logit contributions
iest+0.096
hy+0.084
bars+0.084
mm+0.079
rob+0.076
Neg logit contributions
mary-0.079
 watered-0.072
ashing-0.068
dy-0.064
bugs-0.064
Token,"
Token ID553
Feature activation-1.54e+00

Pos logit contributions
iest+0.171
hy+0.154
bars+0.149
mm+0.139
hetically+0.130
Neg logit contributions
mary-0.166
 watered-0.152
ashing-0.142
dy-0.138
bugs-0.133
Token Mia
Token ID32189
Feature activation+3.73e-02

Pos logit contributions
iest+0.123
hy+0.113
bars+0.109
mm+0.105
 course+0.101
Neg logit contributions
mary-0.051
 watered-0.042
ashing-0.039
uggets-0.035
dy-0.034
Token says
Token ID1139
Feature activation-8.12e-01

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
dy+0.002
uggets+0.002
Neg logit contributions
iest-0.002
hy-0.002
bars-0.002
mm-0.002
iness-0.002
Token are
Token ID389
Feature activation-1.31e+00

Pos logit contributions
mary+0.036
 watered+0.034
ashing+0.031
dy+0.030
bugs+0.030
Neg logit contributions
iest-0.024
bars-0.021
hy-0.020
mm-0.018
hetically-0.017
Token not
Token ID407
Feature activation-6.48e-01

Pos logit contributions
hy+0.063
iest+0.061
 yourself+0.056
 course+0.053
 temptation+0.052
Neg logit contributions
mary-0.080
ashing-0.072
 watered-0.069
rig-0.068
ashed-0.062
Token welcome
Token ID7062
Feature activation-7.10e-01

Pos logit contributions
iest+0.034
hy+0.032
bars+0.026
 temptation+0.026
 yourself+0.026
Neg logit contributions
mary-0.039
 watered-0.033
ashing-0.032
rig-0.031
uggets-0.030
Token here
Token ID994
Feature activation-2.54e-01

Pos logit contributions
iest+0.044
hy+0.040
 goodness+0.033
 temptation+0.033
bars+0.033
Neg logit contributions
mary-0.036
 watered-0.034
rig-0.031
ashing-0.031
dy-0.029
Token.
Token ID13
Feature activation+3.16e-02

Pos logit contributions
iest+0.016
hy+0.014
bars+0.013
mm+0.012
iness+0.012
Neg logit contributions
mary-0.013
 watered-0.012
ashing-0.011
dy-0.010
uggets-0.010
Token Leave
Token ID17446
Feature activation-5.18e+00

Pos logit contributions
mary+0.002
uggets+0.001
bugs+0.001
ashing+0.001
dy+0.001
Neg logit contributions
iest-0.002
bars-0.002
hetically-0.002
iness-0.001
robat-0.001
Token the
Token ID262
Feature activation-1.91e+00

Pos logit contributions
iest+0.316
hy+0.282
bars+0.265
mm+0.254
 course+0.249
Neg logit contributions
mary-0.268
 watered-0.238
ashing-0.229
dy-0.215
uggets-0.213
Token seeds
Token ID11904
Feature activation-1.24e+00

Pos logit contributions
iest+0.095
hy+0.081
 course+0.073
 temptation+0.072
bars+0.072
Neg logit contributions
mary-0.120
uggets-0.106
ashing-0.105
 watered-0.104
rig-0.103
Token for
Token ID329
Feature activation+7.04e-01

Pos logit contributions
iest+0.080
hy+0.072
bars+0.069
mm+0.064
iness+0.062
Neg logit contributions
mary-0.058
 watered-0.051
ashing-0.048
dy-0.046
uggets-0.045
Token the
Token ID262
Feature activation+2.93e-01

Pos logit contributions
mary+0.035
 watered+0.032
ashing+0.030
dy+0.029
uggets+0.028
Neg logit contributions
iest-0.044
hy-0.039
bars-0.038
mm-0.035
iness-0.033
Token other
Token ID584
Feature activation-1.33e+00

Pos logit contributions
mary+0.018
 watered+0.015
ashing+0.015
uggets+0.015
rig+0.015
Neg logit contributions
iest-0.016
hy-0.014
bars-0.012
 temptation-0.012
 course-0.012
Token or
Token ID393
Feature activation-5.09e-01

Pos logit contributions
mary+0.033
 watered+0.030
ashing+0.030
dy+0.029
rig+0.029
Neg logit contributions
iest-0.024
hy-0.021
bars-0.021
 course-0.020
bike-0.018
Tokenchard
Token ID30215
Feature activation+9.67e-01

Pos logit contributions
iest+0.029
hy+0.028
bars+0.027
 elbow+0.024
 pedal+0.024
Neg logit contributions
mary-0.025
ashing-0.023
 watered-0.022
rig-0.021
dy-0.021
Token and
Token ID290
Feature activation+3.27e-01

Pos logit contributions
mary+0.046
 watered+0.039
ashing+0.038
rig+0.036
dy+0.035
Neg logit contributions
iest-0.060
hy-0.054
bars-0.053
bike-0.047
 helmet-0.047
Token fill
Token ID6070
Feature activation-8.97e-01

Pos logit contributions
mary+0.020
 watered+0.017
ashing+0.017
dy+0.017
uggets+0.016
Neg logit contributions
iest-0.016
hy-0.015
bars-0.014
mm-0.013
 course-0.012
Token his
Token ID465
Feature activation-3.71e+00

Pos logit contributions
iest+0.046
hy+0.038
bars+0.038
mm+0.036
 course+0.033
Neg logit contributions
mary-0.054
ashing-0.049
 watered-0.049
rig-0.046
bugs-0.044
Token wagon
Token ID31860
Feature activation-5.18e+00

Pos logit contributions
iest+0.191
hy+0.172
bars+0.162
mm+0.154
 elbow+0.145
Neg logit contributions
mary-0.220
 watered-0.194
ashing-0.191
rig-0.180
bugs-0.178
Token with
Token ID351
Feature activation-1.72e+00

Pos logit contributions
iest+0.365
hy+0.333
bars+0.327
mm+0.298
hetically+0.293
Neg logit contributions
mary-0.212
 watered-0.184
ashing-0.171
dy-0.160
uggets-0.154
Token juicy
Token ID35075
Feature activation+4.01e-01

Pos logit contributions
iest+0.119
hy+0.113
bars+0.106
rob+0.101
mm+0.100
Neg logit contributions
mary-0.071
 watered-0.070
 over-0.057
uggets-0.055
dy-0.055
Token red
Token ID2266
Feature activation-8.64e-01

Pos logit contributions
mary+0.022
 watered+0.020
ashing+0.019
dy+0.018
uggets+0.018
Neg logit contributions
iest-0.023
hy-0.020
bars-0.019
mm-0.018
iness-0.017
Token apples
Token ID22514
Feature activation-1.06e+00

Pos logit contributions
iest+0.054
hy+0.050
bars+0.046
mm+0.043
hetically+0.042
Neg logit contributions
mary-0.042
 watered-0.039
ashing-0.034
dy-0.034
uggets-0.033
Token.
Token ID13
Feature activation-4.76e-01

Pos logit contributions
iest+0.063
hy+0.055
bars+0.055
mm+0.048
hetically+0.047
Neg logit contributions
mary-0.055
 watered-0.050
ashing-0.047
rig-0.045
dy-0.045
Token and
Token ID290
Feature activation+9.64e-03

Pos logit contributions
mary+0.032
 watered+0.030
ashing+0.026
dy+0.026
 over+0.026
Neg logit contributions
iest-0.039
bars-0.035
hy-0.034
rob-0.032
mm-0.032
Token the
Token ID262
Feature activation-2.46e-01

Pos logit contributions
mary+0.001
 watered+0.000
dy+0.000
ashing+0.000
bugs+0.000
Neg logit contributions
iest-0.001
hy-0.001
bars-0.000
mm-0.000
iness-0.000
Token owl
Token ID39610
Feature activation+1.67e+00

Pos logit contributions
iest+0.015
hy+0.014
bars+0.013
mm+0.012
iness+0.012
Neg logit contributions
mary-0.012
 watered-0.011
ashing-0.010
dy-0.010
uggets-0.010
Token told
Token ID1297
Feature activation+1.51e+00

Pos logit contributions
mary+0.073
 watered+0.065
ashing+0.058
dy+0.056
bugs+0.054
Neg logit contributions
iest-0.114
hy-0.103
bars-0.101
mm-0.096
rob-0.090
Token him
Token ID683
Feature activation+1.59e+00

Pos logit contributions
mary+0.101
 watered+0.093
dy+0.086
ashing+0.086
uggets+0.084
Neg logit contributions
iest-0.069
hy-0.058
bars-0.057
mm-0.050
rob-0.046
Token:
Token ID25
Feature activation+4.85e+00

Pos logit contributions
mary+0.056
 watered+0.047
ashing+0.041
dy+0.041
bugs+0.038
Neg logit contributions
iest-0.122
hy-0.112
bars-0.110
mm-0.105
rob-0.103
Token "
Token ID366
Feature activation+1.27e+00

Pos logit contributions
mary+0.180
 watered+0.158
ashing+0.144
dy+0.131
uggets+0.129
Neg logit contributions
iest-0.347
hy-0.331
bars-0.319
mm-0.301
 course-0.293
TokenA
Token ID32
Feature activation+1.11e+00

Pos logit contributions
mary+0.072
 watered+0.067
ashing+0.062
dy+0.060
uggets+0.059
Neg logit contributions
iest-0.067
hy-0.063
bars-0.058
 elbow-0.053
mm-0.053
Token frog
Token ID21264
Feature activation+1.83e+00

Pos logit contributions
mary+0.058
 watered+0.052
ashing+0.048
dy+0.046
uggets+0.046
Neg logit contributions
iest-0.067
hy-0.060
bars-0.057
mm-0.053
iness-0.050
Token who
Token ID508
Feature activation-7.06e-01

Pos logit contributions
mary+0.092
 watered+0.082
ashing+0.076
dy+0.073
uggets+0.071
Neg logit contributions
iest-0.113
hy-0.102
bars-0.099
mm-0.092
hetically-0.087
Token never
Token ID1239
Feature activation-1.14e+00

Pos logit contributions
iest+0.043
hy+0.039
bars+0.038
mm+0.037
hetically+0.035
Neg logit contributions
mary-0.035
 watered-0.032
ashing-0.029
bugs-0.029
dy-0.028
Token.
Token ID13
Feature activation+3.56e-01

Pos logit contributions
iest+0.154
hy+0.146
bars+0.139
mm+0.136
 elbow+0.132
Neg logit contributions
mary-0.055
 watered-0.045
ashing-0.038
dy-0.036
 over-0.035
Token
Token ID198
Feature activation+4.77e-01

Pos logit contributions
mary+0.017
 watered+0.015
ashing+0.014
dy+0.013
uggets+0.013
Neg logit contributions
iest-0.023
hy-0.021
bars-0.020
mm-0.019
iness-0.018
Token
Token ID198
Feature activation+4.09e-01

Pos logit contributions
mary+0.021
 watered+0.018
ashing+0.018
uggets+0.016
dy+0.015
Neg logit contributions
iest-0.032
hy-0.030
bars-0.027
 course-0.027
mm-0.027
TokenThe
Token ID464
Feature activation-3.55e-01

Pos logit contributions
mary+0.026
 watered+0.024
ashing+0.024
uggets+0.022
dy+0.022
Neg logit contributions
iest-0.020
hy-0.017
bars-0.016
 course-0.015
mm-0.015
Token Moral
Token ID39020
Feature activation+2.46e+00

Pos logit contributions
iest+0.023
hy+0.021
bars+0.020
mm+0.018
 course+0.018
Neg logit contributions
mary-0.017
 watered-0.015
ashing-0.014
uggets-0.014
dy-0.013
Token:
Token ID25
Feature activation+6.29e+00

Pos logit contributions
mary+0.115
 watered+0.103
bugs+0.092
ashing+0.092
 over+0.089
Neg logit contributions
iest-0.151
hy-0.138
bars-0.137
hetically-0.131
 elbow-0.130
Token Always
Token ID16622
Feature activation+6.70e-01

Pos logit contributions
mary+0.347
 watered+0.312
ashing+0.294
dy+0.281
uggets+0.277
Neg logit contributions
iest-0.354
hy-0.317
bars-0.306
mm-0.282
 course-0.267
Token respect
Token ID2461
Feature activation-2.03e+00

Pos logit contributions
mary+0.033
 watered+0.032
dy+0.029
ashing+0.028
 over+0.027
Neg logit contributions
iest-0.042
hy-0.039
bars-0.038
rob-0.035
mm-0.034
Token other
Token ID584
Feature activation-2.59e+00

Pos logit contributions
iest+0.135
hy+0.122
bars+0.117
mm+0.110
iness+0.105
Neg logit contributions
mary-0.092
 watered-0.081
ashing-0.076
dy-0.072
uggets-0.070
Token creatures
Token ID8109
Feature activation+6.34e-01

Pos logit contributions
iest+0.148
hy+0.132
bars+0.126
mm+0.116
iness+0.110
Neg logit contributions
mary-0.142
 watered-0.128
ashing-0.121
dy-0.116
uggets-0.114
Token'
Token ID6
Feature activation+1.57e+00

Pos logit contributions
mary+0.024
 watered+0.021
ashing+0.019
dy+0.018
bugs+0.017
Neg logit contributions
iest-0.046
hy-0.043
bars-0.042
mm-0.040
rob-0.038
Token moral
Token ID6573
Feature activation+3.96e+00

Pos logit contributions
iest+0.014
hy+0.013
bars+0.012
 course+0.012
mm+0.012
Neg logit contributions
mary-0.011
 watered-0.010
ashing-0.009
uggets-0.009
bugs-0.009
Token of
Token ID286
Feature activation+3.15e+00

Pos logit contributions
mary+0.186
 watered+0.167
ashing+0.153
 over+0.151
 to+0.149
Neg logit contributions
iest-0.242
hetically-0.221
hy-0.218
bars-0.214
 elbow-0.211
Token the
Token ID262
Feature activation+2.58e+00

Pos logit contributions
mary+0.167
ashing+0.151
 watered+0.148
dy+0.135
rig+0.134
Neg logit contributions
iest-0.189
hy-0.167
 course-0.155
bars-0.154
mm-0.153
Token story
Token ID1621
Feature activation+4.29e+00

Pos logit contributions
mary+0.141
 watered+0.127
ashing+0.121
dy+0.115
uggets+0.114
Neg logit contributions
iest-0.150
hy-0.136
bars-0.127
mm-0.121
 course-0.115
Token is
Token ID318
Feature activation+3.10e+00

Pos logit contributions
mary+0.259
 watered+0.235
ashing+0.223
dy+0.215
uggets+0.213
Neg logit contributions
iest-0.225
hy-0.198
bars-0.188
mm-0.172
iness-0.162
Token:
Token ID25
Feature activation+4.71e+00

Pos logit contributions
mary+0.114
 watered+0.105
ashing+0.092
dy+0.087
die+0.086
Neg logit contributions
iest-0.221
hy-0.211
mm-0.195
bars-0.194
ance-0.191
Token Don
Token ID2094
Feature activation-1.80e+00

Pos logit contributions
mary+0.296
 watered+0.275
ashing+0.259
dy+0.250
rig+0.249
Neg logit contributions
iest-0.212
hy-0.198
bars-0.188
mm-0.176
 course-0.164
Token't
Token ID470
Feature activation+8.73e-01

Pos logit contributions
iest+0.065
hy+0.055
bars+0.051
mm+0.044
 course+0.042
Neg logit contributions
mary-0.136
 watered-0.128
ashing-0.124
uggets-0.120
dy-0.120
Token jump
Token ID4391
Feature activation+2.28e+00

Pos logit contributions
mary+0.050
 watered+0.045
ashing+0.042
dy+0.041
uggets+0.040
Neg logit contributions
iest-0.049
hy-0.043
bars-0.041
mm-0.038
hetically-0.036
Token to
Token ID284
Feature activation-4.13e-01

Pos logit contributions
mary+0.098
 watered+0.089
ashing+0.080
uggets+0.079
dy+0.076
Neg logit contributions
iest-0.156
hy-0.142
bars-0.134
iness-0.124
mm-0.123
Token conclusions
Token ID13242
Feature activation-2.50e+00

Pos logit contributions
iest+0.024
hy+0.022
bars+0.020
mm+0.019
 course+0.019
Neg logit contributions
mary-0.022
 watered-0.020
ashing-0.019
dy-0.018
uggets-0.018
Token them
Token ID606
Feature activation+1.40e+00

Pos logit contributions
mary+0.068
ashing+0.062
 watered+0.062
uggets+0.057
dy+0.054
Neg logit contributions
iest-0.069
hy-0.061
 course-0.059
mm-0.054
ance-0.054
Token a
Token ID257
Feature activation+2.51e+00

Pos logit contributions
mary+0.060
 watered+0.052
ashing+0.049
uggets+0.046
dy+0.046
Neg logit contributions
iest-0.097
hy-0.087
bars-0.084
mm-0.077
ance-0.076
Token very
Token ID845
Feature activation+2.87e+00

Pos logit contributions
mary+0.139
uggets+0.127
 watered+0.127
ashing+0.127
bugs+0.121
Neg logit contributions
iest-0.140
hy-0.118
 click-0.110
 pedal-0.106
 course-0.106
Token useful
Token ID4465
Feature activation+7.77e-01

Pos logit contributions
mary+0.154
bugs+0.143
 watered+0.143
uggets+0.137
ashing+0.131
Neg logit contributions
iest-0.165
hy-0.133
 temptation-0.131
mm-0.124
bars-0.120
Token lesson
Token ID11483
Feature activation+9.28e-01

Pos logit contributions
mary+0.043
 watered+0.039
ashing+0.037
dy+0.035
uggets+0.035
Neg logit contributions
iest-0.045
hy-0.039
bars-0.037
mm-0.034
 course-0.033
Token:
Token ID25
Feature activation+4.56e+00

Pos logit contributions
mary+0.045
 watered+0.040
ashing+0.038
dy+0.036
uggets+0.035
Neg logit contributions
iest-0.060
hy-0.053
bars-0.051
mm-0.047
iness-0.046
Token that
Token ID326
Feature activation+3.56e-01

Pos logit contributions
mary+0.246
 watered+0.220
ashing+0.210
dy+0.201
uggets+0.198
Neg logit contributions
iest-0.260
hy-0.234
bars-0.226
mm-0.210
 course-0.204
Token it
Token ID340
Feature activation+7.95e-01

Pos logit contributions
mary+0.019
 watered+0.017
ashing+0.016
dy+0.015
uggets+0.015
Neg logit contributions
iest-0.021
hy-0.019
bars-0.018
mm-0.017
 course-0.016
Token's
Token ID338
Feature activation+1.96e+00

Pos logit contributions
mary+0.040
uggets+0.035
ashing+0.035
 watered+0.035
rig+0.031
Neg logit contributions
iest-0.049
bars-0.041
hy-0.041
ance-0.037
 course-0.037
Token always
Token ID1464
Feature activation+1.40e+00

Pos logit contributions
mary+0.105
ashing+0.099
uggets+0.091
 watered+0.091
bugs+0.090
Neg logit contributions
iest-0.103
 yourself-0.086
 course-0.085
hy-0.084
 temptation-0.084
Token important
Token ID1593
Feature activation+1.66e+00

Pos logit contributions
mary+0.068
 watered+0.060
ashing+0.057
uggets+0.054
dy+0.053
Neg logit contributions
iest-0.089
hy-0.080
bars-0.077
mm-0.071
iness-0.068
Token It
Token ID632
Feature activation+1.42e-01

Pos logit contributions
mary+0.010
ashing+0.010
 watered+0.010
dy+0.009
rig+0.009
Neg logit contributions
iest-0.006
hy-0.006
bars-0.005
mm-0.005
 click-0.005
Token says
Token ID1139
Feature activation+9.50e-01

Pos logit contributions
ashing+0.010
mary+0.009
uggets+0.009
 watered+0.009
rig+0.008
Neg logit contributions
iest-0.006
hy-0.005
bars-0.005
mm-0.004
 course-0.004
Token:
Token ID25
Feature activation+4.72e+00

Pos logit contributions
mary+0.035
ashing+0.032
 watered+0.031
dy+0.028
rig+0.028
Neg logit contributions
iest-0.070
hy-0.065
mm-0.060
bars-0.060
 click-0.057
Token "
Token ID366
Feature activation+1.49e+00

Pos logit contributions
mary+0.184
ashing+0.174
 watered+0.173
rig+0.158
dy+0.148
Neg logit contributions
hy-0.309
iest-0.302
bars-0.281
mm-0.279
 click-0.266
TokenWarning
Token ID20361
Feature activation-1.42e+00

Pos logit contributions
mary+0.086
 watered+0.078
ashing+0.075
dy+0.072
uggets+0.070
Neg logit contributions
iest-0.081
hy-0.071
bars-0.068
mm-0.062
iness-0.058
Token:
Token ID25
Feature activation+4.74e+00

Pos logit contributions
iest+0.124
hy+0.115
bars+0.113
rob+0.108
hetically+0.107
Neg logit contributions
mary-0.034
 watered-0.025
 over-0.021
ashing-0.021
dy-0.020
Token Do
Token ID2141
Feature activation-9.95e-01

Pos logit contributions
mary+0.248
 watered+0.226
ashing+0.218
dy+0.205
uggets+0.198
Neg logit contributions
iest-0.273
hy-0.256
bars-0.241
mm-0.226
ance-0.210
Token not
Token ID407
Feature activation+6.61e-01

Pos logit contributions
iest+0.067
hy+0.064
mm+0.060
bars+0.060
 course+0.057
Neg logit contributions
mary-0.043
 watered-0.037
ashing-0.037
uggets-0.033
dy-0.033
Token touch
Token ID3638
Feature activation-1.27e+00

Pos logit contributions
mary+0.038
 watered+0.033
ashing+0.032
dy+0.030
uggets+0.030
Neg logit contributions
iest-0.037
hy-0.033
bars-0.031
mm-0.029
 course-0.027
Token.
Token ID13
Feature activation+2.02e-01

Pos logit contributions
iest+0.081
hy+0.075
bars+0.071
mm+0.067
hetically+0.066
Neg logit contributions
mary-0.060
 watered-0.052
dy-0.047
ashing-0.046
bugs-0.046
Token This
Token ID770
Feature activation-7.28e-01

Pos logit contributions
mary+0.011
 watered+0.010
uggets+0.009
bugs+0.009
 prints+0.009
Neg logit contributions
iest-0.012
hy-0.010
bars-0.010
rob-0.010
iness-0.009
Token much
Token ID881
Feature activation+5.43e-01

Pos logit contributions
mary+0.041
 watered+0.034
ashing+0.030
bugs+0.028
dy+0.028
Neg logit contributions
iest-0.090
bars-0.082
hy-0.082
hetically-0.081
 elbow-0.079
Token."
Token ID526
Feature activation-1.49e+00

Pos logit contributions
mary+0.021
 watered+0.019
ashing+0.017
uggets+0.016
dy+0.016
Neg logit contributions
iest-0.039
hy-0.036
bars-0.035
hetically-0.033
mm-0.032
Token Sara
Token ID24799
Feature activation-5.94e-01

Pos logit contributions
iest+0.107
hy+0.095
bars+0.093
eness+0.087
hetically+0.086
Neg logit contributions
mary-0.063
 watered-0.054
ashing-0.048
dy-0.047
bugs-0.046
Token says
Token ID1139
Feature activation-6.58e-01

Pos logit contributions
bars+0.018
hy+0.016
iest+0.016
 pedal+0.014
 click+0.013
Neg logit contributions
mary-0.043
uggets-0.042
ashing-0.041
 watered-0.039
ectar-0.037
Token,
Token ID11
Feature activation-4.10e-01

Pos logit contributions
iest+0.045
hy+0.041
bars+0.040
mm+0.037
iness+0.036
Neg logit contributions
mary-0.029
 watered-0.025
ashing-0.023
dy-0.022
uggets-0.022
Token proudly
Token ID23017
Feature activation+1.71e+00

Pos logit contributions
hy+0.020
iest+0.020
bars+0.019
 elbow+0.018
 click+0.018
Neg logit contributions
mary-0.022
ashing-0.020
rig-0.020
dy-0.019
uggets-0.019
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
mary+0.085
 watered+0.075
ashing+0.072
dy+0.069
rig+0.069
Neg logit contributions
iest-0.105
hy-0.097
bars-0.092
mm-0.084
hetically-0.081
Token
Token ID198
Feature activation-3.83e-02

Pos logit contributions
iest+0.007
hy+0.007
bars+0.007
mm+0.006
ance+0.006
Neg logit contributions
mary-0.008
 watered-0.008
ashing-0.007
dy-0.007
rig-0.007
Token
Token ID198
Feature activation-2.25e-02

Pos logit contributions
iest+0.003
hy+0.002
bars+0.002
mm+0.002
 course+0.002
Neg logit contributions
mary-0.002
 watered-0.001
ashing-0.001
uggets-0.001
dy-0.001
Token"
Token ID1
Feature activation-2.26e-01

Pos logit contributions
iest+0.002
hy+0.001
bars+0.001
iness+0.001
mm+0.001
Neg logit contributions
mary-0.001
 watered-0.001
ashing-0.001
dy-0.001
uggets-0.001
TokenWow
Token ID22017
Feature activation-1.72e+00

Pos logit contributions
iest+0.014
hy+0.012
bars+0.012
iness+0.011
eness+0.011
Neg logit contributions
mary-0.012
 watered-0.011
ashing-0.010
dy-0.009
uggets-0.009
Tokenummy
Token ID13513
Feature activation+1.57e+00

Pos logit contributions
iest+0.065
hy+0.060
bars+0.057
rob+0.051
bike+0.050
Neg logit contributions
mary-0.059
ashing-0.051
 watered-0.051
dy-0.048
uggets-0.048
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
mary+0.083
 watered+0.077
ashing+0.071
rig+0.069
dy+0.068
Neg logit contributions
iest-0.095
hy-0.079
bars-0.076
mm-0.075
iness-0.070
Token This
Token ID770
Feature activation-2.74e-01

Pos logit contributions
mary+0.008
uggets+0.007
 watered+0.007
bugs+0.007
ashing+0.006
Neg logit contributions
iest-0.008
bars-0.007
hy-0.006
rob-0.006
iness-0.006
Token is
Token ID318
Feature activation+4.09e-01

Pos logit contributions
iest+0.016
hy+0.014
bars+0.013
mm+0.013
 course+0.012
Neg logit contributions
mary-0.014
 watered-0.013
ashing-0.013
uggets-0.012
rig-0.012
Token
Token ID220
Feature activation-2.33e+00

Pos logit contributions
ashing+0.023
mary+0.022
 watered+0.021
rig+0.020
uggets+0.019
Neg logit contributions
iest-0.019
mm-0.019
hy-0.018
 course-0.017
 yourself-0.017
Tokenicky
Token ID17479
Feature activation+2.69e+00

Pos logit contributions
iest+0.152
bars+0.133
hy+0.130
mm+0.127
ance+0.117
Neg logit contributions
mary-0.107
 watered-0.106
ashing-0.088
dy-0.087
die-0.084
Token."
Token ID526
Feature activation-2.31e-01

Pos logit contributions
mary+0.138
 watered+0.124
ashing+0.119
uggets+0.112
rig+0.111
Neg logit contributions
iest-0.167
hy-0.141
bars-0.135
mm-0.130
iness-0.126
Token Ben
Token ID3932
Feature activation-1.21e+00

Pos logit contributions
iest+0.017
hy+0.015
bars+0.015
mm+0.014
hetically+0.013
Neg logit contributions
mary-0.009
 watered-0.008
ashing-0.007
dy-0.007
uggets-0.007
Token said
Token ID531
Feature activation+6.30e-01

Pos logit contributions
iest+0.060
hy+0.055
bars+0.050
mm+0.050
 course+0.049
Neg logit contributions
mary-0.069
ashing-0.063
uggets-0.062
 watered-0.060
rig-0.059
Token,
Token ID11
Feature activation+7.23e-01

Pos logit contributions
mary+0.022
 to+0.020
 watered+0.018
 over+0.018
 qu+0.017
Neg logit contributions
iest-0.046
rob-0.045
bars-0.044
hy-0.042
robat-0.042
Token "
Token ID366
Feature activation+1.44e+00

Pos logit contributions
mary+0.024
 watered+0.020
ashing+0.018
dy+0.017
rig+0.017
Neg logit contributions
iest-0.056
hy-0.053
bars-0.050
mm-0.048
hetically-0.047
Token had
Token ID550
Feature activation+2.63e+00

Pos logit contributions
mary+0.048
 watered+0.042
ashing+0.034
dy+0.034
bugs+0.032
Neg logit contributions
iest-0.113
hy-0.103
bars-0.101
mm-0.096
eness-0.093
Token never
Token ID1239
Feature activation-1.09e+00

Pos logit contributions
mary+0.145
ashing+0.126
 watered+0.126
rig+0.118
dy+0.118
Neg logit contributions
iest-0.148
hy-0.133
bars-0.125
mm-0.116
 course-0.111
Token gone
Token ID3750
Feature activation+2.06e+00

Pos logit contributions
iest+0.069
hy+0.062
bars+0.059
mm+0.054
 course+0.053
Neg logit contributions
mary-0.054
 watered-0.045
ashing-0.044
uggets-0.042
rig-0.042
Token on
Token ID319
Feature activation+7.82e-01

Pos logit contributions
mary+0.082
rig+0.066
 watered+0.066
ashing+0.066
dy+0.061
Neg logit contributions
iest-0.149
hy-0.134
bars-0.122
mm-0.118
ance-0.117
Token that
Token ID326
Feature activation+7.87e-01

Pos logit contributions
mary+0.038
 watered+0.034
ashing+0.033
dy+0.031
uggets+0.030
Neg logit contributions
iest-0.049
hy-0.044
bars-0.042
mm-0.040
hetically-0.038
Token adventurous
Token ID39770
Feature activation+1.29e+00

Pos logit contributions
mary+0.036
 watered+0.032
ashing+0.028
dy+0.028
 raining+0.027
Neg logit contributions
iest-0.052
hy-0.048
bars-0.048
mm-0.044
ance-0.043
Token hike
Token ID18390
Feature activation+8.65e-01

Pos logit contributions
mary+0.063
 watered+0.057
ashing+0.053
dy+0.051
bugs+0.049
Neg logit contributions
iest-0.080
hy-0.073
bars-0.071
mm-0.066
hetically-0.062
Token.
Token ID13
Feature activation-3.95e-02

Pos logit contributions
mary+0.033
 watered+0.028
ashing+0.025
dy+0.023
bugs+0.022
Neg logit contributions
iest-0.064
hy-0.059
bars-0.057
mm-0.054
eness-0.052
Token<|endoftext|>
Token ID50256
Feature activation+6.39e-01

Pos logit contributions
iest+0.002
hy+0.002
bars+0.002
mm+0.002
 course+0.002
Neg logit contributions
mary-0.002
 watered-0.002
ashing-0.002
uggets-0.002
dy-0.001
TokenOnce
Token ID7454
Feature activation-5.81e-01

Pos logit contributions
mary+0.031
 watered+0.028
ashing+0.027
dy+0.024
rig+0.024
Neg logit contributions
iest-0.040
hy-0.037
bars-0.033
he-0.033
mm-0.032
Token upon
Token ID2402
Feature activation+1.10e+00

Pos logit contributions
iest+0.049
bars+0.043
hy+0.043
iness+0.041
he+0.040
Neg logit contributions
mary-0.018
 watered-0.015
uggets-0.012
rig-0.012
ashing-0.011
Token to
Token ID284
Feature activation+1.11e+00

Pos logit contributions
mary+0.002
 watered+0.002
ashing+0.002
dy+0.002
uggets+0.002
Neg logit contributions
iest-0.005
hy-0.004
bars-0.004
mm-0.004
iness-0.004
Token help
Token ID1037
Feature activation-2.54e+00

Pos logit contributions
mary+0.057
 watered+0.052
 over+0.047
dy+0.047
 qu+0.046
Neg logit contributions
iest-0.070
bars-0.059
hy-0.057
mm-0.055
iness-0.053
Token -
Token ID532
Feature activation+2.53e+00

Pos logit contributions
iest+0.145
hy+0.129
bars+0.123
mm+0.114
iness+0.107
Neg logit contributions
mary-0.141
 watered-0.127
ashing-0.119
dy-0.115
uggets-0.113
Token so
Token ID523
Feature activation+2.32e-01

Pos logit contributions
mary+0.111
 watered+0.098
ashing+0.090
dy+0.086
uggets+0.083
Neg logit contributions
iest-0.173
hy-0.156
bars-0.150
mm-0.142
iness-0.136
Token the
Token ID262
Feature activation-9.81e-02

Pos logit contributions
mary+0.011
 watered+0.010
ashing+0.010
dy+0.009
uggets+0.009
Neg logit contributions
iest-0.015
hy-0.013
bars-0.013
mm-0.012
 course-0.011
Token turtle
Token ID28699
Feature activation+1.38e+00

Pos logit contributions
iest+0.006
hy+0.005
bars+0.005
mm+0.005
 course+0.004
Neg logit contributions
mary-0.005
 watered-0.005
ashing-0.004
uggets-0.004
dy-0.004
Token and
Token ID290
Feature activation+2.28e-01

Pos logit contributions
mary+0.059
 watered+0.052
ashing+0.047
dy+0.045
bugs+0.043
Neg logit contributions
iest-0.095
hy-0.086
bars-0.084
mm-0.080
hetically-0.075
Token all
Token ID477
Feature activation-4.84e-01

Pos logit contributions
mary+0.011
 watered+0.010
ashing+0.010
dy+0.009
uggets+0.009
Neg logit contributions
iest-0.014
hy-0.013
bars-0.012
mm-0.011
iness-0.011
Token the
Token ID262
Feature activation+1.63e-01

Pos logit contributions
iest+0.030
hy+0.027
bars+0.026
mm+0.026
rob+0.024
Neg logit contributions
mary-0.024
 watered-0.021
ashing-0.020
dy-0.019
bugs-0.019
Token animals
Token ID4695
Feature activation+1.16e+00

Pos logit contributions
mary+0.010
 watered+0.009
ashing+0.008
uggets+0.008
bugs+0.008
Neg logit contributions
iest-0.009
hy-0.008
bars-0.007
 course-0.007
 temptation-0.006
Token raced
Token ID32897
Feature activation+3.41e-01

Pos logit contributions
mary+0.053
 watered+0.048
ashing+0.044
dy+0.041
bugs+0.040
Neg logit contributions
iest-0.077
hy-0.069
bars-0.068
mm-0.065
rob-0.060
Token washed
Token ID18989
Feature activation+2.01e-01

Pos logit contributions
mary+0.032
ashing+0.027
uggets+0.026
 watered+0.026
dy+0.026
Neg logit contributions
iest-0.043
hy-0.038
bars-0.037
iness-0.034
 course-0.034
Token the
Token ID262
Feature activation-5.85e-01

Pos logit contributions
mary+0.009
 watered+0.008
ashing+0.008
dy+0.007
uggets+0.007
Neg logit contributions
iest-0.013
hy-0.012
bars-0.011
mm-0.011
eness-0.010
Token windows
Token ID9168
Feature activation-1.43e+00

Pos logit contributions
iest+0.034
hy+0.030
bars+0.028
 temptation+0.027
est+0.026
Neg logit contributions
mary-0.030
ashing-0.027
uggets-0.026
 watered-0.026
bugs-0.025
Token and
Token ID290
Feature activation+3.38e-01

Pos logit contributions
iest+0.118
hy+0.111
bars+0.106
mm+0.103
rob+0.101
Neg logit contributions
mary-0.042
 watered-0.034
ashing-0.030
dy-0.026
uggets-0.025
Token made
Token ID925
Feature activation-5.77e-01

Pos logit contributions
mary+0.015
 watered+0.013
ashing+0.012
dy+0.011
uggets+0.011
Neg logit contributions
iest-0.023
hy-0.021
bars-0.020
mm-0.019
iness-0.018
Token sure
Token ID1654
Feature activation+1.42e+00

Pos logit contributions
iest+0.036
hy+0.031
bars+0.030
mm+0.028
ance+0.027
Neg logit contributions
mary-0.029
ashing-0.025
 watered-0.024
dy-0.023
uggets-0.023
Token all
Token ID477
Feature activation+2.23e-01

Pos logit contributions
mary+0.061
 watered+0.051
ashing+0.049
dy+0.047
rig+0.046
Neg logit contributions
iest-0.100
hy-0.089
bars-0.089
mm-0.080
iness-0.079
Token of
Token ID286
Feature activation+6.66e-01

Pos logit contributions
mary+0.010
 watered+0.009
ashing+0.008
dy+0.007
bugs+0.007
Neg logit contributions
iest-0.015
hy-0.014
bars-0.014
mm-0.013
hetically-0.012
Token the
Token ID262
Feature activation+1.76e-01

Pos logit contributions
mary+0.029
 watered+0.025
ashing+0.024
dy+0.022
uggets+0.021
Neg logit contributions
iest-0.046
hy-0.041
bars-0.040
mm-0.038
 course-0.037
Token dirt
Token ID13647
Feature activation-8.51e-02

Pos logit contributions
mary+0.009
 watered+0.008
ashing+0.008
uggets+0.008
dy+0.008
Neg logit contributions
iest-0.010
hy-0.009
bars-0.009
mm-0.008
 temptation-0.008
Token was
Token ID373
Feature activation+1.08e+00

Pos logit contributions
iest+0.006
hy+0.006
bars+0.006
mm+0.005
rob+0.005
Neg logit contributions
mary-0.003
 watered-0.003
ashing-0.002
dy-0.002
 over-0.002
Token his
Token ID465
Feature activation-1.52e+00

Pos logit contributions
iest+0.026
hy+0.023
bars+0.022
mm+0.021
iness+0.020
Neg logit contributions
mary-0.015
 watered-0.014
dy-0.012
ashing-0.012
 raining-0.011
Token yellow
Token ID7872
Feature activation+1.07e+00

Pos logit contributions
iest+0.087
hy+0.074
bars+0.071
mm+0.069
iness+0.064
Neg logit contributions
mary-0.083
 watered-0.078
dy-0.071
ashing-0.071
rig-0.067
Token pants
Token ID12581
Feature activation-2.09e+00

Pos logit contributions
mary+0.061
 watered+0.056
dy+0.050
ashing+0.050
uggets+0.049
Neg logit contributions
iest-0.059
hy-0.052
bars-0.050
mm-0.047
hetically-0.045
Token so
Token ID523
Feature activation-3.95e-01

Pos logit contributions
iest+0.169
hy+0.153
 temptation+0.151
mm+0.150
 avail+0.146
Neg logit contributions
mary-0.057
 watered-0.047
 over-0.043
ashing-0.041
 to-0.041
Token they
Token ID484
Feature activation+7.27e-01

Pos logit contributions
iest+0.019
bars+0.016
hy+0.016
eness+0.016
hing+0.015
Neg logit contributions
mary-0.024
 watered-0.022
dy-0.020
ashing-0.020
 upon-0.019
Token could
Token ID714
Feature activation-1.51e+00

Pos logit contributions
mary+0.031
 watered+0.027
ashing+0.025
dy+0.023
bugs+0.022
Neg logit contributions
iest-0.051
hy-0.046
bars-0.044
mm-0.043
hetically-0.040
Token go
Token ID467
Feature activation-8.37e-01

Pos logit contributions
iest+0.098
hy+0.084
bars+0.080
mm+0.080
iness+0.078
Neg logit contributions
mary-0.074
 watered-0.067
 over-0.059
ashing-0.057
dy-0.057
Token to
Token ID284
Feature activation-6.31e-01

Pos logit contributions
iest+0.061
hy+0.056
bars+0.054
mm+0.049
rob+0.048
Neg logit contributions
mary-0.033
 watered-0.030
ashing-0.026
dy-0.025
uggets-0.024
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
iest+0.041
hy+0.037
bars+0.036
mm+0.033
iness+0.032
Neg logit contributions
mary-0.030
 watered-0.026
ashing-0.025
dy-0.023
uggets-0.023
Token park
Token ID3952
Feature activation-4.20e-01

Pos logit contributions
iest+0.062
hy+0.057
bars+0.053
 course+0.047
mm+0.047
Neg logit contributions
mary-0.064
 watered-0.059
ashing-0.056
uggets-0.053
dy-0.052
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
iest+0.029
hy+0.027
bars+0.026
mm+0.023
bike+0.023
Neg logit contributions
mary-0.018
 watered-0.016
ashing-0.014
dy-0.014
uggets-0.013
Token
Token ID198
Feature activation+4.13e-01

Pos logit contributions
mary+0.010
 watered+0.009
ashing+0.008
dy+0.008
uggets+0.008
Neg logit contributions
iest-0.011
hy-0.009
bars-0.009
iness-0.008
mm-0.008
Token
Token ID198
Feature activation+3.51e-01

Pos logit contributions
mary+0.019
 watered+0.017
ashing+0.016
uggets+0.015
dy+0.014
Neg logit contributions
iest-0.026
hy-0.025
bars-0.023
mm-0.022
 course-0.021
TokenBut
Token ID1537
Feature activation-1.27e+00

Pos logit contributions
mary+0.021
 watered+0.019
ashing+0.018
dy+0.017
uggets+0.017
Neg logit contributions
iest-0.019
hy-0.017
bars-0.016
mm-0.014
iness-0.014
Token Tom
Token ID4186
Feature activation-1.01e+00

Pos logit contributions
iest+0.067
hy+0.061
bars+0.057
mm+0.056
 course+0.053
Neg logit contributions
mary-0.077
 watered-0.068
ashing-0.066
rig-0.063
dy-0.062
Token does
Token ID857
Feature activation+2.09e-01

Pos logit contributions
iest+0.056
hy+0.050
bars+0.048
mm+0.044
 course+0.042
Neg logit contributions
mary-0.057
 watered-0.052
ashing-0.049
uggets-0.047
dy-0.046
Token not
Token ID407
Feature activation+3.80e-01

Pos logit contributions
mary+0.007
 watered+0.006
ashing+0.005
dy+0.005
uggets+0.005
Neg logit contributions
iest-0.016
hy-0.015
bars-0.014
mm-0.014
iness-0.013
Token care
Token ID1337
Feature activation-1.61e+00

Pos logit contributions
mary+0.021
 watered+0.020
ashing+0.019
dy+0.018
 over+0.018
Neg logit contributions
iest-0.021
bars-0.019
hy-0.018
mm-0.017
rob-0.017
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
iest+0.111
hy+0.101
bars+0.097
mm+0.091
hetically+0.087
Neg logit contributions
mary-0.069
 watered-0.061
ashing-0.056
dy-0.053
uggets-0.052
Token He
Token ID679
Feature activation-1.26e+00

Pos logit contributions
iest+0.009
hy+0.007
bars+0.007
rob+0.006
iness+0.006
Neg logit contributions
mary-0.012
 watered-0.011
ashing-0.011
dy-0.010
uggets-0.010
Token keeps
Token ID7622
Feature activation-2.22e+00

Pos logit contributions
iest+0.059
hy+0.055
bars+0.052
mm+0.047
 course+0.046
Neg logit contributions
mary-0.077
 watered-0.070
uggets-0.070
ashing-0.070
dy-0.064
Token running
Token ID2491
Feature activation+2.01e-01

Pos logit contributions
hy+0.109
iest+0.107
 elbow+0.100
bars+0.100
bike+0.095
Neg logit contributions
mary-0.131
rig-0.113
ashing-0.113
 watered-0.112
ocado-0.105
Token friends
Token ID2460
Feature activation-1.76e+00

Pos logit contributions
mary+0.031
ashing+0.026
 watered+0.026
rig+0.025
dy+0.024
Neg logit contributions
iest-0.038
hy-0.033
bars-0.030
 course-0.028
ance-0.028
Token again
Token ID757
Feature activation+5.83e-01

Pos logit contributions
iest+0.111
hy+0.100
bars+0.093
 course+0.088
eness+0.084
Neg logit contributions
mary-0.086
 watered-0.075
ashing-0.071
dy-0.069
rig-0.067
Token.
Token ID13
Feature activation+2.21e-01

Pos logit contributions
mary+0.034
ashing+0.029
rig+0.028
uggets+0.027
 watered+0.027
Neg logit contributions
iest-0.031
hy-0.025
 course-0.023
 yourself-0.023
mm-0.023
Token From
Token ID3574
Feature activation-3.09e-01

Pos logit contributions
 watered+0.013
mary+0.013
ashing+0.011
dy+0.011
uggets+0.011
Neg logit contributions
hy-0.010
bars-0.010
iest-0.010
mm-0.009
 course-0.009
Token then
Token ID788
Feature activation+1.90e+00

Pos logit contributions
iest+0.016
hy+0.014
bars+0.014
mm+0.013
 course+0.013
Neg logit contributions
mary-0.018
 watered-0.017
ashing-0.016
uggets-0.015
dy-0.015
Token on
Token ID319
Feature activation+6.49e-01

Pos logit contributions
mary+0.055
 watered+0.044
ashing+0.042
 over+0.041
dy+0.036
Neg logit contributions
iest-0.149
hy-0.143
bars-0.138
 elbow-0.129
mm-0.129
Token,
Token ID11
Feature activation+7.12e-01

Pos logit contributions
mary+0.033
 watered+0.029
ashing+0.026
dy+0.026
bugs+0.025
Neg logit contributions
iest-0.040
hy-0.037
bars-0.036
mm-0.032
eness-0.031
Token they
Token ID484
Feature activation+5.93e-01

Pos logit contributions
mary+0.034
 watered+0.031
ashing+0.030
dy+0.028
uggets+0.028
Neg logit contributions
iest-0.045
hy-0.040
bars-0.038
mm-0.036
 course-0.036
Token always
Token ID1464
Feature activation+1.70e+00

Pos logit contributions
mary+0.028
ashing+0.024
 watered+0.023
uggets+0.023
rig+0.023
Neg logit contributions
iest-0.038
hy-0.035
bars-0.033
 course-0.030
ance-0.030
Token found
Token ID1043
Feature activation+4.18e-01

Pos logit contributions
mary+0.060
 watered+0.060
dy+0.047
ashing+0.045
 printed+0.045
Neg logit contributions
iest-0.132
hy-0.119
bars-0.118
mm-0.114
hetically-0.107
Token creative
Token ID7325
Feature activation+7.94e-02

Pos logit contributions
mary+0.019
 watered+0.017
ashing+0.016
dy+0.015
uggets+0.015
Neg logit contributions
iest-0.028
hy-0.025
bars-0.024
mm-0.022
 course-0.022
Token He
Token ID679
Feature activation-1.11e+00

Pos logit contributions
iest+0.008
hy+0.006
bars+0.006
rob+0.005
mm+0.005
Neg logit contributions
mary-0.010
 watered-0.010
ashing-0.009
dy-0.009
uggets-0.009
Token reaches
Token ID12229
Feature activation+1.27e-01

Pos logit contributions
iest+0.058
hy+0.053
bars+0.050
mm+0.045
 course+0.043
Neg logit contributions
mary-0.065
 watered-0.059
ashing-0.056
uggets-0.055
dy-0.054
Token the
Token ID262
Feature activation-1.10e-01

Pos logit contributions
mary+0.006
 watered+0.005
ashing+0.005
dy+0.005
uggets+0.005
Neg logit contributions
iest-0.008
hy-0.007
bars-0.007
 elbow-0.006
mm-0.006
Token top
Token ID1353
Feature activation-1.07e+00

Pos logit contributions
iest+0.006
hy+0.005
bars+0.005
mm+0.005
iness+0.004
Neg logit contributions
mary-0.006
 watered-0.006
ashing-0.005
dy-0.005
rig-0.005
Token and
Token ID290
Feature activation+3.10e-01

Pos logit contributions
iest+0.066
hy+0.060
bars+0.056
mm+0.054
eness+0.051
Neg logit contributions
mary-0.053
 watered-0.047
ashing-0.044
dy-0.042
rig-0.041
Token looks
Token ID3073
Feature activation+7.43e-01

Pos logit contributions
mary+0.017
 watered+0.015
ashing+0.014
dy+0.013
bugs+0.013
Neg logit contributions
iest-0.019
hy-0.016
bars-0.015
mm-0.015
iness-0.014
Token around
Token ID1088
Feature activation+5.44e-01

Pos logit contributions
mary+0.034
uggets+0.028
 watered+0.028
bugs+0.025
dy+0.025
Neg logit contributions
iest-0.049
hy-0.043
bars-0.042
 temptation-0.039
 helmet-0.039
Token.
Token ID13
Feature activation-2.87e-01

Pos logit contributions
mary+0.027
 watered+0.024
ashing+0.023
dy+0.022
rig+0.021
Neg logit contributions
iest-0.034
hy-0.031
bars-0.029
mm-0.027
 course-0.026
Token He
Token ID679
Feature activation-1.34e+00

Pos logit contributions
iest+0.012
hy+0.011
bars+0.010
mm+0.009
iness+0.008
Neg logit contributions
mary-0.020
 watered-0.018
ashing-0.018
dy-0.017
uggets-0.017
Token sees
Token ID7224
Feature activation-4.25e-02

Pos logit contributions
iest+0.073
hy+0.067
bars+0.065
mm+0.058
 elbow+0.056
Neg logit contributions
mary-0.075
 watered-0.067
ashing-0.065
uggets-0.064
dy-0.061
Token the
Token ID262
Feature activation-3.77e-01

Pos logit contributions
iest+0.003
hy+0.003
bars+0.003
mm+0.003
eness+0.002
Neg logit contributions
mary-0.002
 watered-0.002
dy-0.001
 over-0.001
bugs-0.001
Token boat
Token ID8848
Feature activation-2.32e+00

Pos logit contributions
iest+0.080
hy+0.068
bars+0.066
 elbow+0.059
mm+0.059
Neg logit contributions
mary-0.089
 watered-0.078
ashing-0.077
rig-0.073
dy-0.072
Token on
Token ID319
Feature activation-3.25e-01

Pos logit contributions
iest+0.146
hy+0.136
bars+0.128
 helmet+0.122
hetically+0.119
Neg logit contributions
mary-0.101
rig-0.088
ashing-0.087
uggets-0.083
die-0.082
Token the
Token ID262
Feature activation+1.17e-01

Pos logit contributions
iest+0.015
hy+0.015
 course+0.014
bars+0.013
 pedal+0.012
Neg logit contributions
ashing-0.018
mary-0.018
 watered-0.016
rig-0.016
dy-0.016
Token water
Token ID1660
Feature activation+3.08e-02

Pos logit contributions
mary+0.007
 watered+0.006
ashing+0.006
dy+0.005
uggets+0.005
Neg logit contributions
iest-0.007
hy-0.006
bars-0.006
mm-0.005
hetically-0.005
Token and
Token ID290
Feature activation+7.01e-02

Pos logit contributions
mary+0.001
 watered+0.001
ashing+0.001
dy+0.001
uggets+0.001
Neg logit contributions
iest-0.002
hy-0.002
bars-0.002
 course-0.002
iness-0.002
Token pushed
Token ID7121
Feature activation-6.93e-01

Pos logit contributions
mary+0.003
ashing+0.003
rig+0.003
uggets+0.003
dy+0.003
Neg logit contributions
iest-0.004
hy-0.004
bars-0.004
 elbow-0.003
mm-0.003
Token it
Token ID340
Feature activation+6.69e-01

Pos logit contributions
iest+0.034
hy+0.029
bars+0.028
 temptation+0.026
 course+0.026
Neg logit contributions
mary-0.041
ashing-0.038
rig-0.037
 watered-0.037
uggets-0.034
Token with
Token ID351
Feature activation-7.66e-02

Pos logit contributions
mary+0.028
uggets+0.025
die+0.024
 watered+0.024
ashing+0.023
Neg logit contributions
iest-0.042
hy-0.040
bars-0.038
 click-0.035
 brake-0.035
Token a
Token ID257
Feature activation+1.06e+00

Pos logit contributions
iest+0.006
hy+0.006
bars+0.006
mm+0.005
iness+0.005
Neg logit contributions
mary-0.003
 watered-0.002
ashing-0.002
dy-0.002
uggets-0.002
Token stick
Token ID4859
Feature activation-5.58e-01

Pos logit contributions
mary+0.059
 watered+0.054
ashing+0.051
uggets+0.050
bugs+0.048
Neg logit contributions
iest-0.059
hy-0.054
bars-0.048
 click-0.046
 brake-0.044
Token.
Token ID13
Feature activation-3.45e-02

Pos logit contributions
iest+0.034
hy+0.032
bars+0.030
iness+0.026
ance+0.026
Neg logit contributions
mary-0.027
 watered-0.024
dy-0.023
die-0.023
uggets-0.023
Token is
Token ID318
Feature activation+6.47e-01

Pos logit contributions
iest+0.024
hy+0.022
bars+0.021
mm+0.019
hetically+0.019
Neg logit contributions
mary-0.020
 watered-0.017
ashing-0.016
dy-0.016
uggets-0.015
Token a
Token ID257
Feature activation+2.33e-01

Pos logit contributions
mary+0.029
ashing+0.027
 watered+0.026
rig+0.025
dy+0.023
Neg logit contributions
iest-0.042
hy-0.037
mm-0.034
 course-0.033
bars-0.032
Token good
Token ID922
Feature activation-5.31e-01

Pos logit contributions
mary+0.013
ashing+0.012
 watered+0.012
uggets+0.011
bugs+0.011
Neg logit contributions
iest-0.013
hy-0.011
 course-0.010
mm-0.010
 helmet-0.009
Token baker
Token ID46412
Feature activation+1.26e+00

Pos logit contributions
iest+0.031
hy+0.027
bars+0.024
mm+0.024
est+0.023
Neg logit contributions
mary-0.029
 watered-0.026
ashing-0.024
bugs-0.024
rig-0.023
Token."
Token ID526
Feature activation-1.08e+00

Pos logit contributions
mary+0.064
 watered+0.057
ashing+0.054
dy+0.051
uggets+0.050
Neg logit contributions
iest-0.077
hy-0.069
bars-0.066
mm-0.062
iness-0.058
Token Tom
Token ID4186
Feature activation-2.10e+00

Pos logit contributions
iest+0.076
hy+0.064
bars+0.062
eness+0.061
iness+0.060
Neg logit contributions
mary-0.048
 watered-0.041
ashing-0.038
dy-0.036
bugs-0.036
Token compliments
Token ID42025
Feature activation-9.04e-01

Pos logit contributions
iest+0.072
bars+0.071
hy+0.068
 course+0.060
 pedal+0.056
Neg logit contributions
mary-0.146
ashing-0.139
uggets-0.137
 watered-0.134
ectar-0.124
Token.
Token ID13
Feature activation-3.06e-01

Pos logit contributions
iest+0.057
hy+0.051
bars+0.050
mm+0.049
 course+0.045
Neg logit contributions
mary-0.043
 watered-0.039
ashing-0.035
 over-0.034
dy-0.034
Token
Token ID198
Feature activation-1.26e-01

Pos logit contributions
iest+0.021
hy+0.019
bars+0.019
mm+0.017
iness+0.017
Neg logit contributions
mary-0.013
 watered-0.012
ashing-0.011
dy-0.010
uggets-0.010
Token
Token ID198
Feature activation-4.07e-02

Pos logit contributions
iest+0.009
hy+0.009
bars+0.008
mm+0.008
hetically+0.007
Neg logit contributions
mary-0.005
 watered-0.004
ashing-0.004
dy-0.004
uggets-0.003
TokenThey
Token ID2990
Feature activation-1.11e-01

Pos logit contributions
iest+0.003
hy+0.003
bars+0.003
iness+0.003
 elbow+0.003
Neg logit contributions
mary-0.002
 watered-0.001
dy-0.001
ashing-0.001
bugs-0.001
Token not
Token ID407
Feature activation+1.03e-01

Pos logit contributions
mary+0.009
 watered+0.008
ashing+0.007
dy+0.007
uggets+0.006
Neg logit contributions
iest-0.018
hy-0.017
bars-0.016
mm-0.015
 course-0.015
Token take
Token ID1011
Feature activation-1.84e+00

Pos logit contributions
mary+0.006
 watered+0.006
ashing+0.005
dy+0.005
uggets+0.005
Neg logit contributions
iest-0.005
hy-0.005
bars-0.005
iness-0.004
mm-0.004
Token care
Token ID1337
Feature activation-1.75e+00

Pos logit contributions
iest+0.113
hy+0.103
bars+0.097
mm+0.089
ance+0.087
Neg logit contributions
mary-0.092
 watered-0.084
ashing-0.078
rig-0.073
dy-0.073
Token of
Token ID286
Feature activation-3.37e-01

Pos logit contributions
iest+0.106
hy+0.098
bars+0.092
mm+0.088
rob+0.085
Neg logit contributions
mary-0.088
 watered-0.078
ashing-0.075
uggets-0.070
dy-0.070
Token their
Token ID511
Feature activation-7.48e-01

Pos logit contributions
iest+0.026
hy+0.024
bars+0.023
mm+0.022
hetically+0.021
Neg logit contributions
mary-0.012
 watered-0.010
ashing-0.009
dy-0.009
uggets-0.008
Token toys
Token ID14958
Feature activation-2.67e+00

Pos logit contributions
iest+0.045
hy+0.041
bars+0.039
mm+0.036
iness+0.034
Neg logit contributions
mary-0.039
 watered-0.034
ashing-0.032
dy-0.031
uggets-0.030
Token.
Token ID13
Feature activation-7.12e-01

Pos logit contributions
iest+0.190
hy+0.172
bars+0.166
mm+0.158
hetically+0.150
Neg logit contributions
mary-0.111
 watered-0.096
ashing-0.088
dy-0.083
uggets-0.080
Token They
Token ID1119
Feature activation-5.64e-01

Pos logit contributions
iest+0.041
bars+0.040
hy+0.039
mm+0.037
 ignition+0.033
Neg logit contributions
mary-0.036
 watered-0.035
ashing-0.030
dy-0.029
rig-0.028
Token break
Token ID2270
Feature activation-1.04e-01

Pos logit contributions
iest+0.035
bars+0.029
hy+0.029
mm+0.028
rob+0.027
Neg logit contributions
mary-0.030
 watered-0.027
ashing-0.024
dy-0.024
bugs-0.023
Token them
Token ID606
Feature activation-3.03e-01

Pos logit contributions
iest+0.007
bars+0.006
hy+0.006
eness+0.006
iness+0.005
Neg logit contributions
mary-0.005
 watered-0.004
ashing-0.004
rig-0.004
uggets-0.004
Token,
Token ID11
Feature activation-3.25e-01

Pos logit contributions
iest+0.022
hy+0.020
bars+0.020
mm+0.018
hetically+0.018
Neg logit contributions
mary-0.012
 watered-0.010
ashing-0.009
dy-0.009
uggets-0.009
Token top
Token ID1353
Feature activation-5.78e-01

Pos logit contributions
mary+0.027
 watered+0.024
ashing+0.024
dy+0.022
uggets+0.022
Neg logit contributions
iest-0.032
hy-0.028
bars-0.028
mm-0.026
 course-0.025
Token.
Token ID13
Feature activation+1.52e-01

Pos logit contributions
iest+0.036
hy+0.033
bars+0.031
mm+0.030
hetically+0.028
Neg logit contributions
mary-0.028
 watered-0.025
ashing-0.023
dy-0.022
uggets-0.022
Token
Token ID198
Feature activation-1.05e-01

Pos logit contributions
 watered+0.008
mary+0.008
ashing+0.007
dy+0.007
rig+0.006
Neg logit contributions
hy-0.008
bars-0.007
iest-0.007
mm-0.007
ner-0.006
Token
Token ID198
Feature activation-1.14e-01

Pos logit contributions
iest+0.005
bars+0.005
hy+0.005
mm+0.004
 course+0.004
Neg logit contributions
mary-0.006
 watered-0.005
ashing-0.005
uggets-0.005
bugs-0.005
Token"
Token ID1
Feature activation-3.10e-01

Pos logit contributions
iest+0.006
hy+0.005
bars+0.005
mm+0.005
 course+0.005
Neg logit contributions
mary-0.006
 watered-0.006
ashing-0.006
dy-0.005
uggets-0.005
TokenLook
Token ID8567
Feature activation-2.10e+00

Pos logit contributions
iest+0.017
hy+0.015
bars+0.014
mm+0.013
iness+0.013
Neg logit contributions
mary-0.018
 watered-0.016
ashing-0.015
dy-0.014
uggets-0.014
Token,
Token ID11
Feature activation+3.36e-02

Pos logit contributions
iest+0.101
hy+0.086
mm+0.085
bars+0.081
 goodness+0.078
Neg logit contributions
mary-0.135
 watered-0.124
ashing-0.116
rig-0.112
uggets-0.110
Token our
Token ID674
Feature activation-1.20e+00

Pos logit contributions
mary+0.002
 watered+0.001
ashing+0.001
dy+0.001
uggets+0.001
Neg logit contributions
iest-0.002
hy-0.002
bars-0.002
mm-0.002
hetically-0.002
Token tower
Token ID10580
Feature activation-2.44e-01

Pos logit contributions
iest+0.068
hy+0.060
bars+0.059
mm+0.054
 elbow+0.051
Neg logit contributions
mary-0.069
 watered-0.061
ashing-0.059
uggets-0.055
dy-0.054
Token is
Token ID318
Feature activation+2.81e-01

Pos logit contributions
iest+0.014
hy+0.012
bars+0.012
mm+0.011
hetically+0.010
Neg logit contributions
mary-0.013
 watered-0.012
ashing-0.011
dy-0.011
bugs-0.011
Token very
Token ID845
Feature activation+4.17e-01

Pos logit contributions
mary+0.015
ashing+0.013
 watered+0.013
uggets+0.012
rig+0.012
Neg logit contributions
iest-0.017
hy-0.016
bars-0.015
 click-0.014
mm-0.013
Token of
Token ID286
Feature activation-6.25e-01

Pos logit contributions
iest+0.083
hy+0.075
bars+0.072
mm+0.067
hetically+0.064
Neg logit contributions
mary-0.063
 watered-0.056
ashing-0.052
dy-0.050
uggets-0.049
Token your
Token ID534
Feature activation-1.34e+00

Pos logit contributions
iest+0.044
hy+0.040
bars+0.040
hetically+0.036
iness+0.036
Neg logit contributions
mary-0.025
 watered-0.024
 prints-0.019
uggets-0.019
dy-0.019
Token tasty
Token ID25103
Feature activation+3.55e-01

Pos logit contributions
iest+0.078
hy+0.071
bars+0.066
mm+0.063
 elbow+0.059
Neg logit contributions
mary-0.072
 watered-0.064
ashing-0.062
dy-0.058
uggets-0.057
Token banana
Token ID25996
Feature activation+8.97e-01

Pos logit contributions
mary+0.020
 watered+0.017
ashing+0.017
dy+0.016
rig+0.016
Neg logit contributions
iest-0.021
hy-0.018
bars-0.017
mm-0.016
 course-0.015
Token?"
Token ID1701
Feature activation-4.70e-02

Pos logit contributions
mary+0.051
 watered+0.046
ashing+0.044
dy+0.042
rig+0.041
Neg logit contributions
iest-0.051
hy-0.043
bars-0.041
mm-0.040
 course-0.037
Token
Token ID220
Feature activation-2.60e+00

Pos logit contributions
iest+0.003
hy+0.002
bars+0.002
 course+0.002
mm+0.002
Neg logit contributions
mary-0.002
 watered-0.002
ashing-0.002
uggets-0.002
dy-0.002
Token
Token ID198
Feature activation-4.63e-01

Pos logit contributions
iest+0.152
bars+0.136
hy+0.133
mm+0.127
he+0.122
Neg logit contributions
mary-0.132
 watered-0.124
ashing-0.111
uggets-0.104
bugs-0.101
Token
Token ID198
Feature activation-2.17e-01

Pos logit contributions
iest+0.028
hy+0.025
bars+0.024
 course+0.024
mm+0.024
Neg logit contributions
mary-0.023
 watered-0.020
ashing-0.019
uggets-0.018
dy-0.017
TokenJack
Token ID14295
Feature activation+3.20e-01

Pos logit contributions
iest+0.012
hy+0.010
bars+0.010
 course+0.009
mm+0.009
Neg logit contributions
mary-0.013
 watered-0.011
ashing-0.011
uggets-0.010
dy-0.010
Token smiled
Token ID13541
Feature activation+6.31e-01

Pos logit contributions
mary+0.019
ashing+0.017
uggets+0.017
 watered+0.017
 raining+0.016
Neg logit contributions
iest-0.016
hy-0.014
bars-0.013
hetically-0.012
 course-0.012
Token and
Token ID290
Feature activation-1.45e-01

Pos logit contributions
mary+0.025
 watered+0.020
ashing+0.019
uggets+0.018
bugs+0.018
Neg logit contributions
iest-0.046
hy-0.042
bars-0.040
mm-0.037
eness-0.037
Token my
Token ID616
Feature activation-1.92e+00

Pos logit contributions
iest+0.009
hy+0.008
 yourself+0.007
mm+0.007
bars+0.007
Neg logit contributions
mary-0.009
ashing-0.009
uggets-0.008
bugs-0.008
rig-0.008
Token home
Token ID1363
Feature activation-2.96e+00

Pos logit contributions
iest+0.133
hy+0.121
bars+0.116
mm+0.109
iness+0.104
Neg logit contributions
mary-0.084
 watered-0.072
ashing-0.068
dy-0.064
uggets-0.063
Token.
Token ID13
Feature activation-1.60e-01

Pos logit contributions
iest+0.209
hy+0.194
bars+0.187
mm+0.177
rob+0.176
Neg logit contributions
mary-0.119
 watered-0.104
ashing-0.092
dy-0.086
bugs-0.085
Token I
Token ID314
Feature activation-1.18e+00

Pos logit contributions
iest+0.009
bars+0.007
hy+0.007
iness+0.007
hetically+0.007
Neg logit contributions
mary-0.009
 watered-0.008
ashing-0.008
uggets-0.008
bugs-0.008
Token feel
Token ID1254
Feature activation-6.28e-02

Pos logit contributions
iest+0.062
hy+0.055
bars+0.051
mm+0.047
iness+0.044
Neg logit contributions
mary-0.070
 watered-0.063
ashing-0.061
dy-0.058
uggets-0.058
Token safe
Token ID3338
Feature activation-3.11e+00

Pos logit contributions
iest+0.004
bars+0.004
hy+0.004
hetically+0.004
mm+0.004
Neg logit contributions
mary-0.002
 watered-0.002
 over-0.002
ashing-0.002
dy-0.002
Token and
Token ID290
Feature activation-6.01e-01

Pos logit contributions
iest+0.219
hy+0.196
bars+0.189
mm+0.178
iness+0.172
Neg logit contributions
mary-0.131
 watered-0.112
ashing-0.106
dy-0.101
rig-0.098
Token cozy
Token ID37438
Feature activation-2.04e+00

Pos logit contributions
iest+0.044
bars+0.041
hy+0.040
rob+0.039
mm+0.037
Neg logit contributions
 watered-0.023
mary-0.022
ashing-0.017
 upon-0.017
 over-0.017
Token here
Token ID994
Feature activation-6.98e-01

Pos logit contributions
iest+0.140
hy+0.129
bars+0.126
mm+0.117
hetically+0.112
Neg logit contributions
mary-0.088
 watered-0.080
ashing-0.071
dy-0.067
uggets-0.067
Token.
Token ID13
Feature activation+1.86e-01

Pos logit contributions
iest+0.043
hy+0.038
bars+0.037
mm+0.034
iness+0.032
Neg logit contributions
mary-0.036
 watered-0.031
ashing-0.030
dy-0.029
uggets-0.028
Token Do
Token ID2141
Feature activation-1.27e+00

Pos logit contributions
mary+0.011
 watered+0.009
uggets+0.009
ashing+0.009
bugs+0.009
Neg logit contributions
iest-0.011
bars-0.008
hy-0.008
iness-0.008
hetically-0.008