TOP ACTIVATIONS
MAX = 8.285

, sauce , cheese and topp ings . She showed them
asks . Max bar ks and nods . He
the princess says . She pret ends to wear the hat
" O st ric hes do not like people
us ?" Spot bar ks . He wants to
sad ." Tom bar ks yes . He is
says . Max bar ks and nods . He
ags his tail . He bar ks . "
to Tim and Mia and bar ks . He grabs the
noisy and scary . He bar ks and grow ls and
of cheese and sauce and topp ings . The people who
dog watches them . He bar ks and cheers . He
l icks his lips and bar ks . He is happy
dog ." Max bar ks and w ags his
. The dog bar ks and runs away .
name ?" Tom bar ks and jumps . He
?" The dog bar ks . The dog is
afraid . Max bar ks at the van .
Spot is scared . He bar ks at the truck and
out and cry . Rex bar ks at them .

MIN ACTIVATIONS
MIN = -7.467

aded in the water delic ately with his fishing rod .
day . They worked delic ately and carefully and nothing broke
Yes , I am G ert ie ! â Mr
very special toy for L ott ie . It was a
to wait until d inn ert ime . Anna
little girl 's shoulders affection ately . Sarah smiled
uff led his hair affection ately . The
enjoy it until d inn ert ime .
so he stepped forward courage ously . When he
it went on the w ett est of adventures . After
! I am the fastest rusher !" <|endoftext|> Once there was
who could get the w ett est and who could make
work , carefully and delic ately repairing the butterfly 's wings
amazed by how good the mother kept it .
knowing that even the t ini est and darkest of gardens
to swim around the p ail . The fisherman was so
hopped back onto the windows ill . The pr une whispered
a little girl named G ert ie , stopped by to
que aky in its sharp tal ons .
the top of the anth ill . But the ant wouldn

INTERVAL 4.347 - 8.285
CONTAINS 0.173%

There were many people and clown s and animals . Anna
can 't . You are too little ." Tim was sad
a pen . He wrote something and put it in an
, for helping us ," their dad said to the nice
." The ice cream man gives them ice cream

INTERVAL 0.409 - 4.347
CONTAINS 36.064%

bug ," Lily said . " We like bugs and flowers
He loved playing with his toys and eating candy .
for it ." Mia says . They look around
John walked up to Jane and said ,
scan our tickets and our bodies . They will make sure

INTERVAL -3.529 - 0.409
CONTAINS 63.354%

would struggle to practice so he could be the best musician
said . " I love you too , Ben
to explore . One day she was playing in the backyard
listen . Tim my went outside and saw his
creative and draw beautiful pictures that he shared with the world

INTERVAL -7.467 - -3.529
CONTAINS 0.410%

The sun was setting again but it was okay . The
more than anything else she had ever carried .
have such a cool souven ir from their exciting adventure !
He lived a happy life but something was missing . He
who knew how disappointed Ted was . " We can try
Token,
Token ID11
Feature activation+3.87e-01

Pos logit contributions
 badges+0.060
ows+0.059
 tricks+0.057
 diapers+0.056
 names+0.056
Neg logit contributions
 least-0.035
Little-0.031
ime-0.029
illy-0.028
ately-0.026
Token sauce
Token ID10746
Feature activation+2.75e+00

Pos logit contributions
 badges+0.012
ows+0.012
 tricks+0.011
 names+0.011
 diapers+0.011
Neg logit contributions
 least-0.015
Little-0.014
ime-0.013
illy-0.013
ately-0.012
Token,
Token ID11
Feature activation+7.14e-01

Pos logit contributions
 badges+0.123
ows+0.121
 tricks+0.117
 names+0.116
 diapers+0.115
Neg logit contributions
 least-0.068
Little-0.060
ime-0.056
illy-0.053
Maria-0.049
Token cheese
Token ID9891
Feature activation+2.94e+00

Pos logit contributions
 badges+0.026
ows+0.025
 tricks+0.024
 names+0.024
 chips+0.024
Neg logit contributions
 least-0.024
Little-0.022
ime-0.022
illy-0.020
Maria-0.020
Token and
Token ID290
Feature activation+1.08e+00

Pos logit contributions
 badges+0.148
ows+0.142
 tricks+0.138
cuts+0.138
 diapers+0.138
Neg logit contributions
 least-0.053
Little-0.042
ime-0.040
illy-0.039
ill-0.035
Token topp
Token ID23126
Feature activation+8.18e+00

Pos logit contributions
ows+0.034
 badges+0.034
 tricks+0.032
orts+0.031
 names+0.031
Neg logit contributions
 least-0.041
Little-0.037
ime-0.035
illy-0.034
Maria-0.033
Tokenings
Token ID654
Feature activation+3.66e+00

Pos logit contributions
 badges+0.253
trained+0.230
 facts+0.221
 homework+0.217
cuts+0.215
Neg logit contributions
ime-0.289
ill-0.273
illy-0.266
oh-0.264
 least-0.259
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
 badges+0.152
ows+0.145
 tricks+0.145
 hides+0.144
cks+0.142
Neg logit contributions
 least-0.090
Little-0.085
illy-0.082
ime-0.079
 Little-0.078
Token She
Token ID1375
Feature activation+7.11e-01

Pos logit contributions
 badges+0.017
ows+0.016
 tricks+0.016
aches+0.016
cks+0.016
Neg logit contributions
 least-0.018
Little-0.017
 Little-0.016
illy-0.016
ime-0.016
Token showed
Token ID3751
Feature activation-1.10e+00

Pos logit contributions
 badges+0.027
ows+0.026
 tricks+0.025
 names+0.025
 diapers+0.025
Neg logit contributions
 least-0.023
Little-0.021
ime-0.020
illy-0.019
ately-0.018
Token them
Token ID606
Feature activation+2.77e+00

Pos logit contributions
 least+0.034
Little+0.032
illy+0.031
ime+0.030
 Little+0.030
Neg logit contributions
ows-0.041
 badges-0.041
 tricks-0.039
 gag-0.038
cks-0.038
Token asks
Token ID7893
Feature activation+1.90e+00

Pos logit contributions
 badges+0.035
ows+0.033
 diapers+0.031
 tricks+0.031
orts+0.030
Neg logit contributions
 least-0.048
Little-0.044
ime-0.042
illy-0.041
Maria-0.041
Token.
Token ID13
Feature activation+2.66e+00

Pos logit contributions
 badges+0.066
ows+0.065
 tricks+0.061
 names+0.061
 diapers+0.061
Neg logit contributions
 least-0.067
Little-0.061
ime-0.058
illy-0.055
Maria-0.053
Token
Token ID198
Feature activation+1.22e+00

Pos logit contributions
 badges+0.114
ows+0.112
 names+0.109
 tricks+0.107
 diapers+0.107
Neg logit contributions
 least-0.073
Little-0.061
ime-0.061
illy-0.057
ately-0.054
Token
Token ID198
Feature activation+1.10e+00

Pos logit contributions
 badges+0.046
ows+0.046
orts+0.046
 names+0.045
 tricks+0.044
Neg logit contributions
 least-0.039
ime-0.031
ately-0.031
illy-0.030
Little-0.030
TokenMax
Token ID11518
Feature activation+1.42e+00

Pos logit contributions
 badges+0.046
ows+0.045
 tricks+0.044
 names+0.043
 diapers+0.043
Neg logit contributions
 least-0.031
Little-0.027
ime-0.026
illy-0.025
ately-0.023
Token bar
Token ID2318
Feature activation+8.09e+00

Pos logit contributions
bones+0.044
 ours+0.043
 badges+0.043
aches+0.042
 diapers+0.042
Neg logit contributions
 least-0.052
Little-0.045
 Little-0.042
 mid-0.042
ill-0.041
Tokenks
Token ID591
Feature activation+4.78e+00

Pos logit contributions
 badges+0.156
 diapers+0.135
 tricks+0.130
 chips+0.128
ows+0.128
Neg logit contributions
 least-0.393
ime-0.372
ill-0.368
Little-0.358
ately-0.355
Token and
Token ID290
Feature activation+1.57e+00

Pos logit contributions
 badges+0.234
cuts+0.226
ows+0.224
aches+0.220
 diapers+0.219
Neg logit contributions
 least-0.080
Little-0.076
ime-0.072
ill-0.067
 mid-0.065
Token nods
Token ID34833
Feature activation+1.62e+00

Pos logit contributions
ages+0.058
ows+0.057
uries+0.052
aches+0.052
ves+0.051
Neg logit contributions
 least-0.052
 M-0.044
 mid-0.043
 Little-0.043
 tw-0.043
Token.
Token ID13
Feature activation+1.53e+00

Pos logit contributions
 badges+0.066
ows+0.064
 diapers+0.061
 tricks+0.061
 names+0.061
Neg logit contributions
 least-0.046
Little-0.042
ime-0.039
illy-0.038
Maria-0.036
Token He
Token ID679
Feature activation+2.04e+00

Pos logit contributions
 badges+0.058
ows+0.057
aches+0.055
cks+0.054
 tricks+0.054
Neg logit contributions
 least-0.045
Little-0.043
ime-0.039
 Little-0.039
Maria-0.037
Token the
Token ID262
Feature activation+2.78e+00

Pos logit contributions
ows+0.109
 badges+0.108
 tricks+0.101
 diapers+0.100
 names+0.100
Neg logit contributions
 least-0.090
Little-0.085
ime-0.078
illy-0.076
Maria-0.074
Token princess
Token ID21752
Feature activation+3.68e+00

Pos logit contributions
 badges+0.108
ows+0.107
 tricks+0.101
 diapers+0.100
 names+0.100
Neg logit contributions
 least-0.085
Little-0.076
ime-0.073
illy-0.069
ately-0.066
Token says
Token ID1139
Feature activation+1.97e+00

Pos logit contributions
 badges+0.138
ows+0.131
 diapers+0.129
 tricks+0.127
 names+0.125
Neg logit contributions
 least-0.118
Little-0.104
ime-0.102
illy-0.097
ately-0.093
Token.
Token ID13
Feature activation+3.66e+00

Pos logit contributions
 badges+0.080
ows+0.076
 diapers+0.074
 tricks+0.074
 names+0.073
Neg logit contributions
 least-0.057
Little-0.051
ime-0.049
illy-0.047
ately-0.045
Token She
Token ID1375
Feature activation+2.70e+00

Pos logit contributions
 badges+0.144
ows+0.142
 names+0.136
 tricks+0.135
 diapers+0.134
Neg logit contributions
 least-0.111
Little-0.098
ime-0.095
illy-0.090
ately-0.086
Token pret
Token ID2181
Feature activation+7.92e+00

Pos logit contributions
 badges+0.070
ows+0.068
 diapers+0.068
orts+0.066
bones+0.064
Neg logit contributions
 least-0.115
Little-0.101
ime-0.095
illy-0.094
ill-0.091
Tokenends
Token ID2412
Feature activation+4.99e+00

Pos logit contributions
 diapers+0.175
 preferences+0.173
 facts+0.166
 choices+0.164
bows+0.162
Neg logit contributions
 least-0.316
oh-0.315
Little-0.296
M-0.291
ately-0.291
Token to
Token ID284
Feature activation+1.41e+00

Pos logit contributions
 badges+0.236
ows+0.234
orts+0.222
cuts+0.221
 diapers+0.220
Neg logit contributions
 least-0.100
Little-0.081
ime-0.081
Maria-0.073
illy-0.071
Token wear
Token ID5806
Feature activation+1.48e+00

Pos logit contributions
ows+0.053
 badges+0.053
cuts+0.050
 diapers+0.049
orts+0.048
Neg logit contributions
 least-0.045
Little-0.037
ime-0.037
ill-0.035
 mid-0.033
Token the
Token ID262
Feature activation+7.29e-02

Pos logit contributions
 gag+0.059
ows+0.058
trained+0.058
orts+0.056
ashes+0.056
Neg logit contributions
 least-0.034
Little-0.032
 Little-0.030
 M-0.029
illy-0.028
Token hat
Token ID6877
Feature activation+1.54e+00

Pos logit contributions
ows+0.002
 badges+0.002
orts+0.002
cks+0.002
 diapers+0.002
Neg logit contributions
 least-0.003
Little-0.002
ime-0.002
illy-0.002
 3-0.002
Token
Token ID198
Feature activation+4.26e-01

Pos logit contributions
 badges+0.076
ows+0.076
 names+0.072
 diapers+0.072
 tricks+0.071
Neg logit contributions
 least-0.061
Little-0.053
ime-0.052
illy-0.049
ately-0.047
Token
Token ID198
Feature activation+4.88e-01

Pos logit contributions
ows+0.016
orts+0.015
 badges+0.015
 names+0.014
 tricks+0.014
Neg logit contributions
 least-0.015
ime-0.012
illy-0.011
bul-0.011
ately-0.011
Token"
Token ID1
Feature activation+1.20e+00

Pos logit contributions
 badges+0.020
ows+0.019
 tricks+0.019
 names+0.019
 diapers+0.018
Neg logit contributions
 least-0.014
Little-0.013
ime-0.012
illy-0.012
Maria-0.011
TokenO
Token ID46
Feature activation-1.18e-01

Pos logit contributions
 badges+0.048
ows+0.046
 tricks+0.045
 diapers+0.045
 names+0.045
Neg logit contributions
 least-0.036
Little-0.031
ime-0.031
illy-0.030
ately-0.028
Tokenst
Token ID301
Feature activation+3.63e-01

Pos logit contributions
 least+0.004
Little+0.004
ime+0.003
illy+0.003
ately+0.003
Neg logit contributions
 badges-0.004
 names-0.004
 tricks-0.004
 diapers-0.004
ows-0.004
Tokenric
Token ID1173
Feature activation+7.88e+00

Pos logit contributions
 badges+0.013
 diapers+0.012
 helmets+0.012
 facts+0.012
 tricks+0.012
Neg logit contributions
 least-0.012
ime-0.012
Little-0.010
ately-0.010
illy-0.010
Tokenhes
Token ID956
Feature activation+3.40e+00

Pos logit contributions
 badges+0.147
 diapers+0.121
 chips+0.110
 tricks+0.109
 names+0.109
Neg logit contributions
 least-0.401
ime-0.384
Little-0.383
illy-0.358
Maria-0.358
Token do
Token ID466
Feature activation+2.00e+00

Pos logit contributions
 badges+0.109
ows+0.103
 diapers+0.099
 tricks+0.099
 names+0.098
Neg logit contributions
 least-0.129
Little-0.118
ime-0.116
illy-0.110
ately-0.106
Token not
Token ID407
Feature activation+1.60e+00

Pos logit contributions
 badges+0.064
 diapers+0.058
ows+0.056
 gag+0.056
irms+0.056
Neg logit contributions
 least-0.079
Little-0.074
ime-0.067
oh-0.062
'-0.062
Token like
Token ID588
Feature activation+2.40e+00

Pos logit contributions
ows+0.055
 badges+0.054
 diapers+0.052
bes+0.051
orts+0.050
Neg logit contributions
 least-0.058
Little-0.053
ime-0.052
illy-0.046
ful-0.046
Token people
Token ID661
Feature activation-1.32e-01

Pos logit contributions
 badges+0.089
ows+0.087
 tricks+0.083
 names+0.082
 diapers+0.082
Neg logit contributions
 least-0.079
Little-0.072
ime-0.068
illy-0.066
ately-0.063
Token us
Token ID514
Feature activation+2.28e-01

Pos logit contributions
ows+0.075
 badges+0.071
bows+0.069
 names+0.068
 tricks+0.068
Neg logit contributions
 least-0.033
Little-0.029
ime-0.025
illy-0.024
 Little-0.021
Token?"
Token ID1701
Feature activation+2.33e+00

Pos logit contributions
 badges+0.008
ows+0.008
 tricks+0.008
 names+0.008
 diapers+0.008
Neg logit contributions
 least-0.007
Little-0.007
ime-0.006
illy-0.006
Maria-0.006
Token
Token ID198
Feature activation+7.93e-01

Pos logit contributions
 badges+0.118
ows+0.116
 tricks+0.112
 names+0.112
 diapers+0.112
Neg logit contributions
 least-0.043
Little-0.039
ime-0.034
illy-0.031
Maria-0.029
Token
Token ID198
Feature activation+7.33e-01

Pos logit contributions
ows+0.034
 badges+0.034
 tricks+0.033
 names+0.033
orts+0.033
Neg logit contributions
 least-0.021
Little-0.017
ime-0.017
illy-0.016
ately-0.016
TokenSpot
Token ID32565
Feature activation+3.19e+00

Pos logit contributions
 badges+0.032
ows+0.031
 tricks+0.030
 names+0.030
 diapers+0.030
Neg logit contributions
 least-0.019
Little-0.018
ime-0.016
illy-0.015
Maria-0.014
Token bar
Token ID2318
Feature activation+7.73e+00

Pos logit contributions
bones+0.112
ages+0.108
aches+0.106
 ours+0.105
 badges+0.105
Neg logit contributions
 least-0.101
 and-0.084
 again-0.084
 Bear-0.083
Little-0.081
Tokenks
Token ID591
Feature activation+4.60e+00

Pos logit contributions
 badges+0.175
 diapers+0.156
bes+0.155
 chips+0.150
 helmets+0.147
Neg logit contributions
 least-0.342
ill-0.335
ime-0.327
in-0.315
ately-0.309
Token.
Token ID13
Feature activation+1.54e+00

Pos logit contributions
 badges+0.213
ows+0.204
cuts+0.203
 diapers+0.198
bows+0.197
Neg logit contributions
 least-0.095
Little-0.091
ime-0.086
 mid-0.077
ill-0.077
Token He
Token ID679
Feature activation+2.09e+00

Pos logit contributions
aches+0.067
cks+0.066
 badges+0.066
ows+0.064
 facts+0.063
Neg logit contributions
Little-0.034
 Little-0.034
 least-0.033
 3-0.029
ime-0.028
Token wants
Token ID3382
Feature activation+1.12e+00

Pos logit contributions
ages+0.074
bones+0.070
 diapers+0.067
ows+0.067
ometers+0.066
Neg logit contributions
 least-0.071
 tw-0.056
andy-0.054
 knew-0.054
 and-0.053
Token to
Token ID284
Feature activation+6.66e-01

Pos logit contributions
ows+0.066
cks+0.061
cuts+0.059
bows+0.058
bes+0.058
Neg logit contributions
 least-0.015
 3-0.010
Little-0.009
B-0.009
 Peter-0.009
Token sad
Token ID6507
Feature activation+2.65e+00

Pos logit contributions
ows+0.094
 badges+0.093
cuts+0.087
orts+0.084
bes+0.084
Neg logit contributions
 least-0.075
ime-0.055
Little-0.054
 since-0.054
 3-0.053
Token."
Token ID526
Feature activation+3.22e+00

Pos logit contributions
 badges+0.102
ows+0.098
 diapers+0.090
orts+0.090
 labels+0.090
Neg logit contributions
 least-0.085
Little-0.074
ime-0.073
illy-0.068
ately-0.066
Token
Token ID198
Feature activation+9.64e-01

Pos logit contributions
 badges+0.154
ows+0.152
 tricks+0.147
 names+0.146
 diapers+0.145
Neg logit contributions
 least-0.071
Little-0.061
ime-0.057
illy-0.053
Maria-0.049
Token
Token ID198
Feature activation+8.11e-01

Pos logit contributions
 badges+0.042
ows+0.042
 tricks+0.040
orts+0.040
 names+0.040
Neg logit contributions
 least-0.026
Little-0.021
ime-0.020
illy-0.020
ately-0.019
TokenTom
Token ID13787
Feature activation+7.65e-01

Pos logit contributions
 badges+0.030
ows+0.029
 tricks+0.028
 names+0.028
 diapers+0.028
Neg logit contributions
 least-0.027
Little-0.024
ime-0.023
illy-0.022
Maria-0.021
Token bar
Token ID2318
Feature activation+7.73e+00

Pos logit contributions
 badges+0.027
 diapers+0.026
bones+0.026
 gag+0.025
 tricks+0.025
Neg logit contributions
 least-0.026
Little-0.022
ill-0.021
ime-0.020
illy-0.020
Tokenks
Token ID591
Feature activation+4.73e+00

Pos logit contributions
 badges+0.151
 diapers+0.132
ows+0.126
 tricks+0.125
 chips+0.123
Neg logit contributions
 least-0.381
ime-0.357
ill-0.347
Little-0.346
ately-0.342
Token yes
Token ID3763
Feature activation+1.46e+00

Pos logit contributions
 badges+0.235
ows+0.230
cuts+0.229
bows+0.225
aches+0.225
Neg logit contributions
 least-0.077
Little-0.069
ime-0.062
 again-0.062
 of-0.059
Token.
Token ID13
Feature activation+1.06e+00

Pos logit contributions
 badges+0.059
ows+0.057
 tricks+0.055
 names+0.055
 diapers+0.054
Neg logit contributions
 least-0.043
Little-0.039
ime-0.037
illy-0.035
ately-0.033
Token He
Token ID679
Feature activation+1.47e+00

Pos logit contributions
 badges+0.043
ows+0.042
aches+0.042
cks+0.040
 tricks+0.040
Neg logit contributions
 least-0.029
Little-0.026
 Little-0.025
ime-0.024
ill-0.024
Token is
Token ID318
Feature activation+7.06e-01

Pos logit contributions
 diapers+0.043
 gag+0.043
bones+0.042
ages+0.042
ows+0.041
Neg logit contributions
 least-0.060
Little-0.046
andy-0.044
 se-0.043
 knew-0.042
Token says
Token ID1139
Feature activation+1.73e+00

Pos logit contributions
 badges+0.039
ows+0.035
 tricks+0.034
 diapers+0.034
 helmets+0.032
Neg logit contributions
 least-0.077
Little-0.072
ime-0.069
illy-0.066
ill-0.065
Token.
Token ID13
Feature activation+2.12e+00

Pos logit contributions
ows+0.062
 badges+0.061
 tricks+0.058
 names+0.057
 diapers+0.057
Neg logit contributions
 least-0.059
Little-0.054
ime-0.051
illy-0.049
Maria-0.047
Token
Token ID198
Feature activation+6.73e-01

Pos logit contributions
 badges+0.082
ows+0.082
 names+0.081
 name+0.079
 diapers+0.079
Neg logit contributions
 least-0.067
ime-0.056
Little-0.055
illy-0.053
ately-0.051
Token
Token ID198
Feature activation+6.11e-01

Pos logit contributions
ows+0.026
 badges+0.025
orts+0.025
 names+0.025
 tricks+0.024
Neg logit contributions
 least-0.022
ime-0.017
ately-0.017
Little-0.017
illy-0.017
TokenMax
Token ID11518
Feature activation+1.08e+00

Pos logit contributions
 badges+0.024
ows+0.023
 diapers+0.022
 tricks+0.022
 names+0.022
Neg logit contributions
 least-0.019
ime-0.016
Little-0.015
illy-0.015
ately-0.015
Token bar
Token ID2318
Feature activation+7.71e+00

Pos logit contributions
 badges+0.032
bones+0.032
ows+0.031
 diapers+0.031
ages+0.030
Neg logit contributions
 least-0.043
Little-0.037
 mid-0.034
ill-0.033
 Little-0.033
Tokenks
Token ID591
Feature activation+4.57e+00

Pos logit contributions
 badges+0.140
ows+0.123
 diapers+0.122
 tricks+0.121
 helmets+0.113
Neg logit contributions
 least-0.388
ime-0.360
Little-0.356
ill-0.348
ately-0.344
Token and
Token ID290
Feature activation+1.31e+00

Pos logit contributions
 badges+0.230
cuts+0.220
ows+0.220
ages+0.214
 diapers+0.214
Neg logit contributions
 least-0.080
Little-0.070
ime-0.064
 mid-0.062
 again-0.060
Token nods
Token ID34833
Feature activation+1.36e+00

Pos logit contributions
ows+0.047
ages+0.047
uries+0.045
 badges+0.043
ves+0.043
Neg logit contributions
 least-0.046
Little-0.037
 mid-0.037
 Little-0.036
 M-0.036
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 badges+0.053
ows+0.052
 tricks+0.049
 diapers+0.049
 names+0.049
Neg logit contributions
 least-0.042
Little-0.038
ime-0.036
illy-0.035
ately-0.033
Token He
Token ID679
Feature activation+1.60e+00

Pos logit contributions
 badges+0.039
ows+0.038
 tricks+0.037
cks+0.036
aches+0.036
Neg logit contributions
 least-0.029
Little-0.028
 Little-0.026
ime-0.026
illy-0.025
Tokenags
Token ID3775
Feature activation+3.12e+00

Pos logit contributions
 badges+0.135
 diapers+0.129
 names+0.123
bows+0.122
 chips+0.121
Neg logit contributions
 least-0.217
ime-0.205
illy-0.197
Little-0.187
ill-0.181
Token his
Token ID465
Feature activation+4.39e+00

Pos logit contributions
 badges+0.124
ows+0.122
 names+0.115
 diapers+0.115
 tricks+0.114
Neg logit contributions
 least-0.092
Little-0.082
ime-0.079
Maria-0.075
illy-0.074
Token tail
Token ID7894
Feature activation+2.87e+00

Pos logit contributions
ows+0.126
 badges+0.126
cuts+0.117
 tricks+0.116
 facts+0.115
Neg logit contributions
 least-0.176
Little-0.157
ime-0.152
illy-0.144
 3-0.144
Token.
Token ID13
Feature activation+1.59e+00

Pos logit contributions
 badges+0.139
cuts+0.131
 diapers+0.130
ows+0.127
 chips+0.126
Neg logit contributions
 least-0.060
ime-0.045
ill-0.044
Little-0.044
 mid-0.040
Token He
Token ID679
Feature activation+2.02e+00

Pos logit contributions
 badges+0.059
ows+0.058
 tricks+0.056
aches+0.056
cks+0.055
Neg logit contributions
 least-0.049
Little-0.046
ime-0.042
 Little-0.042
illy-0.041
Token bar
Token ID2318
Feature activation+7.63e+00

Pos logit contributions
ages+0.067
 diapers+0.066
ows+0.064
bones+0.063
 choices+0.062
Neg logit contributions
 least-0.076
 knew-0.055
Little-0.054
 se-0.052
 and-0.052
Tokenks
Token ID591
Feature activation+4.48e+00

Pos logit contributions
 badges+0.153
 diapers+0.137
 chips+0.133
 helmets+0.129
 tricks+0.129
Neg logit contributions
 least-0.371
ill-0.341
ime-0.338
ately-0.327
Little-0.326
Token.
Token ID13
Feature activation+1.64e+00

Pos logit contributions
 badges+0.218
ows+0.214
cuts+0.213
bows+0.211
aches+0.211
Neg logit contributions
 least-0.070
Little-0.066
 of-0.064
 again-0.063
ime-0.061
Token
Token ID198
Feature activation+1.56e-01

Pos logit contributions
 badges+0.062
ows+0.061
 tricks+0.059
 diapers+0.058
 names+0.057
Neg logit contributions
 least-0.051
Little-0.047
ime-0.044
illy-0.042
Maria-0.041
Token
Token ID198
Feature activation+2.10e-01

Pos logit contributions
ows+0.007
 badges+0.007
 names+0.006
 tricks+0.006
orts+0.006
Neg logit contributions
 least-0.004
Little-0.004
ime-0.004
illy-0.003
ately-0.003
Token"
Token ID1
Feature activation+1.12e+00

Pos logit contributions
 badges+0.009
ows+0.009
 tricks+0.009
 names+0.009
 diapers+0.009
Neg logit contributions
 least-0.005
Little-0.005
ime-0.005
illy-0.004
Maria-0.004
Token to
Token ID284
Feature activation+1.40e+00

Pos logit contributions
 badges+0.056
ows+0.054
 names+0.052
 tricks+0.052
 diapers+0.052
Neg logit contributions
 least-0.033
Little-0.028
ime-0.026
illy-0.025
ately-0.024
Token Tim
Token ID5045
Feature activation-1.47e+00

Pos logit contributions
 badges+0.056
ows+0.055
 tricks+0.053
 names+0.053
 diapers+0.052
Neg logit contributions
 least-0.041
Little-0.037
ime-0.035
illy-0.033
ately-0.032
Token and
Token ID290
Feature activation+1.57e+00

Pos logit contributions
Little+0.037
 least+0.036
ime+0.034
Maria+0.033
illy+0.033
Neg logit contributions
ows-0.061
 badges-0.060
 tricks-0.057
 names-0.057
 homework-0.057
Token Mia
Token ID32189
Feature activation+1.05e+00

Pos logit contributions
ows+0.064
 facts+0.060
 badges+0.059
 names+0.058
bows+0.058
Neg logit contributions
 least-0.049
Little-0.036
 M-0.036
 Peter-0.035
 Little-0.034
Token and
Token ID290
Feature activation+2.42e+00

Pos logit contributions
 badges+0.042
ows+0.041
 tricks+0.040
 diapers+0.039
 names+0.039
Neg logit contributions
 least-0.031
Little-0.027
ime-0.026
illy-0.024
ately-0.023
Token bar
Token ID2318
Feature activation+7.61e+00

Pos logit contributions
ows+0.091
 badges+0.087
 diapers+0.083
orts+0.083
 tricks+0.082
Neg logit contributions
 least-0.083
Little-0.063
 Little-0.061
 M-0.060
 Peter-0.060
Tokenks
Token ID591
Feature activation+4.75e+00

Pos logit contributions
 badges+0.128
ows+0.111
 tricks+0.110
 diapers+0.108
 names+0.102
Neg logit contributions
 least-0.402
ime-0.370
Little-0.366
ately-0.361
illy-0.355
Token.
Token ID13
Feature activation+1.80e+00

Pos logit contributions
 badges+0.210
ows+0.204
cuts+0.201
 diapers+0.198
 preferences+0.197
Neg logit contributions
 least-0.103
Little-0.096
ime-0.090
 mid-0.083
ful-0.082
Token He
Token ID679
Feature activation+1.91e+00

Pos logit contributions
 badges+0.068
ows+0.067
 tricks+0.064
 diapers+0.063
 names+0.062
Neg logit contributions
 least-0.057
Little-0.053
ime-0.049
illy-0.047
Maria-0.046
Token grabs
Token ID22378
Feature activation+1.27e+00

Pos logit contributions
ages+0.068
 diapers+0.064
uggets+0.064
ows+0.064
ometers+0.061
Neg logit contributions
 least-0.070
 knew-0.048
 was-0.046
Little-0.046
 tw-0.046
Token the
Token ID262
Feature activation+4.11e-01

Pos logit contributions
ows+0.054
 badges+0.052
cuts+0.051
 tricks+0.051
 facts+0.050
Neg logit contributions
 least-0.034
Little-0.031
ime-0.027
 Little-0.027
illy-0.027
Token noisy
Token ID31210
Feature activation+1.64e+00

Pos logit contributions
cuts+0.036
ows+0.035
bows+0.035
 badges+0.034
 preferences+0.034
Neg logit contributions
 least-0.022
 nowhere-0.020
 3-0.018
 mid-0.018
ful-0.017
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
 badges+0.082
ows+0.080
 names+0.078
 tricks+0.077
 diapers+0.077
Neg logit contributions
 least-0.032
Little-0.025
ime-0.025
illy-0.022
ately-0.020
Token scary
Token ID14343
Feature activation+1.64e+00

Pos logit contributions
ows+0.040
 badges+0.040
bows+0.039
aches+0.038
 addresses+0.037
Neg logit contributions
 least-0.025
Little-0.021
 mid-0.020
 night-0.020
 Little-0.020
Token.
Token ID13
Feature activation+2.23e+00

Pos logit contributions
 badges+0.073
ows+0.069
orts+0.068
aches+0.067
cuts+0.067
Neg logit contributions
 least-0.039
ime-0.033
Little-0.031
ately-0.029
ful-0.027
Token He
Token ID679
Feature activation+2.24e+00

Pos logit contributions
 badges+0.081
ows+0.079
 tricks+0.076
 names+0.074
 diapers+0.073
Neg logit contributions
 least-0.074
Little-0.069
ime-0.065
illy-0.061
Maria-0.060
Token bar
Token ID2318
Feature activation+7.60e+00

Pos logit contributions
bows+0.069
ages+0.068
ows+0.067
 badges+0.067
 choices+0.065
Neg logit contributions
 least-0.084
 knew-0.064
 se-0.062
ime-0.061
 couldn-0.061
Tokenks
Token ID591
Feature activation+4.58e+00

Pos logit contributions
 badges+0.174
 diapers+0.152
 chips+0.148
bes+0.148
 helmets+0.144
Neg logit contributions
 least-0.349
ime-0.323
ill-0.313
ately-0.311
ful-0.301
Token and
Token ID290
Feature activation+1.69e+00

Pos logit contributions
 badges+0.230
ows+0.224
 diapers+0.219
 homework+0.217
bows+0.217
Neg logit contributions
 least-0.074
Little-0.068
ime-0.061
Maria-0.049
 mid-0.049
Token grow
Token ID1663
Feature activation+4.54e+00

Pos logit contributions
ows+0.061
uries+0.054
ages+0.054
edy+0.053
cases+0.053
Neg logit contributions
 least-0.058
 mid-0.049
 M-0.048
 tw-0.046
 bur-0.046
Tokenls
Token ID7278
Feature activation+2.31e+00

Pos logit contributions
 badges+0.132
uries+0.127
 homework+0.123
 wrists+0.122
 receipt+0.121
Neg logit contributions
ime-0.165
Little-0.160
 least-0.157
 of-0.147
in-0.143
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
 badges+0.100
ows+0.097
 tricks+0.094
 diapers+0.093
 names+0.093
Neg logit contributions
 least-0.061
Little-0.053
ime-0.050
illy-0.047
ately-0.046
Token of
Token ID286
Feature activation-3.11e-01

Pos logit contributions
 badges+0.000
ows+0.000
 tricks+0.000
 names+0.000
 diapers+0.000
Neg logit contributions
 least-0.000
Little-0.000
ime-0.000
illy-0.000
Maria-0.000
Token cheese
Token ID9891
Feature activation+1.72e+00

Pos logit contributions
 least+0.012
ime+0.011
Little+0.010
 night+0.010
 Little+0.010
Neg logit contributions
ows-0.009
orts-0.008
 gag-0.008
 badges-0.008
cuts-0.008
Token and
Token ID290
Feature activation+1.19e+00

Pos logit contributions
 badges+0.073
ows+0.072
 tricks+0.069
 names+0.069
 diapers+0.068
Neg logit contributions
 least-0.046
Little-0.040
ime-0.038
illy-0.036
ately-0.034
Token sauce
Token ID10746
Feature activation+3.28e+00

Pos logit contributions
ows+0.037
 badges+0.035
orts+0.034
cuts+0.033
 tricks+0.033
Neg logit contributions
 least-0.046
Little-0.041
ime-0.038
ately-0.037
illy-0.036
Token and
Token ID290
Feature activation+1.60e+00

Pos logit contributions
 badges+0.126
ows+0.122
 tricks+0.118
 names+0.117
 diapers+0.116
Neg logit contributions
 least-0.101
Little-0.091
ime-0.087
illy-0.083
ately-0.079
Token topp
Token ID23126
Feature activation+7.57e+00

Pos logit contributions
ows+0.050
 badges+0.047
orts+0.046
cuts+0.044
 tricks+0.044
Neg logit contributions
 least-0.063
Little-0.055
ime-0.053
illy-0.050
ately-0.050
Tokenings
Token ID654
Feature activation+3.79e+00

Pos logit contributions
 badges+0.232
trained+0.226
 facts+0.211
bows+0.207
 versa+0.205
Neg logit contributions
ime-0.261
ill-0.232
oh-0.230
ately-0.225
illy-0.223
Token.
Token ID13
Feature activation+2.00e+00

Pos logit contributions
 badges+0.152
ows+0.145
 gag+0.144
 tricks+0.144
 facts+0.138
Neg logit contributions
 least-0.103
Little-0.095
ime-0.088
illy-0.083
 Little-0.082
Token The
Token ID383
Feature activation+1.16e+00

Pos logit contributions
 badges+0.062
 tricks+0.060
ows+0.060
aches+0.057
 homework+0.055
Neg logit contributions
 least-0.077
Little-0.072
 Little-0.065
ime-0.064
illy-0.063
Token people
Token ID661
Feature activation+3.31e-01

Pos logit contributions
ows+0.039
 badges+0.036
orts+0.036
cks+0.034
 gag+0.034
Neg logit contributions
 least-0.043
Little-0.036
ime-0.035
 3-0.034
illy-0.032
Token who
Token ID508
Feature activation+2.52e+00

Pos logit contributions
 badges+0.012
ows+0.011
 diapers+0.011
 tricks+0.011
 names+0.011
Neg logit contributions
 least-0.011
ime-0.010
Little-0.010
ately-0.008
illy-0.008
Token dog
Token ID3290
Feature activation+1.98e+00

Pos logit contributions
 badges+0.018
ows+0.018
 tricks+0.017
 names+0.017
 diapers+0.017
Neg logit contributions
 least-0.014
Little-0.013
ime-0.012
illy-0.012
ately-0.011
Token watches
Token ID16860
Feature activation+2.83e-02

Pos logit contributions
 badges+0.070
ows+0.068
 diapers+0.067
bones+0.066
orts+0.065
Neg logit contributions
 least-0.068
Little-0.054
ime-0.048
 mid-0.047
st-0.047
Token them
Token ID606
Feature activation+2.62e+00

Pos logit contributions
 badges+0.001
ows+0.001
 tricks+0.001
 names+0.001
 diapers+0.001
Neg logit contributions
 least-0.001
Little-0.001
ime-0.001
illy-0.001
Maria-0.001
Token.
Token ID13
Feature activation+1.21e+00

Pos logit contributions
 badges+0.114
ows+0.112
 tricks+0.108
 diapers+0.107
 names+0.107
Neg logit contributions
 least-0.069
Little-0.060
ime-0.057
illy-0.054
ately-0.051
Token He
Token ID679
Feature activation+1.69e+00

Pos logit contributions
 badges+0.043
ows+0.043
 tricks+0.041
 diapers+0.040
aches+0.039
Neg logit contributions
 least-0.040
Little-0.038
ime-0.034
 Little-0.034
Maria-0.033
Token bar
Token ID2318
Feature activation+7.57e+00

Pos logit contributions
 badges+0.052
ows+0.051
 diapers+0.051
ages+0.049
 chips+0.048
Neg logit contributions
 least-0.067
Little-0.053
ime-0.050
 mid-0.049
 knew-0.048
Tokenks
Token ID591
Feature activation+4.36e+00

Pos logit contributions
 badges+0.155
 diapers+0.136
 chips+0.133
ows+0.128
 labels+0.127
Neg logit contributions
 least-0.371
ime-0.343
ill-0.333
Little-0.329
ately-0.326
Token and
Token ID290
Feature activation+1.53e+00

Pos logit contributions
 badges+0.215
ows+0.208
 diapers+0.204
cuts+0.202
 homework+0.201
Neg logit contributions
 least-0.077
Little-0.071
ime-0.065
Maria-0.055
illy-0.055
Token cheers
Token ID34550
Feature activation+2.13e+00

Pos logit contributions
ows+0.054
 badges+0.049
ages+0.049
cuts+0.049
edy+0.049
Neg logit contributions
 least-0.054
 mid-0.044
Little-0.042
 M-0.041
 Little-0.041
Token.
Token ID13
Feature activation+1.69e+00

Pos logit contributions
 badges+0.084
ows+0.081
 tricks+0.078
 diapers+0.078
 names+0.077
Neg logit contributions
 least-0.064
Little-0.058
ime-0.055
illy-0.053
ately-0.050
Token He
Token ID679
Feature activation+1.81e+00

Pos logit contributions
 badges+0.069
ows+0.068
 tricks+0.066
 diapers+0.065
 names+0.064
Neg logit contributions
 least-0.047
Little-0.044
ime-0.040
illy-0.038
Maria-0.037
Token l
Token ID300
Feature activation+5.50e+00

Pos logit contributions
 badges+0.047
ows+0.046
 diapers+0.045
orts+0.044
bows+0.044
Neg logit contributions
 least-0.030
Little-0.024
ime-0.023
ately-0.020
 Little-0.020
Tokenicks
Token ID3378
Feature activation+1.99e+00

Pos logit contributions
 badges+0.158
 diapers+0.142
 tricks+0.140
ows+0.138
cuts+0.137
Neg logit contributions
 least-0.230
ime-0.206
illy-0.204
ill-0.199
Little-0.198
Token his
Token ID465
Feature activation+3.23e+00

Pos logit contributions
 badges+0.075
ows+0.074
 tricks+0.070
 diapers+0.069
 names+0.069
Neg logit contributions
 least-0.061
Little-0.057
ime-0.054
illy-0.052
Maria-0.050
Token lips
Token ID11914
Feature activation+2.09e+00

Pos logit contributions
ows+0.101
 badges+0.101
cuts+0.097
bows+0.095
orts+0.092
Neg logit contributions
 least-0.113
ime-0.104
Little-0.102
 3-0.098
 mid-0.096
Token and
Token ID290
Feature activation+1.48e+00

Pos logit contributions
 badges+0.098
ows+0.093
 tricks+0.091
 diapers+0.091
 names+0.090
Neg logit contributions
 least-0.047
Little-0.041
ime-0.039
illy-0.036
ill-0.034
Token bar
Token ID2318
Feature activation+7.54e+00

Pos logit contributions
ows+0.056
cuts+0.052
 badges+0.052
orts+0.050
 names+0.049
Neg logit contributions
 least-0.045
 mid-0.037
Little-0.037
 Little-0.036
 M-0.036
Tokenks
Token ID591
Feature activation+4.70e+00

Pos logit contributions
 badges+0.150
 diapers+0.126
 tricks+0.126
 labels+0.124
ows+0.122
Neg logit contributions
 least-0.371
ime-0.349
Little-0.339
ately-0.338
ill-0.333
Token.
Token ID13
Feature activation+2.67e+00

Pos logit contributions
 badges+0.207
cuts+0.199
ows+0.196
 diapers+0.194
orts+0.193
Neg logit contributions
 least-0.099
ime-0.098
Little-0.096
ful-0.086
 mid-0.085
Token He
Token ID679
Feature activation+2.37e+00

Pos logit contributions
 badges+0.107
ows+0.105
 tricks+0.100
 diapers+0.098
 names+0.097
Neg logit contributions
 least-0.077
Little-0.072
ime-0.067
illy-0.063
Maria-0.062
Token is
Token ID318
Feature activation+1.31e+00

Pos logit contributions
ages+0.075
ows+0.075
 badges+0.072
 diapers+0.072
 ours+0.070
Neg logit contributions
 least-0.089
 se-0.066
Little-0.066
 knew-0.065
 mid-0.064
Token happy
Token ID3772
Feature activation+1.21e+00

Pos logit contributions
cuts+0.054
 badges+0.054
ows+0.053
bows+0.051
gers+0.050
Neg logit contributions
 least-0.038
 3-0.030
 nowhere-0.028
ful-0.027
 mid-0.027
Token dog
Token ID3290
Feature activation+4.10e-01

Pos logit contributions
 badges+0.022
ows+0.022
 tricks+0.021
 diapers+0.021
 names+0.020
Neg logit contributions
 least-0.019
Little-0.017
ime-0.016
illy-0.015
ately-0.014
Token."
Token ID526
Feature activation+2.01e+00

Pos logit contributions
 badges+0.015
ows+0.015
 names+0.014
 diapers+0.014
 tricks+0.014
Neg logit contributions
 least-0.013
Little-0.012
ime-0.011
illy-0.011
ately-0.010
Token
Token ID198
Feature activation+8.44e-03

Pos logit contributions
 badges+0.092
ows+0.090
 tricks+0.087
 names+0.087
 diapers+0.086
Neg logit contributions
 least-0.049
Little-0.042
ime-0.041
illy-0.038
ately-0.036
Token
Token ID198
Feature activation+4.96e-02

Pos logit contributions
 badges+0.000
ows+0.000
 tricks+0.000
 names+0.000
orts+0.000
Neg logit contributions
 least-0.000
ime-0.000
Little-0.000
ately-0.000
illy-0.000
TokenMax
Token ID11518
Feature activation+9.48e-01

Pos logit contributions
 badges+0.001
ows+0.001
 helmets+0.001
 tricks+0.001
orts+0.001
Neg logit contributions
 least-0.002
ime-0.002
ately-0.002
illy-0.002
ill-0.002
Token bar
Token ID2318
Feature activation+7.54e+00

Pos logit contributions
bones+0.032
 diapers+0.032
 badges+0.032
ows+0.031
 gag+0.031
Neg logit contributions
 least-0.033
Little-0.027
 Little-0.025
 mid-0.024
illy-0.024
Tokenks
Token ID591
Feature activation+4.26e+00

Pos logit contributions
 badges+0.141
 diapers+0.128
 tricks+0.122
cuts+0.117
ows+0.117
Neg logit contributions
 least-0.370
ime-0.342
ill-0.339
Little-0.332
ately-0.331
Token and
Token ID290
Feature activation+1.15e+00

Pos logit contributions
 badges+0.226
ows+0.222
cuts+0.221
aches+0.217
 diapers+0.216
Neg logit contributions
 least-0.054
Little-0.048
ime-0.041
 mid-0.038
 Little-0.037
Token w
Token ID266
Feature activation+4.85e+00

Pos logit contributions
ows+0.042
ages+0.041
bones+0.041
 preferences+0.039
 meanings+0.039
Neg logit contributions
 least-0.036
 Little-0.030
 M-0.030
Little-0.029
 Bear-0.029
Tokenags
Token ID3775
Feature activation+2.94e+00

Pos logit contributions
 badges+0.120
 diapers+0.112
 names+0.108
 gag+0.104
 hides+0.104
Neg logit contributions
 least-0.206
ime-0.196
illy-0.189
Little-0.185
ately-0.176
Token his
Token ID465
Feature activation+3.70e+00

Pos logit contributions
ows+0.121
 badges+0.120
cuts+0.113
 diapers+0.112
 names+0.112
Neg logit contributions
 least-0.079
Little-0.072
ime-0.068
Maria-0.066
illy-0.063
Token.
Token ID13
Feature activation+3.25e+00

Pos logit contributions
 badges+0.103
ows+0.096
 names+0.095
 tricks+0.095
 diapers+0.094
Neg logit contributions
 least-0.071
Little-0.063
ime-0.062
illy-0.058
ately-0.057
Token
Token ID198
Feature activation+1.52e+00

Pos logit contributions
 badges+0.139
ows+0.136
 tricks+0.132
 names+0.130
 diapers+0.130
Neg logit contributions
 least-0.085
Little-0.078
ime-0.072
illy-0.068
Maria-0.065
Token
Token ID198
Feature activation+1.41e+00

Pos logit contributions
 badges+0.069
ows+0.069
 tricks+0.066
 names+0.066
 diapers+0.065
Neg logit contributions
 least-0.036
Little-0.030
ime-0.029
illy-0.028
ately-0.026
TokenThe
Token ID464
Feature activation+1.96e+00

Pos logit contributions
 badges+0.053
ows+0.052
 tricks+0.050
 names+0.049
 diapers+0.049
Neg logit contributions
 least-0.046
Little-0.042
ime-0.040
illy-0.038
Maria-0.036
Token dog
Token ID3290
Feature activation+2.31e+00

Pos logit contributions
ows+0.067
 badges+0.064
 diapers+0.060
cks+0.059
 tricks+0.059
Neg logit contributions
 least-0.071
Little-0.065
ime-0.061
illy-0.059
 3-0.057
Token bar
Token ID2318
Feature activation+7.53e+00

Pos logit contributions
ages+0.077
 ours+0.075
bows+0.075
 badges+0.075
ometers+0.074
Neg logit contributions
 least-0.078
 again-0.066
 mid-0.060
 and-0.060
Little-0.060
Tokenks
Token ID591
Feature activation+4.44e+00

Pos logit contributions
 badges+0.157
 diapers+0.143
cuts+0.131
 labels+0.129
 ours+0.128
Neg logit contributions
 least-0.348
ime-0.328
ill-0.327
ately-0.316
Little-0.308
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
 badges+0.221
ows+0.212
cuts+0.211
 diapers+0.209
bows+0.208
Neg logit contributions
 least-0.074
Little-0.068
ime-0.064
ill-0.056
 mid-0.055
Token runs
Token ID4539
Feature activation+1.45e+00

Pos logit contributions
ows+0.065
ages+0.063
uries+0.062
bows+0.059
edy+0.059
Neg logit contributions
 least-0.060
 mid-0.051
 tw-0.048
 bur-0.047
 bubble-0.046
Token away
Token ID1497
Feature activation+2.25e+00

Pos logit contributions
 badges+0.068
 preferences+0.067
aches+0.066
ows+0.065
cks+0.065
Neg logit contributions
 least-0.030
Little-0.024
B-0.024
 again-0.022
 since-0.021
Token.
Token ID13
Feature activation+1.86e+00

Pos logit contributions
 badges+0.103
cuts+0.095
ows+0.095
 names+0.094
 helmets+0.092
Neg logit contributions
 least-0.054
Little-0.046
ime-0.045
ill-0.042
ately-0.041
Token name
Token ID1438
Feature activation+2.04e+00

Pos logit contributions
 badges+0.027
ows+0.026
cks+0.026
bones+0.025
trained+0.024
Neg logit contributions
 least-0.080
Little-0.068
 3-0.068
illy-0.068
ime-0.067
Token?"
Token ID1701
Feature activation+2.17e+00

Pos logit contributions
 badges+0.081
ows+0.080
 tricks+0.077
 names+0.076
 diapers+0.075
Neg logit contributions
 least-0.061
Little-0.054
ime-0.052
illy-0.049
ately-0.047
Token
Token ID198
Feature activation+6.43e-01

Pos logit contributions
 badges+0.103
ows+0.101
 tricks+0.098
 names+0.097
 diapers+0.097
Neg logit contributions
 least-0.049
Little-0.042
ime-0.040
illy-0.037
ately-0.034
Token
Token ID198
Feature activation+6.03e-01

Pos logit contributions
 badges+0.028
ows+0.028
 tricks+0.027
 names+0.027
orts+0.027
Neg logit contributions
 least-0.017
Little-0.013
ime-0.013
illy-0.013
ately-0.012
TokenTom
Token ID13787
Feature activation+7.39e-01

Pos logit contributions
 badges+0.029
ows+0.029
 names+0.028
 tricks+0.028
 diapers+0.028
Neg logit contributions
Little-0.012
 least-0.012
ime-0.010
Maria-0.010
illy-0.009
Token bar
Token ID2318
Feature activation+7.53e+00

Pos logit contributions
 badges+0.021
bones+0.021
 diapers+0.020
ages+0.020
ows+0.020
Neg logit contributions
 least-0.030
Little-0.026
 mid-0.024
andy-0.024
ill-0.024
Tokenks
Token ID591
Feature activation+4.37e+00

Pos logit contributions
 badges+0.149
 diapers+0.130
ows+0.125
 tricks+0.125
 chips+0.124
Neg logit contributions
 least-0.364
ime-0.345
ill-0.338
Little-0.333
ately-0.325
Token and
Token ID290
Feature activation+1.16e+00

Pos logit contributions
 badges+0.224
cuts+0.216
ows+0.216
 diapers+0.211
aches+0.211
Neg logit contributions
 least-0.066
Little-0.062
ime-0.057
 mid-0.051
 Little-0.049
Token jumps
Token ID18045
Feature activation+2.47e+00

Pos logit contributions
ages+0.040
ows+0.038
uries+0.037
bones+0.036
ggies+0.035
Neg logit contributions
 least-0.041
 tw-0.035
 M-0.035
 mid-0.035
 Little-0.034
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
 badges+0.103
ows+0.096
 tricks+0.095
 preferences+0.095
 facts+0.094
Neg logit contributions
 least-0.067
Little-0.062
ime-0.058
illy-0.055
ately-0.053
Token He
Token ID679
Feature activation+1.78e+00

Pos logit contributions
 badges+0.046
ows+0.044
cks+0.043
cuts+0.042
aches+0.042
Neg logit contributions
 least-0.031
Little-0.030
 Little-0.029
ime-0.028
Maria-0.026
Token?"
Token ID1701
Feature activation+1.96e+00

Pos logit contributions
 least+0.011
Little+0.010
ime+0.009
illy+0.009
Maria+0.008
Neg logit contributions
 badges-0.015
ows-0.015
 tricks-0.015
 names-0.015
 diapers-0.014
Token
Token ID198
Feature activation-4.26e-01

Pos logit contributions
 badges+0.084
ows+0.084
 tricks+0.079
 diapers+0.079
 names+0.079
Neg logit contributions
 least-0.052
Little-0.048
ime-0.043
illy-0.042
Maria-0.040
Token
Token ID198
Feature activation-4.86e-01

Pos logit contributions
 least+0.011
Little+0.009
ime+0.008
illy+0.008
ately+0.008
Neg logit contributions
 badges-0.019
ows-0.019
 tricks-0.018
 names-0.018
orts-0.018
TokenThe
Token ID464
Feature activation+7.56e-01

Pos logit contributions
 least+0.012
Little+0.010
ime+0.010
illy+0.009
ately+0.009
Neg logit contributions
 badges-0.022
ows-0.022
 tricks-0.021
 names-0.021
 diapers-0.021
Token dog
Token ID3290
Feature activation+2.35e+00

Pos logit contributions
ows+0.028
 badges+0.028
 diapers+0.026
cks+0.025
 names+0.025
Neg logit contributions
 least-0.025
Little-0.023
ime-0.021
illy-0.020
 3-0.019
Token bar
Token ID2318
Feature activation+7.53e+00

Pos logit contributions
 badges+0.092
 diapers+0.089
ows+0.089
cks+0.087
bones+0.086
Neg logit contributions
 least-0.067
Little-0.060
 Little-0.053
illy-0.051
ime-0.051
Tokenks
Token ID591
Feature activation+4.35e+00

Pos logit contributions
 badges+0.167
 diapers+0.151
ows+0.149
 tricks+0.148
 names+0.143
Neg logit contributions
 least-0.350
ime-0.328
Little-0.322
ately-0.316
ill-0.314
Token.
Token ID13
Feature activation+9.59e-01

Pos logit contributions
 badges+0.190
ows+0.185
 diapers+0.178
 tricks+0.178
 names+0.177
Neg logit contributions
 least-0.109
Little-0.099
ime-0.094
illy-0.088
Maria-0.083
Token The
Token ID383
Feature activation+9.05e-01

Pos logit contributions
 badges+0.037
ows+0.036
 diapers+0.035
aches+0.035
 tricks+0.035
Neg logit contributions
 least-0.028
Little-0.026
 Little-0.024
ime-0.023
ill-0.023
Token dog
Token ID3290
Feature activation+1.83e+00

Pos logit contributions
ows+0.033
 badges+0.031
cks+0.030
 diapers+0.029
bows+0.028
Neg logit contributions
 least-0.031
Little-0.028
ime-0.026
 3-0.025
illy-0.025
Token is
Token ID318
Feature activation+3.65e-01

Pos logit contributions
 badges+0.063
 diapers+0.061
bones+0.060
ages+0.059
ows+0.058
Neg logit contributions
 least-0.060
Little-0.050
 mid-0.046
 Little-0.045
 knew-0.045
Token afraid
Token ID7787
Feature activation+2.25e+00

Pos logit contributions
bows+0.035
cuts+0.035
 facts+0.035
 badges+0.034
orts+0.034
Neg logit contributions
 least-0.023
 nowhere-0.019
 3-0.018
ful-0.017
 mid-0.017
Token.
Token ID13
Feature activation+2.26e+00

Pos logit contributions
 badges+0.091
ows+0.090
 tricks+0.087
 names+0.086
 diapers+0.086
Neg logit contributions
 least-0.066
Little-0.058
ime-0.055
illy-0.054
Maria-0.050
Token
Token ID198
Feature activation+5.44e-01

Pos logit contributions
 badges+0.085
ows+0.083
 names+0.080
 diapers+0.079
 tricks+0.079
Neg logit contributions
 least-0.074
Little-0.065
ime-0.063
illy-0.062
ately-0.057
Token
Token ID198
Feature activation+5.37e-01

Pos logit contributions
 badges+0.023
ows+0.023
 names+0.022
 tricks+0.022
orts+0.022
Neg logit contributions
 least-0.015
ime-0.012
Little-0.012
illy-0.012
ately-0.011
TokenMax
Token ID11518
Feature activation+8.30e-01

Pos logit contributions
 badges+0.022
ows+0.022
 tricks+0.021
 names+0.021
 diapers+0.021
Neg logit contributions
 least-0.015
Little-0.013
ime-0.013
illy-0.012
ately-0.012
Token bar
Token ID2318
Feature activation+7.48e+00

Pos logit contributions
 badges+0.028
 facts+0.027
 diapers+0.027
bows+0.027
bones+0.027
Neg logit contributions
 least-0.029
Little-0.024
ime-0.022
oh-0.021
'-0.021
Tokenks
Token ID591
Feature activation+4.42e+00

Pos logit contributions
 badges+0.151
 diapers+0.134
 tricks+0.127
 chips+0.126
 labels+0.125
Neg logit contributions
 least-0.355
ime-0.340
ill-0.324
ately-0.323
Little-0.319
Token at
Token ID379
Feature activation+8.73e-01

Pos logit contributions
 badges+0.203
cuts+0.192
aches+0.190
bows+0.190
ows+0.190
Neg logit contributions
 least-0.086
Little-0.082
ime-0.078
 Little-0.070
 mid-0.069
Token the
Token ID262
Feature activation+6.14e-01

Pos logit contributions
 badges+0.024
 diapers+0.023
ows+0.023
 tricks+0.022
 names+0.022
Neg logit contributions
 least-0.035
Little-0.033
ime-0.033
illy-0.031
Em-0.031
Token van
Token ID5719
Feature activation-4.10e-01

Pos logit contributions
ows+0.022
 badges+0.022
 tricks+0.021
 diapers+0.020
 names+0.020
Neg logit contributions
 least-0.021
Little-0.019
ime-0.018
illy-0.017
ately-0.016
Token.
Token ID13
Feature activation+1.39e+00

Pos logit contributions
 least+0.012
Little+0.010
ime+0.010
ately+0.009
illy+0.009
Neg logit contributions
 badges-0.016
ows-0.016
 diapers-0.015
 tricks-0.015
 names-0.015
Token Spot
Token ID15899
Feature activation+2.76e+00

Pos logit contributions
 least+0.048
Little+0.042
 Little+0.038
ime+0.035
ately+0.035
Neg logit contributions
 badges-0.076
ows-0.076
bows-0.073
 tricks-0.072
orts-0.071
Token is
Token ID318
Feature activation+5.12e-01

Pos logit contributions
 badges+0.110
 diapers+0.103
 facts+0.103
bones+0.101
 titles+0.101
Neg logit contributions
 least-0.083
oh-0.062
'-0.059
 knew-0.058
Little-0.057
Token scared
Token ID12008
Feature activation+2.29e+00

Pos logit contributions
 badges+0.022
cuts+0.021
 facts+0.021
bows+0.021
 names+0.020
Neg logit contributions
 least-0.014
 nowhere-0.012
 mid-0.011
 3-0.011
ime-0.011
Token.
Token ID13
Feature activation+2.03e+00

Pos logit contributions
 badges+0.077
ows+0.077
 tricks+0.074
 diapers+0.073
 names+0.073
Neg logit contributions
 least-0.082
Little-0.074
ime-0.070
illy-0.068
ately-0.066
Token He
Token ID679
Feature activation+2.51e+00

Pos logit contributions
 badges+0.086
 tricks+0.083
aches+0.083
ows+0.082
 facts+0.081
Neg logit contributions
Little-0.052
 least-0.050
 Little-0.046
ime-0.043
Maria-0.042
Token bar
Token ID2318
Feature activation+7.47e+00

Pos logit contributions
bows+0.081
bones+0.074
ages+0.073
ows+0.071
 choices+0.071
Neg logit contributions
 least-0.095
 knew-0.076
Little-0.072
 couldn-0.071
ime-0.071
Tokenks
Token ID591
Feature activation+4.48e+00

Pos logit contributions
 badges+0.152
 diapers+0.133
 chips+0.127
 tricks+0.126
bes+0.126
Neg logit contributions
 least-0.359
ime-0.339
ill-0.326
ately-0.325
Little-0.322
Token at
Token ID379
Feature activation+1.03e+00

Pos logit contributions
 badges+0.216
ows+0.210
bows+0.208
cuts+0.207
 homework+0.205
Neg logit contributions
 least-0.075
Little-0.073
ime-0.066
 Little-0.058
 mid-0.056
Token the
Token ID262
Feature activation+6.64e-01

Pos logit contributions
 badges+0.038
ows+0.038
 tricks+0.035
 names+0.035
 diapers+0.034
Neg logit contributions
 least-0.035
Little-0.031
ime-0.029
illy-0.028
ately-0.027
Token truck
Token ID7779
Feature activation+1.41e+00

Pos logit contributions
ows+0.024
 badges+0.022
orts+0.021
aches+0.021
cks+0.021
Neg logit contributions
 least-0.021
Little-0.019
ime-0.018
 3-0.018
 mid-0.017
Token and
Token ID290
Feature activation+1.79e+00

Pos logit contributions
 badges+0.064
ows+0.061
 diapers+0.060
 tricks+0.059
 names+0.059
Neg logit contributions
 least-0.034
Little-0.027
ime-0.027
ately-0.024
ill-0.024
Token out
Token ID503
Feature activation+1.11e+00

Pos logit contributions
 badges+0.029
ows+0.028
 tricks+0.027
 diapers+0.027
 names+0.027
Neg logit contributions
 least-0.021
Little-0.019
ime-0.018
illy-0.017
ately-0.016
Token and
Token ID290
Feature activation+1.56e+00

Pos logit contributions
ows+0.044
 badges+0.043
 tricks+0.042
 names+0.042
 diapers+0.041
Neg logit contributions
 least-0.034
Little-0.030
illy-0.028
ime-0.028
Em-0.027
Token cry
Token ID3960
Feature activation+2.03e+00

Pos logit contributions
ows+0.059
 badges+0.058
cuts+0.057
oodle+0.055
orts+0.054
Neg logit contributions
 least-0.053
Little-0.042
 mid-0.042
ime-0.040
 se-0.039
Token.
Token ID13
Feature activation+2.96e+00

Pos logit contributions
 badges+0.076
ows+0.074
 tricks+0.072
 names+0.071
 diapers+0.070
Neg logit contributions
 least-0.066
Little-0.059
ime-0.057
illy-0.054
ately-0.052
Token Rex
Token ID17853
Feature activation+3.62e+00

Pos logit contributions
 badges+0.123
ows+0.121
 tricks+0.117
 diapers+0.113
 names+0.112
Neg logit contributions
 least-0.082
Little-0.076
ime-0.070
illy-0.066
Maria-0.066
Token bar
Token ID2318
Feature activation+7.46e+00

Pos logit contributions
 badges+0.124
bones+0.114
 facts+0.113
 receipt+0.113
uries+0.112
Neg logit contributions
 least-0.126
Little-0.097
 mid-0.094
ime-0.092
oh-0.092
Tokenks
Token ID591
Feature activation+4.53e+00

Pos logit contributions
 badges+0.161
 diapers+0.139
 helmets+0.134
 labels+0.131
 chips+0.131
Neg logit contributions
 least-0.354
ime-0.333
ill-0.319
ately-0.313
Little-0.312
Token at
Token ID379
Feature activation+9.35e-01

Pos logit contributions
 badges+0.246
ows+0.237
bows+0.234
cuts+0.233
 diapers+0.231
Neg logit contributions
 least-0.058
Little-0.049
ime-0.043
 mid-0.035
ful-0.033
Token them
Token ID606
Feature activation+3.06e+00

Pos logit contributions
 badges+0.027
ows+0.026
 tricks+0.025
 diapers+0.025
 names+0.025
Neg logit contributions
 least-0.037
Little-0.035
ime-0.034
illy-0.033
Maria-0.032
Token.
Token ID13
Feature activation+2.47e+00

Pos logit contributions
 badges+0.155
ows+0.145
 diapers+0.143
 tricks+0.143
 names+0.142
Neg logit contributions
 least-0.061
Little-0.048
ime-0.047
illy-0.040
ill-0.039
Token
Token ID198
Feature activation+7.54e-01

Pos logit contributions
 badges+0.112
ows+0.108
aches+0.107
bows+0.104
 tricks+0.104
Neg logit contributions
Little-0.053
 least-0.053
 Little-0.047
ime-0.044
Maria-0.042
Tokenaded
Token ID5286
Feature activation-1.03e+00

Pos logit contributions
 badges+0.139
ows+0.137
 diapers+0.130
 tricks+0.129
 names+0.129
Neg logit contributions
 least-0.132
Little-0.118
ime-0.118
illy-0.113
ately-0.106
Token in
Token ID287
Feature activation-2.41e-01

Pos logit contributions
 least+0.033
Little+0.030
ime+0.027
illy+0.027
Em+0.026
Neg logit contributions
 badges-0.039
ows-0.038
 tricks-0.038
 names-0.037
 diapers-0.036
Token the
Token ID262
Feature activation-8.27e-01

Pos logit contributions
enny+0.009
ately+0.009
 least+0.009
Em+0.009
illy+0.009
Neg logit contributions
 names-0.007
 tricks-0.007
 labels-0.007
 badges-0.007
 helmets-0.007
Token water
Token ID1660
Feature activation+9.66e-02

Pos logit contributions
 least+0.029
ately+0.029
enny+0.026
Maria+0.026
illy+0.026
Neg logit contributions
 badges-0.027
 names-0.026
 tricks-0.026
 helmets-0.025
 diapers-0.025
Token delic
Token ID8675
Feature activation-1.53e+00

Pos logit contributions
ows+0.004
 tricks+0.003
 names+0.003
 badges+0.003
 diapers+0.003
Neg logit contributions
Little-0.003
 least-0.003
Em-0.003
Maria-0.003
ime-0.003
Tokenately
Token ID1286
Feature activation-7.47e+00

Pos logit contributions
 least+0.053
Little+0.053
Em+0.047
Maria+0.046
ime+0.043
Neg logit contributions
 badges-0.052
ows-0.051
 tricks-0.050
 names-0.049
cks-0.048
Token with
Token ID351
Feature activation+1.26e+00

Pos logit contributions
 least+0.206
Little+0.182
ime+0.174
illy+0.165
ately+0.155
Neg logit contributions
 badges-0.313
ows-0.306
 tricks-0.294
 names-0.292
 diapers-0.292
Token his
Token ID465
Feature activation+1.19e+00

Pos logit contributions
 badges+0.044
ows+0.042
 tricks+0.042
 names+0.041
 diapers+0.041
Neg logit contributions
 least-0.044
Little-0.040
ime-0.038
illy-0.037
ately-0.036
Token fishing
Token ID12478
Feature activation+3.94e+00

Pos logit contributions
 badges+0.039
 tricks+0.037
 names+0.037
ows+0.036
 diapers+0.035
Neg logit contributions
 least-0.045
Little-0.042
ime-0.039
illy-0.039
Maria-0.039
Token rod
Token ID15299
Feature activation+9.17e-01

Pos logit contributions
 badges+0.122
ows+0.119
 tricks+0.114
 names+0.112
 diapers+0.111
Neg logit contributions
 least-0.152
Little-0.141
ime-0.135
illy-0.131
Maria-0.126
Token.
Token ID13
Feature activation-6.53e-01

Pos logit contributions
 badges+0.033
ows+0.033
 tricks+0.032
 names+0.031
 diapers+0.031
Neg logit contributions
 least-0.030
Little-0.028
ime-0.026
illy-0.025
Maria-0.024
Token day
Token ID1110
Feature activation-1.20e+00

Pos logit contributions
 least+0.110
Little+0.097
illy+0.093
ately+0.091
Daddy+0.087
Neg logit contributions
 tricks-0.137
ows-0.134
 badges-0.134
 names-0.131
 labels-0.130
Token.
Token ID13
Feature activation-1.46e+00

Pos logit contributions
 least+0.039
Little+0.035
ime+0.033
illy+0.032
Maria+0.031
Neg logit contributions
ows-0.045
 badges-0.045
 tricks-0.043
 names-0.042
 diapers-0.042
Token They
Token ID1119
Feature activation+1.03e+00

Pos logit contributions
 least+0.063
Little+0.058
ime+0.056
illy+0.054
ately+0.053
Neg logit contributions
 badges-0.038
ows-0.037
 names-0.035
 tricks-0.035
 diapers-0.034
Token worked
Token ID3111
Feature activation-1.76e+00

Pos logit contributions
 badges+0.038
ows+0.036
 names+0.035
 tricks+0.034
 labels+0.034
Neg logit contributions
 least-0.032
Little-0.030
ime-0.030
illy-0.029
ately-0.027
Token delic
Token ID8675
Feature activation-4.36e-01

Pos logit contributions
 least+0.061
Little+0.055
ime+0.053
illy+0.051
ately+0.049
Neg logit contributions
 badges-0.062
ows-0.061
 tricks-0.058
 names-0.057
 diapers-0.057
Tokenately
Token ID1286
Feature activation-7.18e+00

Pos logit contributions
 least+0.007
Little+0.006
Maria+0.005
Em+0.004
ime+0.004
Neg logit contributions
ows-0.024
 badges-0.023
 tricks-0.022
 names-0.022
 diapers-0.022
Token and
Token ID290
Feature activation-9.03e-01

Pos logit contributions
 least+0.241
Little+0.224
illy+0.207
ime+0.203
Maria+0.202
Neg logit contributions
 badges-0.254
ows-0.248
 tricks-0.248
 labels-0.237
 names-0.236
Token carefully
Token ID7773
Feature activation-1.35e+00

Pos logit contributions
 least+0.026
Little+0.025
ime+0.024
illy+0.023
Maria+0.021
Neg logit contributions
 badges-0.035
ows-0.033
 tricks-0.032
 labels-0.032
 names-0.032
Token and
Token ID290
Feature activation-6.44e-01

Pos logit contributions
 least+0.042
Little+0.038
illy+0.035
ime+0.035
Maria+0.033
Neg logit contributions
 badges-0.053
ows-0.053
 tricks-0.051
 names-0.049
 labels-0.049
Token nothing
Token ID2147
Feature activation+1.47e+00

Pos logit contributions
 least+0.018
Little+0.016
ime+0.015
illy+0.015
Maria+0.014
Neg logit contributions
 badges-0.027
ows-0.026
 tricks-0.025
 names-0.025
 diapers-0.025
Token broke
Token ID6265
Feature activation-2.86e+00

Pos logit contributions
ows+0.056
 badges+0.054
 tricks+0.053
 names+0.050
 diapers+0.050
Neg logit contributions
 least-0.047
Little-0.043
ime-0.040
illy-0.039
Maria-0.038
TokenYes
Token ID5297
Feature activation-1.06e+00

Pos logit contributions
ows+0.015
 badges+0.015
 tricks+0.014
 diapers+0.014
 labels+0.014
Neg logit contributions
 least-0.007
Little-0.007
ime-0.006
illy-0.006
 3-0.006
Token,
Token ID11
Feature activation-7.37e-01

Pos logit contributions
 least+0.025
Little+0.021
ime+0.020
illy+0.019
Maria+0.018
Neg logit contributions
 badges-0.049
ows-0.048
 tricks-0.047
 names-0.046
 diapers-0.046
Token I
Token ID314
Feature activation-2.28e+00

Pos logit contributions
 least+0.021
Little+0.020
ime+0.018
illy+0.018
ately+0.017
Neg logit contributions
 badges-0.030
ows-0.029
 tricks-0.028
 diapers-0.028
 names-0.027
Token am
Token ID716
Feature activation+4.78e-01

Pos logit contributions
 least+0.095
Little+0.088
ime+0.085
illy+0.082
ately+0.079
Neg logit contributions
 badges-0.064
ows-0.063
 tricks-0.059
 names-0.058
 diapers-0.058
Token G
Token ID402
Feature activation-2.20e+00

Pos logit contributions
 badges+0.019
ows+0.018
 names+0.017
 tricks+0.017
 diapers+0.017
Neg logit contributions
 least-0.015
Little-0.013
ime-0.013
illy-0.012
 Little-0.012
Tokenert
Token ID861
Feature activation-6.83e+00

Pos logit contributions
 least+0.057
Little+0.048
Maria+0.043
ime+0.041
Em+0.040
Neg logit contributions
ows-0.097
 badges-0.090
 tricks-0.089
 names-0.088
cuts-0.088
Tokenie
Token ID494
Feature activation-2.65e+00

Pos logit contributions
 least+0.217
Little+0.178
Maria+0.162
illy+0.160
Em+0.157
Neg logit contributions
ows-0.260
 tricks-0.242
aches-0.235
cks-0.233
 badges-0.230
Token!
Token ID0
Feature activation-1.85e+00

Pos logit contributions
 least+0.064
Little+0.056
ime+0.053
illy+0.048
ately+0.045
Neg logit contributions
 badges-0.122
ows-0.116
 names-0.114
 diapers-0.114
 tricks-0.113
Tokenâ
Token ID22940
Feature activation-2.50e+00

Pos logit contributions
 least+0.065
Little+0.059
ime+0.058
illy+0.055
ately+0.053
Neg logit contributions
 badges-0.063
ows-0.061
 tricks-0.059
 names-0.058
 diapers-0.058
Token
Token ID26391
Feature activation+5.31e-01

Pos logit contributions
 least+0.089
Little+0.082
ime+0.077
illy+0.075
Em+0.069
Neg logit contributions
 badges-0.089
ows-0.084
 diapers-0.082
 names-0.082
 tricks-0.082
Token Mr
Token ID1770
Feature activation+3.04e+00

Pos logit contributions
 badges+0.021
ows+0.020
 tricks+0.020
 diapers+0.020
 names+0.019
Neg logit contributions
 least-0.016
Little-0.015
ime-0.014
illy-0.013
 Little-0.013
Token very
Token ID845
Feature activation+1.88e+00

Pos logit contributions
 least+0.008
Little+0.007
ime+0.007
illy+0.007
Maria+0.006
Neg logit contributions
 badges-0.008
ows-0.008
 tricks-0.007
 diapers-0.007
 names-0.007
Token special
Token ID2041
Feature activation-1.62e+00

Pos logit contributions
 badges+0.083
ows+0.080
cks+0.079
girls+0.077
bows+0.077
Neg logit contributions
 least-0.044
Little-0.043
illy-0.042
ime-0.042
 3-0.041
Token toy
Token ID13373
Feature activation-5.92e-01

Pos logit contributions
 least+0.060
Little+0.056
ime+0.054
illy+0.052
 3+0.049
Neg logit contributions
ows-0.051
 badges-0.051
cks-0.046
 tricks-0.046
 names-0.046
Token for
Token ID329
Feature activation-1.74e-02

Pos logit contributions
 least+0.018
Little+0.016
ime+0.015
illy+0.015
ately+0.014
Neg logit contributions
 badges-0.023
ows-0.023
 tricks-0.022
 names-0.021
orts-0.021
Token L
Token ID406
Feature activation-3.13e+00

Pos logit contributions
 least+0.001
Little+0.001
ime+0.001
Maria+0.001
illy+0.000
Neg logit contributions
 badges-0.001
 tricks-0.001
 diapers-0.001
 labels-0.001
ows-0.001
Tokenott
Token ID1252
Feature activation-6.78e+00

Pos logit contributions
Little+0.082
 least+0.082
Peter+0.069
 mid+0.069
where+0.069
Neg logit contributions
ows-0.120
aches-0.118
 labels-0.110
 homework-0.109
its-0.105
Tokenie
Token ID494
Feature activation-3.64e+00

Pos logit contributions
 least+0.132
Little+0.112
ime+0.099
illy+0.088
ately+0.084
Neg logit contributions
 badges-0.338
ows-0.337
 tricks-0.327
 names-0.323
 diapers-0.321
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
 least+0.106
Little+0.091
ime+0.088
illy+0.085
ately+0.080
Neg logit contributions
 badges-0.149
ows-0.145
 tricks-0.140
orts-0.139
 diapers-0.139
Token It
Token ID632
Feature activation+4.11e-02

Pos logit contributions
 least+0.045
Little+0.041
ime+0.039
illy+0.038
ately+0.036
Neg logit contributions
 badges-0.047
ows-0.046
 tricks-0.044
 diapers-0.043
 names-0.043
Token was
Token ID373
Feature activation-1.75e+00

Pos logit contributions
 badges+0.002
ows+0.002
 tricks+0.002
 names+0.002
 diapers+0.002
Neg logit contributions
 least-0.001
Little-0.001
ime-0.001
illy-0.001
ately-0.001
Token a
Token ID257
Feature activation+2.51e-01

Pos logit contributions
 least+0.046
Little+0.040
ime+0.037
illy+0.037
 Little+0.033
Neg logit contributions
 badges-0.075
ows-0.075
orts-0.072
 tricks-0.071
cuts-0.070
Token to
Token ID284
Feature activation+5.41e-01

Pos logit contributions
 least+0.043
Little+0.037
ime+0.035
illy+0.034
ately+0.032
Neg logit contributions
ows-0.065
 badges-0.065
 tricks-0.062
 diapers-0.062
 names-0.061
Token wait
Token ID4043
Feature activation-1.06e+00

Pos logit contributions
ows+0.020
 badges+0.020
orts+0.018
 diapers+0.018
 tricks+0.018
Neg logit contributions
 least-0.019
Little-0.017
ime-0.016
illy-0.016
ately-0.014
Token until
Token ID1566
Feature activation-2.89e+00

Pos logit contributions
 least+0.036
Little+0.034
ime+0.032
Maria+0.030
illy+0.030
Neg logit contributions
ows-0.037
 badges-0.036
 tricks-0.036
 diapers-0.035
 names-0.035
Token d
Token ID288
Feature activation+4.69e-01

Pos logit contributions
 least+0.087
Little+0.078
ime+0.074
illy+0.071
ately+0.067
Neg logit contributions
 badges-0.115
ows-0.112
 tricks-0.108
 names-0.107
 diapers-0.106
Tokeninn
Token ID3732
Feature activation-1.43e+00

Pos logit contributions
 badges+0.018
ows+0.018
 tricks+0.017
 names+0.017
 diapers+0.017
Neg logit contributions
 least-0.014
Little-0.013
ime-0.013
illy-0.012
ately-0.011
Tokenert
Token ID861
Feature activation-6.54e+00

Pos logit contributions
 least+0.040
Little+0.035
ime+0.033
illy+0.031
Maria+0.030
Neg logit contributions
 badges-0.060
ows-0.059
 tricks-0.056
 names-0.056
 diapers-0.056
Tokenime
Token ID524
Feature activation-1.39e+00

Pos logit contributions
 least+0.191
Little+0.155
Peter+0.138
Maria+0.136
 3+0.136
Neg logit contributions
ows-0.273
aches-0.243
cks-0.231
 badges-0.230
ves-0.229
Token.
Token ID13
Feature activation-5.20e-01

Pos logit contributions
 least+0.042
Little+0.037
ime+0.035
illy+0.034
Maria+0.032
Neg logit contributions
 badges-0.055
ows-0.054
 tricks-0.052
 names-0.051
 diapers-0.051
Token
Token ID198
Feature activation-2.04e+00

Pos logit contributions
 least+0.012
Little+0.011
 Little+0.009
Em+0.009
ime+0.009
Neg logit contributions
 badges-0.025
 tricks-0.023
ows-0.023
aches-0.023
cks-0.022
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
 least+0.053
Little+0.042
ime+0.042
illy+0.040
ately+0.039
Neg logit contributions
ows-0.090
 badges-0.089
 tricks-0.087
 names-0.086
orts-0.085
TokenAnna
Token ID31160
Feature activation+7.10e-01

Pos logit contributions
 least+0.057
Little+0.055
ime+0.049
illy+0.047
Em+0.046
Neg logit contributions
 badges-0.084
ows-0.081
 tricks-0.078
 names-0.078
 diapers-0.077
Token little
Token ID1310
Feature activation-2.51e+00

Pos logit contributions
 badges+0.011
ows+0.011
 tricks+0.011
 names+0.011
 diapers+0.010
Neg logit contributions
 least-0.011
Little-0.010
ime-0.010
illy-0.009
Maria-0.009
Token girl
Token ID2576
Feature activation-2.36e+00

Pos logit contributions
 least+0.064
Little+0.054
ime+0.053
illy+0.050
ately+0.046
Neg logit contributions
 badges-0.112
ows-0.111
 tricks-0.105
cks-0.104
 diapers-0.103
Token's
Token ID338
Feature activation-9.09e-01

Pos logit contributions
 least+0.060
ime+0.051
Little+0.051
ately+0.046
ill+0.045
Neg logit contributions
 badges-0.106
 diapers-0.098
cuts-0.097
orts-0.097
ows-0.096
Token shoulders
Token ID12450
Feature activation-2.61e+00

Pos logit contributions
 least+0.031
Little+0.028
ime+0.027
illy+0.025
ately+0.025
Neg logit contributions
 badges-0.033
ows-0.032
 diapers-0.030
 tricks-0.030
orts-0.030
Token affection
Token ID17696
Feature activation-6.60e-01

Pos logit contributions
 least+0.088
Little+0.081
ime+0.075
illy+0.075
Maria+0.072
Neg logit contributions
ows-0.094
 badges-0.091
 tricks-0.087
 names-0.086
 diapers-0.085
Tokenately
Token ID1286
Feature activation-6.44e+00

Pos logit contributions
 least+0.021
Little+0.019
Em+0.016
Maria+0.015
ime+0.015
Neg logit contributions
ows-0.027
 diapers-0.024
 badges-0.023
 names-0.023
 hats-0.023
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
 least+0.177
Little+0.158
ime+0.156
illy+0.143
ately+0.139
Neg logit contributions
 badges-0.272
ows-0.258
 names-0.252
 diapers-0.250
 tricks-0.245
Token
Token ID198
Feature activation-2.59e+00

Pos logit contributions
 least+0.042
ime+0.038
illy+0.035
Little+0.035
ately+0.033
Neg logit contributions
ows-0.038
 badges-0.037
 names-0.036
 name-0.035
orts-0.034
Token
Token ID198
Feature activation-2.44e+00

Pos logit contributions
 least+0.098
ately+0.078
ime+0.078
illy+0.072
bul+0.070
Neg logit contributions
ows-0.086
 badges-0.082
 names-0.081
orts-0.081
 name-0.079
TokenSarah
Token ID29284
Feature activation-1.65e+00

Pos logit contributions
 least+0.086
ime+0.069
ately+0.067
illy+0.065
 ocean+0.061
Neg logit contributions
 badges-0.085
 helmets-0.080
ows-0.079
 names-0.078
 labels-0.078
Token smiled
Token ID13541
Feature activation-1.14e+00

Pos logit contributions
 least+0.053
Little+0.047
ime+0.047
illy+0.045
ately+0.043
Neg logit contributions
 badges-0.059
ows-0.057
 tricks-0.056
 names-0.055
 wrists-0.053
Tokenuff
Token ID1648
Feature activation+1.45e+00

Pos logit contributions
 badges+0.057
ows+0.056
 tricks+0.052
 names+0.052
 diapers+0.052
Neg logit contributions
 least-0.065
Little-0.059
ime-0.056
illy-0.054
Maria-0.051
Tokenled
Token ID992
Feature activation+1.69e+00

Pos logit contributions
 badges+0.041
ows+0.041
 tricks+0.038
 diapers+0.037
 names+0.037
Neg logit contributions
 least-0.060
Little-0.055
ime-0.053
illy-0.051
Maria-0.050
Token his
Token ID465
Feature activation+2.44e+00

Pos logit contributions
ows+0.070
 badges+0.068
cuts+0.066
orts+0.065
 tricks+0.065
Neg logit contributions
 least-0.045
Little-0.041
ime-0.039
 Little-0.038
 3-0.037
Token hair
Token ID4190
Feature activation+3.54e+00

Pos logit contributions
 badges+0.073
ows+0.073
 tricks+0.068
 names+0.067
 diapers+0.067
Neg logit contributions
 least-0.096
Little-0.088
ime-0.085
illy-0.082
ately-0.080
Token affection
Token ID17696
Feature activation-1.91e-01

Pos logit contributions
 badges+0.158
ows+0.156
 tricks+0.150
 diapers+0.148
 names+0.147
Neg logit contributions
 least-0.089
Little-0.078
ime-0.073
illy-0.069
Maria-0.066
Tokenately
Token ID1286
Feature activation-6.42e+00

Pos logit contributions
 least+0.005
Little+0.005
Maria+0.004
Em+0.004
ime+0.004
Neg logit contributions
ows-0.008
 badges-0.008
 diapers-0.008
 names-0.007
 teeth-0.007
Token.
Token ID13
Feature activation-9.15e-01

Pos logit contributions
 least+0.139
Little+0.122
ime+0.121
illy+0.111
ately+0.108
Neg logit contributions
 badges-0.296
ows-0.286
 names-0.278
cuts-0.273
orts-0.273
Token
Token ID220
Feature activation-2.12e-01

Pos logit contributions
 least+0.034
ime+0.029
illy+0.027
ately+0.027
Little+0.026
Neg logit contributions
 name-0.030
 names-0.030
orts-0.028
ows-0.028
 badges-0.028
Token
Token ID198
Feature activation-2.10e+00

Pos logit contributions
 least+0.006
Little+0.005
ime+0.005
illy+0.004
ately+0.004
Neg logit contributions
ows-0.009
 badges-0.009
 names-0.009
orts-0.008
 tricks-0.008
Token
Token ID198
Feature activation-2.06e+00

Pos logit contributions
 least+0.090
ately+0.072
ime+0.072
illy+0.070
bul+0.068
Neg logit contributions
orts-0.059
ows-0.057
 name-0.054
 names-0.053
ends-0.052
TokenThe
Token ID464
Feature activation+1.96e-01

Pos logit contributions
 least+0.072
ately+0.057
ime+0.056
illy+0.055
ill+0.048
Neg logit contributions
 badges-0.071
 helmets-0.068
 tricks-0.066
 diapers-0.066
 chips-0.066
Token enjoy
Token ID2883
Feature activation-1.89e-02

Pos logit contributions
 least+0.039
Little+0.032
ime+0.031
ately+0.029
Maria+0.029
Neg logit contributions
ows-0.044
 badges-0.044
orts-0.042
cuts-0.041
 diapers-0.040
Token it
Token ID340
Feature activation-1.46e+00

Pos logit contributions
 least+0.001
Little+0.000
ime+0.000
illy+0.000
Maria+0.000
Neg logit contributions
ows-0.001
 badges-0.001
orts-0.001
 names-0.001
 diapers-0.001
Token until
Token ID1566
Feature activation-2.87e+00

Pos logit contributions
 least+0.049
Little+0.044
ime+0.042
illy+0.041
Maria+0.039
Neg logit contributions
 badges-0.052
ows-0.052
 tricks-0.050
 names-0.049
 diapers-0.049
Token d
Token ID288
Feature activation+9.77e-01

Pos logit contributions
 least+0.100
Little+0.098
ime+0.096
illy+0.092
Maria+0.091
Neg logit contributions
 badges-0.092
 helmets-0.088
 tricks-0.088
 diapers-0.086
 names-0.085
Tokeninn
Token ID3732
Feature activation-1.16e+00

Pos logit contributions
 badges+0.039
ows+0.037
 tricks+0.036
 diapers+0.036
 names+0.035
Neg logit contributions
 least-0.030
ime-0.027
Little-0.027
illy-0.025
ately-0.024
Tokenert
Token ID861
Feature activation-6.40e+00

Pos logit contributions
 least+0.037
Little+0.034
ime+0.031
illy+0.029
Maria+0.029
Neg logit contributions
ows-0.044
 badges-0.044
 tricks-0.041
 names-0.041
 diapers-0.040
Tokenime
Token ID524
Feature activation-1.24e+00

Pos logit contributions
 least+0.173
Little+0.144
Peter+0.135
Mill+0.132
Maria+0.130
Neg logit contributions
ows-0.275
aches-0.247
cks-0.239
ves-0.233
bows-0.232
Token.
Token ID13
Feature activation-8.04e-01

Pos logit contributions
 least+0.041
Little+0.037
ime+0.035
illy+0.034
Maria+0.033
Neg logit contributions
 badges-0.045
ows-0.045
 tricks-0.043
 names-0.042
 diapers-0.042
Token
Token ID220
Feature activation-6.54e-02

Pos logit contributions
 least+0.025
Little+0.022
ime+0.022
illy+0.022
ately+0.021
Neg logit contributions
 names-0.030
 badges-0.029
ows-0.029
 tricks-0.028
 name-0.028
Token
Token ID198
Feature activation-1.86e+00

Pos logit contributions
 least+0.002
Little+0.002
ime+0.001
illy+0.001
ately+0.001
Neg logit contributions
ows-0.003
 badges-0.003
 names-0.003
 tricks-0.003
orts-0.003
Token
Token ID198
Feature activation-1.92e+00

Pos logit contributions
 least+0.066
ately+0.055
illy+0.054
ime+0.052
Little+0.049
Neg logit contributions
ows-0.064
orts-0.063
 tricks-0.063
 names-0.063
 badges-0.060
Token so
Token ID523
Feature activation+1.65e+00

Pos logit contributions
 least+0.058
Little+0.053
ime+0.051
illy+0.049
Maria+0.046
Neg logit contributions
 badges-0.087
ows-0.085
 tricks-0.084
 names-0.082
 diapers-0.081
Token he
Token ID339
Feature activation-1.38e+00

Pos logit contributions
ows+0.069
 badges+0.069
 names+0.065
 diapers+0.065
 tricks+0.064
Neg logit contributions
 least-0.047
Little-0.042
ime-0.039
illy-0.037
ately-0.036
Token stepped
Token ID10764
Feature activation-1.54e+00

Pos logit contributions
 least+0.038
Little+0.034
ime+0.033
illy+0.031
Maria+0.029
Neg logit contributions
 badges-0.058
ows-0.057
 tricks-0.055
 names-0.054
 diapers-0.054
Token forward
Token ID2651
Feature activation+9.37e-01

Pos logit contributions
 least+0.057
ime+0.053
Little+0.052
Maria+0.049
Em+0.049
Neg logit contributions
ows-0.049
 badges-0.047
 tricks-0.045
 names-0.045
 diapers-0.044
Token courage
Token ID11917
Feature activation-1.43e+00

Pos logit contributions
ows+0.029
 tricks+0.026
 names+0.024
 badges+0.024
 name+0.023
Neg logit contributions
Little-0.037
 least-0.037
Em-0.035
ime-0.034
illy-0.034
Tokenously
Token ID3481
Feature activation-6.22e+00

Pos logit contributions
 least+0.043
Little+0.040
ime+0.037
illy+0.037
Maria+0.035
Neg logit contributions
ows-0.056
 badges-0.055
 tricks-0.053
 helmets-0.051
 names-0.051
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
 least+0.170
Little+0.146
ime+0.143
ately+0.135
illy+0.134
Neg logit contributions
 badges-0.260
ows-0.251
 diapers-0.245
 tricks-0.242
 names-0.240
Token
Token ID198
Feature activation-2.11e+00

Pos logit contributions
 least+0.029
Little+0.026
ime+0.025
illy+0.024
ately+0.022
Neg logit contributions
 badges-0.045
ows-0.044
 tricks-0.043
 names-0.042
 diapers-0.042
Token
Token ID198
Feature activation-2.11e+00

Pos logit contributions
 least+0.072
illy+0.055
ime+0.054
ately+0.054
Little+0.052
Neg logit contributions
ows-0.080
 badges-0.076
orts-0.075
 tricks-0.075
 names-0.075
TokenWhen
Token ID2215
Feature activation+1.74e+00

Pos logit contributions
 least+0.051
Little+0.044
ime+0.042
illy+0.039
Maria+0.036
Neg logit contributions
 badges-0.097
ows-0.095
 tricks-0.092
 names-0.091
 diapers-0.091
Token he
Token ID339
Feature activation-6.93e-01

Pos logit contributions
 badges+0.055
 tricks+0.051
 helmets+0.050
 chips+0.049
 names+0.049
Neg logit contributions
 least-0.065
ime-0.060
Little-0.058
illy-0.058
ill-0.056
Token it
Token ID340
Feature activation+9.48e-01

Pos logit contributions
 least+0.007
Little+0.006
ime+0.006
illy+0.006
Maria+0.005
Neg logit contributions
 badges-0.009
ows-0.008
 tricks-0.008
 diapers-0.008
 names-0.008
Token went
Token ID1816
Feature activation-2.59e+00

Pos logit contributions
 badges+0.037
ows+0.036
 tricks+0.035
 names+0.035
 hides+0.034
Neg logit contributions
 least-0.028
Little-0.025
ime-0.025
illy-0.025
ately-0.023
Token on
Token ID319
Feature activation-2.08e-02

Pos logit contributions
 least+0.084
Little+0.076
ime+0.072
illy+0.069
ately+0.066
Neg logit contributions
 badges-0.097
ows-0.095
 tricks-0.091
 names-0.090
 diapers-0.090
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
 least+0.001
ime+0.001
Little+0.001
illy+0.001
ately+0.001
Neg logit contributions
 badges-0.001
 tricks-0.001
 helmets-0.001
 homework-0.001
 labels-0.001
Token w
Token ID266
Feature activation+7.90e-01

Pos logit contributions
 least+0.037
ime+0.036
Little+0.035
illy+0.034
ately+0.034
Neg logit contributions
 badges-0.035
 tricks-0.034
 helmets-0.033
 names-0.033
ows-0.032
Tokenett
Token ID3087
Feature activation-5.98e+00

Pos logit contributions
 badges+0.021
ows+0.021
 tricks+0.020
 names+0.019
 diapers+0.019
Neg logit contributions
 least-0.034
Little-0.032
Maria-0.029
ime-0.029
Em-0.029
Tokenest
Token ID395
Feature activation-2.08e+00

Pos logit contributions
Little+0.174
 least+0.174
Maria+0.162
Em+0.158
enny+0.156
Neg logit contributions
 tricks-0.221
 badges-0.209
 names-0.208
ows-0.205
bones-0.200
Token of
Token ID286
Feature activation-5.18e-01

Pos logit contributions
 least+0.064
Little+0.059
Maria+0.055
Em+0.052
illy+0.052
Neg logit contributions
 tricks-0.083
 badges-0.083
 names-0.078
 diapers-0.076
 helmets-0.076
Token adventures
Token ID17545
Feature activation-1.50e+00

Pos logit contributions
 least+0.018
Little+0.016
ime+0.016
illy+0.015
ately+0.014
Neg logit contributions
 badges-0.018
ows-0.018
 tricks-0.017
 names-0.017
 diapers-0.017
Token.
Token ID13
Feature activation-1.32e+00

Pos logit contributions
 least+0.048
Little+0.043
ime+0.041
illy+0.040
Maria+0.038
Neg logit contributions
 badges-0.056
ows-0.055
 tricks-0.053
 names-0.052
 diapers-0.052
Token After
Token ID2293
Feature activation-4.70e-02

Pos logit contributions
 least+0.046
Little+0.043
ime+0.041
illy+0.039
ately+0.038
Neg logit contributions
 badges-0.046
ows-0.044
 tricks-0.043
 diapers-0.041
 names-0.041
Token!
Token ID0
Feature activation-2.00e+00

Pos logit contributions
 least+0.001
Little+0.001
ime+0.001
 Little+0.001
 Peter+0.001
Neg logit contributions
 badges-0.004
ows-0.004
orts-0.004
 diapers-0.003
irms-0.003
Token I
Token ID314
Feature activation-2.07e+00

Pos logit contributions
 least+0.067
Little+0.061
ime+0.058
illy+0.056
ately+0.054
Neg logit contributions
 badges-0.072
ows-0.070
 tricks-0.068
 names-0.067
 diapers-0.066
Token am
Token ID716
Feature activation+5.82e-01

Pos logit contributions
 least+0.062
Little+0.055
ime+0.052
illy+0.050
ately+0.047
Neg logit contributions
 badges-0.082
ows-0.080
 diapers-0.077
 tricks-0.077
 names-0.076
Token the
Token ID262
Feature activation-6.86e-01

Pos logit contributions
 badges+0.024
ows+0.024
 diapers+0.022
 names+0.022
 tricks+0.022
Neg logit contributions
 least-0.018
Little-0.015
ime-0.014
illy-0.014
Maria-0.013
Token fastest
Token ID14162
Feature activation+8.26e-02

Pos logit contributions
 least+0.022
Little+0.021
ime+0.020
illy+0.019
ately+0.019
Neg logit contributions
 badges-0.025
 tricks-0.024
ows-0.023
 names-0.023
 diapers-0.023
Token rusher
Token ID47608
Feature activation-5.97e+00

Pos logit contributions
 badges+0.003
 tricks+0.003
ows+0.003
 names+0.003
 diapers+0.003
Neg logit contributions
 least-0.003
Little-0.003
illy-0.002
ime-0.002
Maria-0.002
Token!"
Token ID2474
Feature activation+1.29e+00

Pos logit contributions
 least+0.189
Little+0.170
ime+0.163
illy+0.156
ately+0.148
Neg logit contributions
 badges-0.225
ows-0.221
 tricks-0.211
 names-0.209
 diapers-0.209
Token<|endoftext|>
Token ID50256
Feature activation+3.07e+00

Pos logit contributions
 badges+0.051
ows+0.050
 tricks+0.048
 names+0.048
 diapers+0.047
Neg logit contributions
 least-0.039
Little-0.033
ime-0.033
illy-0.031
ately-0.029
TokenOnce
Token ID7454
Feature activation+2.93e+00

Pos logit contributions
ows+0.125
 badges+0.123
 names+0.121
 tricks+0.118
 diapers+0.116
Neg logit contributions
 least-0.089
Little-0.072
illy-0.070
ime-0.068
ately-0.068
Token there
Token ID612
Feature activation+8.26e-01

Pos logit contributions
ows+0.112
 names+0.104
 badges+0.104
orts+0.103
 tricks+0.101
Neg logit contributions
 least-0.090
Little-0.078
ime-0.070
illy-0.069
ately-0.068
Token was
Token ID373
Feature activation-4.07e-01

Pos logit contributions
 names+0.026
ows+0.025
 name+0.025
 tricks+0.024
 badges+0.024
Neg logit contributions
 least-0.027
illy-0.024
Little-0.024
ime-0.024
ately-0.023
Token who
Token ID508
Feature activation+9.42e-01

Pos logit contributions
 least+0.084
Little+0.076
ime+0.073
illy+0.070
ately+0.067
Neg logit contributions
 badges-0.085
ows-0.083
 tricks-0.079
 names-0.078
 diapers-0.078
Token could
Token ID714
Feature activation-2.35e+00

Pos logit contributions
 badges+0.039
ows+0.039
 tricks+0.037
 names+0.037
 diapers+0.037
Neg logit contributions
 least-0.026
Little-0.023
ime-0.022
illy-0.021
Maria-0.019
Token get
Token ID651
Feature activation+1.76e-01

Pos logit contributions
 least+0.082
Little+0.072
ime+0.069
illy+0.065
ill+0.064
Neg logit contributions
 badges-0.085
ows-0.082
 diapers-0.077
 names-0.076
cuts-0.076
Token the
Token ID262
Feature activation-1.97e+00

Pos logit contributions
ows+0.008
 badges+0.007
 facts+0.007
cuts+0.007
 meanings+0.007
Neg logit contributions
 least-0.005
ime-0.004
Little-0.004
ful-0.004
 Little-0.003
Token w
Token ID266
Feature activation+3.16e-01

Pos logit contributions
 least+0.064
Little+0.054
ime+0.050
illy+0.048
 3+0.048
Neg logit contributions
ows-0.075
 badges-0.075
cks-0.072
orts-0.071
 tricks-0.069
Tokenett
Token ID3087
Feature activation-5.97e+00

Pos logit contributions
 badges+0.007
ows+0.006
 names+0.006
 tricks+0.006
 diapers+0.006
Neg logit contributions
 least-0.015
Little-0.014
ime-0.014
illy-0.014
ately-0.013
Tokenest
Token ID395
Feature activation-2.31e+00

Pos logit contributions
 least+0.204
Little+0.185
ime+0.177
illy+0.171
ately+0.163
Neg logit contributions
 badges-0.211
ows-0.207
 tricks-0.198
 names-0.195
 diapers-0.195
Token and
Token ID290
Feature activation-1.56e+00

Pos logit contributions
 least+0.068
Little+0.059
ime+0.058
illy+0.054
ately+0.052
Neg logit contributions
 badges-0.093
ows-0.091
 tricks-0.087
 names-0.087
 diapers-0.086
Token who
Token ID508
Feature activation+8.04e-01

Pos logit contributions
 least+0.053
Little+0.048
ime+0.044
 Little+0.042
 3+0.042
Neg logit contributions
ows-0.057
 badges-0.054
orts-0.053
cks-0.050
cuts-0.050
Token could
Token ID714
Feature activation-2.37e+00

Pos logit contributions
 badges+0.034
ows+0.034
 tricks+0.033
 names+0.032
 diapers+0.032
Neg logit contributions
 least-0.022
Little-0.019
ime-0.018
illy-0.017
ately-0.016
Token make
Token ID787
Feature activation-8.76e-01

Pos logit contributions
 least+0.081
Little+0.070
ime+0.067
illy+0.062
ill+0.062
Neg logit contributions
 badges-0.088
ows-0.085
 diapers-0.081
cuts-0.080
 facts-0.079
Token work
Token ID670
Feature activation-8.16e-01

Pos logit contributions
 least+0.020
Little+0.018
ime+0.018
illy+0.017
ately+0.016
Neg logit contributions
 badges-0.016
ows-0.015
 tricks-0.015
 names-0.015
 labels-0.015
Token,
Token ID11
Feature activation-1.78e+00

Pos logit contributions
 least+0.024
Little+0.022
ime+0.021
illy+0.021
Maria+0.019
Neg logit contributions
ows-0.033
 badges-0.032
 tricks-0.031
 labels-0.030
 helmets-0.030
Token carefully
Token ID7773
Feature activation-1.78e+00

Pos logit contributions
 least+0.048
Little+0.044
ime+0.043
illy+0.041
ately+0.037
Neg logit contributions
 badges-0.076
ows-0.074
 tricks-0.071
 labels-0.070
 names-0.069
Token and
Token ID290
Feature activation-7.75e-01

Pos logit contributions
 least+0.056
Little+0.050
illy+0.047
ime+0.046
Maria+0.044
Neg logit contributions
 badges-0.071
ows-0.068
 tricks-0.066
 labels-0.065
 names-0.064
Token delic
Token ID8675
Feature activation-1.11e-01

Pos logit contributions
 least+0.022
Little+0.021
ime+0.020
illy+0.019
Maria+0.017
Neg logit contributions
 badges-0.031
ows-0.030
 tricks-0.029
 labels-0.029
 names-0.028
Tokenately
Token ID1286
Feature activation-5.95e+00

Pos logit contributions
Little+0.002
 least+0.002
Em+0.001
Maria+0.001
ime+0.001
Neg logit contributions
ows-0.006
 badges-0.006
 names-0.006
 tricks-0.006
 diapers-0.006
Token repairing
Token ID39005
Feature activation-1.64e-01

Pos logit contributions
 least+0.186
Little+0.165
ime+0.154
illy+0.152
Maria+0.145
Neg logit contributions
 badges-0.231
ows-0.224
 tricks-0.218
 diapers-0.211
 names-0.211
Token the
Token ID262
Feature activation-9.50e-01

Pos logit contributions
 least+0.005
Little+0.005
ime+0.004
illy+0.004
ately+0.004
Neg logit contributions
 badges-0.006
ows-0.006
 tricks-0.006
 names-0.006
 diapers-0.006
Token butterfly
Token ID35113
Feature activation-2.27e+00

Pos logit contributions
 least+0.030
Little+0.028
ime+0.026
illy+0.025
Maria+0.024
Neg logit contributions
 badges-0.036
ows-0.035
 tricks-0.034
 names-0.033
 diapers-0.033
Token's
Token ID338
Feature activation-1.81e+00

Pos logit contributions
 least+0.071
Little+0.064
ime+0.061
illy+0.058
ately+0.055
Neg logit contributions
 badges-0.087
ows-0.085
 tricks-0.082
 names-0.081
 diapers-0.081
Token wings
Token ID12098
Feature activation-1.05e+00

Pos logit contributions
 least+0.065
Little+0.059
ime+0.057
illy+0.055
ately+0.053
Neg logit contributions
 badges-0.061
ows-0.059
 tricks-0.056
 diapers-0.055
 names-0.055
Token amazed
Token ID24562
Feature activation-1.44e+00

Pos logit contributions
 least+0.050
Little+0.043
ime+0.041
illy+0.038
Maria+0.036
Neg logit contributions
 badges-0.088
ows-0.086
 tricks-0.083
 diapers-0.082
 names-0.082
Token by
Token ID416
Feature activation+2.60e-01

Pos logit contributions
 least+0.042
Little+0.038
ime+0.035
illy+0.034
Maria+0.032
Neg logit contributions
 badges-0.058
ows-0.057
 tricks-0.056
 names-0.055
 diapers-0.054
Token how
Token ID703
Feature activation+2.68e+00

Pos logit contributions
 badges+0.010
ows+0.010
 tricks+0.010
 diapers+0.010
 names+0.010
Neg logit contributions
 least-0.008
Little-0.007
ime-0.007
illy-0.006
Maria-0.006
Token good
Token ID922
Feature activation-3.88e-01

Pos logit contributions
 badges+0.106
ows+0.103
 diapers+0.099
 tricks+0.096
orts+0.095
Neg logit contributions
 least-0.079
Little-0.078
ime-0.075
Maria-0.069
illy-0.069
Token the
Token ID262
Feature activation-2.46e+00

Pos logit contributions
 least+0.011
Little+0.010
illy+0.009
ime+0.009
 Little+0.009
Neg logit contributions
ows-0.016
 badges-0.016
orts-0.015
 gag-0.015
cuts-0.014
Token mother
Token ID2802
Feature activation-5.94e+00

Pos logit contributions
 least+0.071
Little+0.064
ime+0.060
illy+0.058
Maria+0.053
Neg logit contributions
 badges-0.101
ows-0.101
 diapers-0.094
 tricks-0.094
orts-0.092
Token kept
Token ID4030
Feature activation-3.31e+00

Pos logit contributions
 least+0.151
Little+0.132
ime+0.125
illy+0.118
ately+0.110
Neg logit contributions
 badges-0.262
ows-0.257
 tricks-0.249
 names-0.246
 diapers-0.245
Token it
Token ID340
Feature activation-2.47e+00

Pos logit contributions
 least+0.097
Little+0.085
ime+0.082
illy+0.079
ately+0.074
Neg logit contributions
ows-0.134
 badges-0.134
 tricks-0.125
 diapers-0.124
 names-0.123
Token.
Token ID13
Feature activation-1.28e+00

Pos logit contributions
 least+0.081
Little+0.077
ime+0.072
illy+0.069
Maria+0.067
Neg logit contributions
ows-0.089
 badges-0.087
 tricks-0.084
 names-0.083
 diapers-0.081
Token
Token ID220
Feature activation-5.48e-01

Pos logit contributions
 least+0.042
Little+0.037
ime+0.037
illy+0.035
ately+0.033
Neg logit contributions
 badges-0.046
ows-0.046
 names-0.044
 tricks-0.043
 diapers-0.043
Token
Token ID198
Feature activation-2.74e+00

Pos logit contributions
 least+0.012
Little+0.011
ime+0.010
illy+0.009
ately+0.009
Neg logit contributions
 badges-0.026
ows-0.025
 tricks-0.024
 names-0.024
 diapers-0.024
Token knowing
Token ID6970
Feature activation-1.88e+00

Pos logit contributions
 least+0.058
Little+0.052
ime+0.050
illy+0.047
ately+0.045
Neg logit contributions
 badges-0.081
ows-0.080
 tricks-0.077
 names-0.076
 diapers-0.076
Token that
Token ID326
Feature activation-1.69e+00

Pos logit contributions
 least+0.069
Little+0.064
ime+0.063
illy+0.057
Maria+0.057
Neg logit contributions
 badges-0.060
 tricks-0.058
ows-0.058
 names-0.056
 diapers-0.055
Token even
Token ID772
Feature activation-2.95e+00

Pos logit contributions
 least+0.049
Little+0.044
ime+0.041
illy+0.039
Maria+0.037
Neg logit contributions
 badges-0.069
ows-0.068
 tricks-0.064
 diapers-0.064
 names-0.063
Token the
Token ID262
Feature activation-9.68e-01

Pos logit contributions
 least+0.089
Little+0.080
ime+0.076
illy+0.073
ately+0.069
Neg logit contributions
 badges-0.117
ows-0.114
 tricks-0.110
 names-0.108
 diapers-0.108
Token t
Token ID256
Feature activation-2.02e+00

Pos logit contributions
 least+0.028
Little+0.025
ime+0.024
illy+0.023
ately+0.022
Neg logit contributions
 badges-0.039
ows-0.039
 tricks-0.037
 diapers-0.036
 names-0.036
Tokenini
Token ID5362
Feature activation-5.93e+00

Pos logit contributions
 least+0.070
Little+0.064
 Little+0.058
 mid+0.055
Em+0.055
Neg logit contributions
ows-0.067
 badges-0.063
bows-0.062
 names-0.062
ages-0.062
Tokenest
Token ID395
Feature activation-1.86e+00

Pos logit contributions
 least+0.186
Little+0.171
ime+0.161
Em+0.153
ately+0.152
Neg logit contributions
ows-0.206
 tricks-0.202
 names-0.201
 badges-0.198
bows-0.194
Token and
Token ID290
Feature activation-1.95e+00

Pos logit contributions
 least+0.060
Little+0.055
ime+0.051
illy+0.049
Maria+0.048
Neg logit contributions
 badges-0.068
ows-0.066
 tricks-0.066
 names-0.065
 diapers-0.064
Token darkest
Token ID35995
Feature activation-3.16e+00

Pos logit contributions
 least+0.069
Little+0.061
ime+0.057
illy+0.055
Maria+0.053
Neg logit contributions
 badges-0.069
ows-0.069
orts-0.064
 tricks-0.064
 diapers-0.063
Token of
Token ID286
Feature activation-1.12e+00

Pos logit contributions
 least+0.093
Little+0.085
illy+0.075
Em+0.073
Maria+0.073
Neg logit contributions
ows-0.123
 tricks-0.123
 badges-0.121
 diapers-0.118
 names-0.118
Token gardens
Token ID25476
Feature activation-3.26e-01

Pos logit contributions
 least+0.036
Little+0.034
ime+0.031
illy+0.030
ill+0.029
Neg logit contributions
 badges-0.041
 tricks-0.040
 names-0.039
ows-0.039
 diapers-0.039
Token to
Token ID284
Feature activation-8.84e-01

Pos logit contributions
 least+0.018
Little+0.016
ime+0.015
illy+0.014
ately+0.013
Neg logit contributions
 badges-0.026
ows-0.025
 tricks-0.025
 names-0.024
 diapers-0.024
Token swim
Token ID9422
Feature activation+2.53e+00

Pos logit contributions
 least+0.035
Little+0.033
illy+0.033
ime+0.032
ately+0.032
Neg logit contributions
 badges-0.025
 tricks-0.024
 names-0.024
ows-0.023
 diapers-0.022
Token around
Token ID1088
Feature activation-6.74e-01

Pos logit contributions
 badges+0.103
ows+0.097
 diapers+0.096
cuts+0.094
 labels+0.093
Neg logit contributions
 least-0.074
Little-0.065
ime-0.063
illy-0.058
ill-0.057
Token the
Token ID262
Feature activation-1.23e+00

Pos logit contributions
 least+0.025
Little+0.024
illy+0.023
ime+0.022
Em+0.022
Neg logit contributions
 tricks-0.022
 badges-0.020
 names-0.020
ows-0.020
 labels-0.019
Token p
Token ID279
Feature activation-2.04e+00

Pos logit contributions
 least+0.038
Little+0.035
ately+0.033
Maria+0.033
illy+0.033
Neg logit contributions
 badges-0.046
 tricks-0.045
 names-0.044
ows-0.044
 labels-0.042
Tokenail
Token ID603
Feature activation-5.92e+00

Pos logit contributions
 least+0.082
Little+0.074
ime+0.073
illy+0.070
ill+0.067
Neg logit contributions
 badges-0.060
ows-0.057
 diapers-0.056
 tricks-0.056
 names-0.056
Token.
Token ID13
Feature activation-1.10e+00

Pos logit contributions
 least+0.215
Little+0.206
illy+0.189
Maria+0.187
Em+0.187
Neg logit contributions
ows-0.192
 tricks-0.182
 badges-0.175
 names-0.169
 chips-0.167
Token The
Token ID383
Feature activation-2.04e-01

Pos logit contributions
 least+0.039
Little+0.035
ime+0.034
illy+0.032
Maria+0.031
Neg logit contributions
 badges-0.038
ows-0.037
 tricks-0.036
 diapers-0.035
 names-0.035
Token fisherman
Token ID48750
Feature activation+6.88e-01

Pos logit contributions
 least+0.007
Little+0.006
ime+0.006
illy+0.006
Maria+0.006
Neg logit contributions
 badges-0.007
ows-0.007
 tricks-0.007
 names-0.007
 diapers-0.007
Token was
Token ID373
Feature activation-1.16e+00

Pos logit contributions
 tricks+0.024
 badges+0.023
ows+0.023
 names+0.022
 labels+0.021
Neg logit contributions
 least-0.022
Little-0.021
illy-0.021
ime-0.020
Em-0.019
Token so
Token ID523
Feature activation+1.97e+00

Pos logit contributions
 least+0.030
Little+0.028
ime+0.027
illy+0.026
ately+0.025
Neg logit contributions
 badges-0.048
ows-0.048
 tricks-0.047
 names-0.046
 diapers-0.045
Token hopped
Token ID45230
Feature activation-1.13e+00

Pos logit contributions
 least+0.016
Little+0.015
illy+0.014
ime+0.014
Em+0.013
Neg logit contributions
ows-0.018
 badges-0.018
 tricks-0.017
aches-0.016
 helmets-0.016
Token back
Token ID736
Feature activation-7.62e-01

Pos logit contributions
 least+0.039
Little+0.036
ime+0.034
illy+0.033
ately+0.032
Neg logit contributions
 badges-0.040
ows-0.039
 tricks-0.037
 names-0.037
 diapers-0.036
Token onto
Token ID4291
Feature activation-1.72e+00

Pos logit contributions
 least+0.022
Little+0.020
ime+0.019
illy+0.018
Maria+0.017
Neg logit contributions
 badges-0.031
ows-0.030
 tricks-0.029
 names-0.029
 diapers-0.029
Token the
Token ID262
Feature activation-1.82e+00

Pos logit contributions
 least+0.059
Little+0.057
ime+0.056
illy+0.054
enny+0.054
Neg logit contributions
 badges-0.057
 tricks-0.055
 names-0.054
 diapers-0.053
 labels-0.053
Token windows
Token ID9168
Feature activation-1.82e+00

Pos logit contributions
 least+0.064
ime+0.061
ill+0.059
Little+0.058
illy+0.058
Neg logit contributions
 badges-0.062
 tricks-0.059
 helmets-0.059
 diapers-0.058
ows-0.058
Tokenill
Token ID359
Feature activation-5.90e+00

Pos logit contributions
Little+0.069
 least+0.067
Em+0.063
Quick+0.060
illy+0.059
Neg logit contributions
ows-0.063
bows-0.049
 names-0.049
 badges-0.049
 tricks-0.048
Token.
Token ID13
Feature activation-1.61e+00

Pos logit contributions
 least+0.221
Little+0.202
illy+0.182
Maria+0.181
ime+0.178
Neg logit contributions
ows-0.195
 badges-0.178
 tricks-0.178
 names-0.177
 diapers-0.168
Token The
Token ID383
Feature activation-2.69e-01

Pos logit contributions
 least+0.072
Little+0.067
ime+0.066
illy+0.064
ately+0.061
Neg logit contributions
ows-0.038
 names-0.037
 badges-0.036
orts-0.035
 tricks-0.034
Token pr
Token ID778
Feature activation+1.33e+00

Pos logit contributions
 least+0.009
Little+0.009
ime+0.009
illy+0.008
Em+0.008
Neg logit contributions
 badges-0.009
 names-0.009
 tricks-0.009
 labels-0.008
ows-0.008
Tokenune
Token ID1726
Feature activation+4.76e-02

Pos logit contributions
ows+0.042
 badges+0.039
 names+0.037
 labels+0.036
orts+0.036
Neg logit contributions
 least-0.051
Little-0.050
Em-0.046
ime-0.045
Peter-0.044
Token whispered
Token ID25029
Feature activation-1.03e+00

Pos logit contributions
ows+0.002
 badges+0.002
 tricks+0.002
aches+0.002
 helmets+0.002
Neg logit contributions
 least-0.002
Little-0.001
illy-0.001
ime-0.001
Maria-0.001
Token a
Token ID257
Feature activation+7.81e-01

Pos logit contributions
 badges+0.000
ows+0.000
 tricks+0.000
 names+0.000
 diapers+0.000
Neg logit contributions
 least-0.000
Little-0.000
ime-0.000
illy-0.000
ately-0.000
Token little
Token ID1310
Feature activation-3.00e+00

Pos logit contributions
 badges+0.030
 tricks+0.028
 names+0.027
 chips+0.027
ows+0.027
Neg logit contributions
 least-0.025
Little-0.022
illy-0.021
ately-0.020
ime-0.020
Token girl
Token ID2576
Feature activation-2.42e+00

Pos logit contributions
 least+0.085
Little+0.076
ime+0.071
illy+0.069
Maria+0.066
Neg logit contributions
 badges-0.124
ows-0.118
 tricks-0.117
 names-0.115
 diapers-0.114
Token named
Token ID3706
Feature activation+1.74e+00

Pos logit contributions
 least+0.073
Little+0.065
ime+0.061
illy+0.059
ately+0.056
Neg logit contributions
 badges-0.094
ows-0.092
 tricks-0.089
 names-0.088
 diapers-0.087
Token G
Token ID402
Feature activation-1.52e+00

Pos logit contributions
 badges+0.069
ows+0.068
 tricks+0.066
 names+0.063
 diapers+0.063
Neg logit contributions
 least-0.052
Little-0.048
ime-0.045
illy-0.045
Maria-0.042
Tokenert
Token ID861
Feature activation-5.89e+00

Pos logit contributions
 least+0.041
Little+0.037
Maria+0.033
ime+0.033
 3+0.031
Neg logit contributions
ows-0.063
 badges-0.060
 tricks-0.058
orts-0.057
 names-0.057
Tokenie
Token ID494
Feature activation-1.57e+00

Pos logit contributions
 least+0.178
Little+0.149
Maria+0.133
Peter+0.130
illy+0.128
Neg logit contributions
ows-0.223
aches-0.208
 tricks-0.203
bones-0.201
 badges-0.198
Token,
Token ID11
Feature activation+2.73e-01

Pos logit contributions
 least+0.036
Little+0.031
ime+0.030
illy+0.028
ately+0.026
Neg logit contributions
 badges-0.073
ows-0.071
 tricks-0.069
 names-0.068
 diapers-0.068
Token stopped
Token ID5025
Feature activation-1.06e+00

Pos logit contributions
 badges+0.011
ows+0.010
 names+0.010
 tricks+0.010
 diapers+0.010
Neg logit contributions
 least-0.008
Little-0.007
ime-0.007
illy-0.007
ately-0.006
Token by
Token ID416
Feature activation+6.61e-01

Pos logit contributions
 least+0.034
Little+0.032
ime+0.029
illy+0.029
Maria+0.028
Neg logit contributions
 badges-0.038
 tricks-0.037
ows-0.036
 names-0.035
 diapers-0.035
Token to
Token ID284
Feature activation-6.46e-01

Pos logit contributions
 badges+0.024
 tricks+0.023
ows+0.023
 names+0.023
 diapers+0.023
Neg logit contributions
 least-0.021
Little-0.019
ime-0.019
illy-0.018
Maria-0.017
Tokenque
Token ID4188
Feature activation+1.97e+00

Pos logit contributions
 least+0.058
Little+0.052
Maria+0.048
ime+0.046
Daddy+0.045
Neg logit contributions
ows-0.083
 badges-0.079
 tricks-0.076
 names-0.075
orts-0.074
Tokenaky
Token ID15492
Feature activation-6.60e-01

Pos logit contributions
 badges+0.077
ows+0.077
 tricks+0.073
 names+0.072
 diapers+0.071
Neg logit contributions
 least-0.060
Little-0.055
ime-0.049
illy-0.049
Maria-0.046
Token in
Token ID287
Feature activation+1.06e+00

Pos logit contributions
 least+0.018
Little+0.016
ime+0.016
illy+0.014
ill+0.014
Neg logit contributions
 badges-0.027
ows-0.026
 tricks-0.025
orts-0.025
cuts-0.025
Token its
Token ID663
Feature activation+1.23e+00

Pos logit contributions
 badges+0.039
ows+0.037
 tricks+0.036
 names+0.036
 diapers+0.036
Neg logit contributions
 least-0.036
Little-0.032
ime-0.031
illy-0.031
ately-0.029
Token sharp
Token ID7786
Feature activation-1.11e+00

Pos logit contributions
 badges+0.042
ows+0.040
 tricks+0.039
 names+0.039
 diapers+0.037
Neg logit contributions
 least-0.044
Little-0.041
illy-0.039
ime-0.039
Em-0.037
Token tal
Token ID3305
Feature activation-5.88e+00

Pos logit contributions
 least+0.046
Little+0.043
illy+0.039
ime+0.039
Em+0.038
Neg logit contributions
 badges-0.033
ows-0.032
 tricks-0.031
 diapers-0.030
 names-0.030
Tokenons
Token ID684
Feature activation-1.03e+00

Pos logit contributions
 least+0.219
Little+0.188
 3+0.173
ime+0.172
ately+0.171
Neg logit contributions
 badges-0.196
ows-0.190
 tricks-0.187
cks-0.186
aches-0.179
Token.
Token ID13
Feature activation-1.45e+00

Pos logit contributions
 least+0.032
Little+0.029
ime+0.028
illy+0.026
Maria+0.025
Neg logit contributions
 badges-0.039
ows-0.039
 tricks-0.037
 names-0.037
 diapers-0.036
Token
Token ID220
Feature activation-7.95e-01

Pos logit contributions
 least+0.039
Little+0.035
ime+0.032
illy+0.031
ately+0.030
Neg logit contributions
 badges-0.062
ows-0.060
 tricks-0.059
 diapers-0.058
 homework-0.058
Token
Token ID198
Feature activation-2.78e+00

Pos logit contributions
 least+0.019
Little+0.016
ime+0.015
illy+0.014
ately+0.013
Neg logit contributions
ows-0.036
 badges-0.036
 tricks-0.035
 names-0.035
 diapers-0.034
Token
Token ID198
Feature activation-2.67e+00

Pos logit contributions
 least+0.069
Little+0.057
ime+0.055
illy+0.052
ately+0.049
Neg logit contributions
 badges-0.125
ows-0.124
 tricks-0.120
 names-0.119
orts-0.118
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
Little+0.017
enny+0.017
Em+0.017
ime+0.016
Maria+0.015
Neg logit contributions
 tricks-0.012
 labels-0.012
 names-0.012
 homework-0.012
 diapers-0.012
Token top
Token ID1353
Feature activation-2.63e+00

Pos logit contributions
Em+0.046
enny+0.045
ime+0.044
Little+0.044
Maria+0.043
Neg logit contributions
 names-0.046
 tricks-0.044
 chips-0.042
 name-0.042
 diapers-0.041
Token of
Token ID286
Feature activation-7.32e-01

Pos logit contributions
 least+0.095
Little+0.093
illy+0.092
Peter+0.090
Em+0.090
Neg logit contributions
ows-0.078
 tricks-0.074
 chips-0.070
bones-0.068
ashes-0.067
Token the
Token ID262
Feature activation-1.66e+00

Pos logit contributions
enny+0.035
Em+0.032
ime+0.030
illy+0.029
enna+0.029
Neg logit contributions
 helmets-0.017
 badges-0.016
 chips-0.016
 labels-0.016
 names-0.016
Token anth
Token ID26794
Feature activation-3.28e+00

Pos logit contributions
Em+0.057
enny+0.057
enna+0.054
bul+0.054
Peter+0.054
Neg logit contributions
 chips-0.051
 names-0.050
ashes-0.049
 tricks-0.049
 diapers-0.048
Tokenill
Token ID359
Feature activation-5.86e+00

Pos logit contributions
 least+0.066
Little+0.066
Em+0.051
Peter+0.051
ime+0.046
Neg logit contributions
ows-0.155
ashes-0.142
bones-0.140
bows-0.137
oodle-0.137
Token.
Token ID13
Feature activation-1.55e+00

Pos logit contributions
 least+0.222
Little+0.208
Em+0.193
Peter+0.193
Maria+0.192
Neg logit contributions
ows-0.176
 tricks-0.169
 names-0.156
aches-0.156
 chips-0.155
Token But
Token ID887
Feature activation-2.65e+00

Pos logit contributions
 least+0.060
Little+0.055
ime+0.054
illy+0.052
ately+0.049
Neg logit contributions
 badges-0.047
ows-0.047
 names-0.045
 tricks-0.044
 diapers-0.044
Token the
Token ID262
Feature activation+7.57e-02

Pos logit contributions
ime+0.086
Little+0.082
illy+0.081
enny+0.081
 least+0.079
Neg logit contributions
 tricks-0.084
 hides-0.081
 helmets-0.080
 badges-0.079
ows-0.079
Token ant
Token ID1885
Feature activation-1.79e+00

Pos logit contributions
 names+0.003
 tricks+0.003
 chips+0.003
 badges+0.003
 diapers+0.003
Neg logit contributions
 least-0.002
Em-0.002
ime-0.002
enny-0.002
Little-0.002
Token wouldn
Token ID3636
Feature activation-1.36e+00

Pos logit contributions
 least+0.056
Little+0.050
illy+0.049
ime+0.048
Maria+0.045
Neg logit contributions
ows-0.064
 tricks-0.064
 badges-0.062
aches-0.059
 hides-0.059
Token There
Token ID1318
Feature activation-8.29e-01

Pos logit contributions
 badges+0.059
 tricks+0.055
ows+0.055
aches+0.053
 labels+0.052
Neg logit contributions
 least-0.045
Little-0.043
ime-0.039
Maria-0.038
 Little-0.038
Token were
Token ID547
Feature activation-1.45e+00

Pos logit contributions
 least+0.024
Little+0.021
ime+0.020
illy+0.019
Em+0.018
Neg logit contributions
ows-0.034
 badges-0.033
 names-0.032
 tricks-0.032
 labels-0.031
Token many
Token ID867
Feature activation-4.43e-01

Pos logit contributions
 least+0.047
Little+0.041
ime+0.039
Maria+0.037
illy+0.037
Neg logit contributions
 badges-0.052
ows-0.051
orts-0.050
 tricks-0.048
cuts-0.048
Token people
Token ID661
Feature activation-8.59e-01

Pos logit contributions
 least+0.016
Little+0.015
ime+0.015
illy+0.014
Maria+0.013
Neg logit contributions
ows-0.014
 badges-0.013
orts-0.013
 gag-0.013
 names-0.013
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
 least+0.023
Little+0.020
ime+0.020
illy+0.018
ately+0.017
Neg logit contributions
 badges-0.037
ows-0.035
 names-0.035
 diapers-0.035
 tricks-0.035
Token clown
Token ID25573
Feature activation+4.86e+00

Pos logit contributions
ows+0.048
orts+0.045
 badges+0.044
cks+0.042
cuts+0.042
Neg logit contributions
 least-0.053
Little-0.049
ime-0.047
Maria-0.044
illy-0.044
Tokens
Token ID82
Feature activation+2.00e+00

Pos logit contributions
 badges+0.162
ows+0.156
 tricks+0.154
 diapers+0.154
 names+0.151
Neg logit contributions
 least-0.170
Little-0.156
ime-0.153
illy-0.144
ately-0.142
Token and
Token ID290
Feature activation+2.08e+00

Pos logit contributions
 badges+0.088
ows+0.085
 tricks+0.083
 diapers+0.082
 names+0.082
Neg logit contributions
 least-0.051
Little-0.044
ime-0.042
illy-0.039
ately-0.037
Token animals
Token ID4695
Feature activation+3.17e+00

Pos logit contributions
ows+0.075
 badges+0.069
orts+0.069
cuts+0.067
 tricks+0.065
Neg logit contributions
 least-0.072
Little-0.062
ime-0.060
Maria-0.057
illy-0.056
Token.
Token ID13
Feature activation+2.18e+00

Pos logit contributions
 badges+0.136
ows+0.132
 diapers+0.129
orts+0.128
 tricks+0.128
Neg logit contributions
 least-0.083
Little-0.069
ime-0.069
illy-0.061
ately-0.061
Token Anna
Token ID11735
Feature activation+2.09e+00

Pos logit contributions
 badges+0.079
aches+0.076
 tricks+0.073
cuts+0.072
ows+0.072
Neg logit contributions
 least-0.069
Little-0.065
 Little-0.063
ill-0.062
Maria-0.061
Token can
Token ID460
Feature activation-6.95e-01

Pos logit contributions
 badges+0.016
ows+0.015
 diapers+0.015
 tricks+0.015
 facts+0.015
Neg logit contributions
 least-0.013
Little-0.011
ime-0.010
ately-0.009
illy-0.009
Token't
Token ID470
Feature activation-3.04e-01

Pos logit contributions
 least+0.020
Little+0.017
ime+0.016
illy+0.014
ately+0.014
Neg logit contributions
 badges-0.029
ows-0.029
 diapers-0.028
 facts-0.027
 tricks-0.027
Token.
Token ID13
Feature activation-1.73e-01

Pos logit contributions
 least+0.011
Little+0.010
ime+0.009
illy+0.009
Maria+0.009
Neg logit contributions
 badges-0.011
ows-0.010
 tricks-0.010
 names-0.010
 diapers-0.010
Token You
Token ID921
Feature activation+7.20e-01

Pos logit contributions
 least+0.005
Little+0.004
ime+0.004
 Little+0.004
ately+0.004
Neg logit contributions
 badges-0.007
ows-0.007
 tricks-0.007
aches-0.007
 chips-0.007
Token are
Token ID389
Feature activation+7.53e-01

Pos logit contributions
 badges+0.025
ows+0.024
 tricks+0.023
 diapers+0.023
 facts+0.023
Neg logit contributions
 least-0.026
Little-0.022
ime-0.022
ately-0.020
illy-0.020
Token too
Token ID1165
Feature activation+5.23e+00

Pos logit contributions
ows+0.033
 badges+0.032
orts+0.031
bows+0.031
 facts+0.030
Neg logit contributions
 least-0.023
 nowhere-0.016
 3-0.015
 mid-0.015
ime-0.014
Token little
Token ID1310
Feature activation-1.84e+00

Pos logit contributions
 badges+0.198
ows+0.195
 tricks+0.187
 diapers+0.183
 names+0.183
Neg logit contributions
 least-0.162
Little-0.153
ime-0.148
illy-0.133
ately-0.127
Token."
Token ID526
Feature activation+1.26e+00

Pos logit contributions
 least+0.060
Little+0.051
ime+0.050
illy+0.048
ately+0.046
Neg logit contributions
 badges-0.069
ows-0.068
 tricks-0.064
 names-0.064
orts-0.063
Token Tim
Token ID5045
Feature activation-5.48e-01

Pos logit contributions
 badges+0.048
ows+0.047
 tricks+0.045
 names+0.045
 diapers+0.044
Neg logit contributions
 least-0.040
Little-0.036
ime-0.034
illy-0.033
ately-0.031
Token was
Token ID373
Feature activation+4.18e-01

Pos logit contributions
 least+0.017
Little+0.016
ime+0.015
illy+0.014
Maria+0.014
Neg logit contributions
 badges-0.021
ows-0.021
 tricks-0.020
 names-0.019
 diapers-0.019
Token sad
Token ID6507
Feature activation+3.21e+00

Pos logit contributions
 badges+0.019
 facts+0.019
cuts+0.018
bows+0.018
ows+0.018
Neg logit contributions
 least-0.011
 3-0.009
 nowhere-0.009
 mid-0.007
 three-0.007
Token a
Token ID257
Feature activation+1.18e+00

Pos logit contributions
 least+0.001
Little+0.001
ime+0.001
illy+0.001
ately+0.001
Neg logit contributions
ows-0.001
 badges-0.001
 tricks-0.001
orts-0.001
 names-0.001
Token pen
Token ID3112
Feature activation+3.86e-01

Pos logit contributions
 badges+0.043
ows+0.042
 tricks+0.040
 names+0.040
 diapers+0.040
Neg logit contributions
 least-0.040
Little-0.036
ime-0.034
illy-0.033
ately-0.032
Token.
Token ID13
Feature activation-6.66e-01

Pos logit contributions
 badges+0.015
ows+0.015
 tricks+0.014
 names+0.014
 diapers+0.014
Neg logit contributions
 least-0.011
Little-0.010
ime-0.010
illy-0.009
ately-0.009
Token He
Token ID679
Feature activation+5.11e-01

Pos logit contributions
 least+0.022
Little+0.019
ime+0.019
illy+0.018
ately+0.017
Neg logit contributions
 badges-0.025
ows-0.024
 tricks-0.023
 names-0.023
 diapers-0.023
Token wrote
Token ID2630
Feature activation+1.62e-01

Pos logit contributions
 badges+0.020
ows+0.019
 tricks+0.018
 names+0.018
 diapers+0.018
Neg logit contributions
 least-0.016
Little-0.014
ime-0.014
illy-0.013
Maria-0.012
Token something
Token ID1223
Feature activation+4.64e+00

Pos logit contributions
 badges+0.007
ows+0.006
 hides+0.006
orts+0.006
 diapers+0.006
Neg logit contributions
Little-0.004
 least-0.004
ime-0.004
illy-0.004
 Little-0.003
Token and
Token ID290
Feature activation-3.39e-01

Pos logit contributions
 badges+0.174
ows+0.167
 diapers+0.159
orts+0.158
 names+0.157
Neg logit contributions
 least-0.148
Little-0.135
ime-0.128
illy-0.123
ately-0.115
Token put
Token ID1234
Feature activation-7.29e-01

Pos logit contributions
 least+0.010
Little+0.009
ime+0.009
illy+0.008
ately+0.008
Neg logit contributions
 badges-0.013
ows-0.013
 tricks-0.013
 names-0.012
 diapers-0.012
Token it
Token ID340
Feature activation-1.54e-01

Pos logit contributions
 least+0.021
Little+0.019
ime+0.018
illy+0.017
 Little+0.016
Neg logit contributions
 badges-0.029
ows-0.029
 tricks-0.028
 gag-0.028
 hides-0.027
Token in
Token ID287
Feature activation-7.82e-02

Pos logit contributions
 least+0.005
Little+0.004
ime+0.004
illy+0.004
ately+0.004
Neg logit contributions
 badges-0.006
ows-0.006
 tricks-0.005
 names-0.005
 diapers-0.005
Token an
Token ID281
Feature activation-1.57e+00

Pos logit contributions
 least+0.003
Little+0.002
ime+0.002
illy+0.002
ately+0.002
Neg logit contributions
 badges-0.003
 names-0.003
 diapers-0.003
 labels-0.003
 tricks-0.003
Token,
Token ID11
Feature activation+1.02e+00

Pos logit contributions
 least+0.014
Little+0.012
ime+0.012
ill+0.011
illy+0.011
Neg logit contributions
 badges-0.029
 diapers-0.028
 helmets-0.027
 gag-0.027
ows-0.027
Token for
Token ID329
Feature activation+1.60e+00

Pos logit contributions
 badges+0.039
ows+0.038
 tricks+0.036
 diapers+0.036
 names+0.035
Neg logit contributions
 least-0.033
Little-0.029
ime-0.027
illy-0.027
ately-0.025
Token helping
Token ID5742
Feature activation+1.61e-01

Pos logit contributions
 badges+0.064
ows+0.061
 tricks+0.061
 names+0.059
 diapers+0.059
Neg logit contributions
 least-0.048
Little-0.043
ime-0.042
illy-0.039
ately-0.038
Token us
Token ID514
Feature activation+6.60e-01

Pos logit contributions
 badges+0.007
ows+0.007
 tricks+0.007
 names+0.007
 diapers+0.006
Neg logit contributions
 least-0.004
Little-0.004
ime-0.004
ately-0.003
illy-0.003
Token,"
Token ID553
Feature activation+3.04e+00

Pos logit contributions
 badges+0.023
ows+0.023
 tricks+0.022
 names+0.022
 diapers+0.021
Neg logit contributions
 least-0.022
Little-0.020
ime-0.020
illy-0.019
ately-0.018
Token their
Token ID511
Feature activation+6.05e+00

Pos logit contributions
 badges+0.095
ows+0.093
 tricks+0.088
 names+0.087
 diapers+0.086
Neg logit contributions
 least-0.117
Little-0.108
ime-0.104
illy-0.100
ately-0.096
Token dad
Token ID9955
Feature activation+4.43e-01

Pos logit contributions
ows+0.225
 badges+0.222
 tricks+0.207
 diapers+0.206
 names+0.203
Neg logit contributions
 least-0.194
Little-0.171
ime-0.168
illy-0.160
ately-0.154
Token said
Token ID531
Feature activation+1.27e+00

Pos logit contributions
 badges+0.014
ows+0.013
 tricks+0.012
 names+0.012
 labels+0.012
Neg logit contributions
 least-0.018
Little-0.016
ime-0.016
illy-0.015
ately-0.014
Token to
Token ID284
Feature activation+2.94e+00

Pos logit contributions
 badges+0.052
ows+0.048
 names+0.048
 tricks+0.048
 diapers+0.048
Neg logit contributions
 least-0.035
Little-0.032
ime-0.031
illy-0.029
ately-0.029
Token the
Token ID262
Feature activation+9.94e-01

Pos logit contributions
 badges+0.095
ows+0.092
 tricks+0.088
 names+0.087
 diapers+0.086
Neg logit contributions
 least-0.110
Little-0.101
ime-0.098
illy-0.094
ately-0.090
Token nice
Token ID3621
Feature activation+1.06e+00

Pos logit contributions
 badges+0.035
ows+0.034
 tricks+0.033
 names+0.032
 diapers+0.032
Neg logit contributions
 least-0.034
Little-0.031
ime-0.030
illy-0.029
ately-0.027
Token."
Token ID526
Feature activation+2.75e+00

Pos logit contributions
 badges+0.134
ows+0.130
 tricks+0.125
 names+0.123
 diapers+0.123
Neg logit contributions
 least-0.110
Little-0.095
ime-0.088
illy-0.087
ately-0.082
Token
Token ID198
Feature activation+7.84e-01

Pos logit contributions
 badges+0.125
ows+0.121
 tricks+0.118
 diapers+0.117
cuts+0.115
Neg logit contributions
 least-0.064
Little-0.059
ime-0.052
 Little-0.049
illy-0.049
Token
Token ID198
Feature activation+7.49e-01

Pos logit contributions
 badges+0.034
ows+0.034
 tricks+0.033
 names+0.033
orts+0.032
Neg logit contributions
 least-0.021
Little-0.017
ime-0.017
illy-0.016
ately-0.016
TokenThe
Token ID464
Feature activation+1.70e+00

Pos logit contributions
 badges+0.034
ows+0.034
 tricks+0.033
 names+0.032
 diapers+0.032
Neg logit contributions
 least-0.018
Little-0.016
ime-0.015
illy-0.014
Maria-0.013
Token ice
Token ID4771
Feature activation+3.32e+00

Pos logit contributions
ows+0.064
 badges+0.057
 diapers+0.055
bows+0.054
 gag+0.053
Neg logit contributions
 least-0.059
Little-0.054
ime-0.049
illy-0.046
 3-0.046
Token cream
Token ID8566
Feature activation+4.37e+00

Pos logit contributions
 badges+0.096
 versa+0.093
 meanings+0.087
uries+0.087
 diapers+0.084
Neg logit contributions
 least-0.121
in-0.113
ime-0.109
ill-0.107
oh-0.106
Token man
Token ID582
Feature activation+1.49e+00

Pos logit contributions
 badges+0.144
ows+0.142
 preferences+0.135
 diapers+0.134
 names+0.134
Neg logit contributions
 least-0.152
Little-0.135
ime-0.128
 mid-0.121
ill-0.118
Token gives
Token ID3607
Feature activation+8.01e-02

Pos logit contributions
ages+0.047
 diapers+0.046
 badges+0.045
 gag+0.044
uries+0.044
Neg logit contributions
 least-0.056
 again-0.046
Little-0.045
 mid-0.045
ill-0.044
Token them
Token ID606
Feature activation+2.52e+00

Pos logit contributions
 badges+0.003
ows+0.003
 tricks+0.003
 diapers+0.002
 gag+0.002
Neg logit contributions
 least-0.003
Little-0.003
ime-0.003
illy-0.002
ill-0.002
Token ice
Token ID4771
Feature activation+2.16e+00

Pos logit contributions
ows+0.105
 badges+0.102
 tricks+0.101
cks+0.101
cuts+0.099
Neg logit contributions
 least-0.069
Little-0.058
illy-0.052
ime-0.050
ill-0.050
Token cream
Token ID8566
Feature activation+3.13e+00

Pos logit contributions
 badges+0.051
 meanings+0.045
ows+0.045
 facts+0.044
 tricks+0.044
Neg logit contributions
 least-0.094
ime-0.085
Little-0.083
illy-0.083
ately-0.082
Token bug
Token ID5434
Feature activation-4.07e-01

Pos logit contributions
 badges+0.006
 tricks+0.006
 names+0.006
 chips+0.006
 labels+0.006
Neg logit contributions
 least-0.007
ime-0.007
Little-0.007
Maria-0.006
Em-0.006
Token,"
Token ID553
Feature activation+2.76e+00

Pos logit contributions
 least+0.011
ime+0.009
Little+0.009
illy+0.009
ill+0.008
Neg logit contributions
 badges-0.017
 names-0.016
 diapers-0.016
 helmets-0.016
ows-0.016
Token Lily
Token ID20037
Feature activation+7.59e-01

Pos logit contributions
ows+0.091
 badges+0.091
 tricks+0.085
 names+0.083
 diapers+0.083
Neg logit contributions
 least-0.102
Little-0.094
ime-0.088
illy-0.086
Maria-0.082
Token said
Token ID531
Feature activation+1.28e+00

Pos logit contributions
 badges+0.030
ows+0.029
 tricks+0.028
 names+0.028
 diapers+0.027
Neg logit contributions
 least-0.024
Little-0.021
ime-0.020
illy-0.019
ately-0.018
Token.
Token ID13
Feature activation+2.61e+00

Pos logit contributions
 badges+0.049
ows+0.047
 tricks+0.046
 names+0.045
 diapers+0.045
Neg logit contributions
 least-0.040
Little-0.036
ime-0.035
illy-0.033
ately-0.032
Token "
Token ID366
Feature activation+2.02e+00

Pos logit contributions
 badges+0.089
ows+0.088
 tricks+0.083
 names+0.083
 diapers+0.082
Neg logit contributions
 least-0.095
Little-0.086
ime-0.084
illy-0.080
ately-0.076
TokenWe
Token ID1135
Feature activation+2.95e-01

Pos logit contributions
 badges+0.084
ows+0.082
 tricks+0.080
 names+0.079
 diapers+0.078
Neg logit contributions
 least-0.057
Little-0.051
ime-0.048
illy-0.046
ately-0.043
Token like
Token ID588
Feature activation+3.05e+00

Pos logit contributions
bones+0.012
cks+0.012
 diapers+0.012
 badges+0.012
orts+0.012
Neg logit contributions
 least-0.009
Little-0.006
illy-0.006
ill-0.006
ime-0.006
Token bugs
Token ID11316
Feature activation-6.21e-01

Pos logit contributions
ows+0.131
 badges+0.128
 diapers+0.117
orts+0.117
cuts+0.116
Neg logit contributions
 least-0.086
Little-0.071
ime-0.070
illy-0.067
Maria-0.062
Token and
Token ID290
Feature activation+1.69e+00

Pos logit contributions
 least+0.016
Little+0.013
ime+0.013
illy+0.012
ill+0.011
Neg logit contributions
 badges-0.028
ows-0.026
 names-0.026
 tricks-0.026
 diapers-0.026
Token flowers
Token ID12734
Feature activation+1.31e+00

Pos logit contributions
ows+0.061
 badges+0.060
 diapers+0.054
orts+0.054
cuts+0.054
Neg logit contributions
 least-0.059
Little-0.051
ime-0.049
illy-0.047
Maria-0.045
Token He
Token ID679
Feature activation+1.58e-01

Pos logit contributions
 least+0.020
Little+0.018
ime+0.017
illy+0.016
Maria+0.015
Neg logit contributions
 badges-0.029
ows-0.028
 tricks-0.027
 diapers-0.027
 names-0.027
Token loved
Token ID6151
Feature activation-6.48e-01

Pos logit contributions
 badges+0.006
ows+0.005
 tricks+0.005
 names+0.005
 diapers+0.005
Neg logit contributions
 least-0.005
Little-0.005
ime-0.005
illy-0.005
ately-0.004
Token playing
Token ID2712
Feature activation+2.09e+00

Pos logit contributions
 least+0.018
Little+0.016
ime+0.015
illy+0.014
Maria+0.013
Neg logit contributions
 badges-0.027
ows-0.027
 tricks-0.026
 names-0.026
 diapers-0.025
Token with
Token ID351
Feature activation+3.00e-01

Pos logit contributions
 badges+0.073
ows+0.072
 names+0.067
 diapers+0.067
orts+0.066
Neg logit contributions
 least-0.071
Little-0.066
ime-0.063
illy-0.060
Maria-0.057
Token his
Token ID465
Feature activation+1.11e+00

Pos logit contributions
ows+0.014
 badges+0.012
orts+0.012
cuts+0.012
bows+0.012
Neg logit contributions
 least-0.008
Little-0.007
ime-0.006
illy-0.006
 Little-0.006
Token toys
Token ID14958
Feature activation+6.89e-01

Pos logit contributions
 badges+0.026
 tricks+0.024
ows+0.024
 names+0.024
 diapers+0.023
Neg logit contributions
 least-0.051
Little-0.048
ime-0.047
illy-0.046
Maria-0.045
Token and
Token ID290
Feature activation-4.35e-01

Pos logit contributions
ows+0.025
 badges+0.025
 tricks+0.025
 labels+0.024
 helmets+0.024
Neg logit contributions
Little-0.022
 least-0.021
ime-0.021
Maria-0.021
illy-0.020
Token eating
Token ID6600
Feature activation+2.77e+00

Pos logit contributions
 least+0.013
Little+0.012
ime+0.011
illy+0.010
Maria+0.010
Neg logit contributions
ows-0.017
 badges-0.016
orts-0.016
 diapers-0.015
cuts-0.015
Token candy
Token ID18550
Feature activation+2.76e+00

Pos logit contributions
ows+0.097
trained+0.093
ages+0.091
orts+0.091
cuts+0.091
Neg logit contributions
 least-0.081
Little-0.080
ime-0.073
 se-0.073
illy-0.072
Token.
Token ID13
Feature activation-6.67e-01

Pos logit contributions
 badges+0.122
orts+0.116
 gag+0.115
 names+0.114
ows+0.113
Neg logit contributions
 least-0.066
Little-0.054
illy-0.051
ime-0.050
st-0.049
Token
Token ID220
Feature activation+1.07e-01

Pos logit contributions
 least+0.017
Little+0.015
ime+0.014
illy+0.014
ately+0.013
Neg logit contributions
 badges-0.029
ows-0.029
 tricks-0.028
 names-0.028
 diapers-0.027
Token for
Token ID329
Feature activation+5.97e-01

Pos logit contributions
 badges+0.058
ows+0.056
 tricks+0.054
 diapers+0.053
 names+0.053
Neg logit contributions
 least-0.053
Little-0.047
ime-0.044
illy-0.043
ately-0.042
Token it
Token ID340
Feature activation-2.96e-01

Pos logit contributions
 badges+0.021
 tricks+0.020
ows+0.020
 names+0.020
 diapers+0.019
Neg logit contributions
 least-0.020
Little-0.019
ime-0.018
illy-0.017
Maria-0.017
Token."
Token ID526
Feature activation+3.47e+00

Pos logit contributions
 least+0.011
Little+0.010
ime+0.010
illy+0.010
Maria+0.009
Neg logit contributions
ows-0.009
 badges-0.009
 tricks-0.009
 names-0.009
 diapers-0.009
Token Mia
Token ID32189
Feature activation+1.06e+00

Pos logit contributions
 badges+0.122
ows+0.119
 tricks+0.114
 diapers+0.112
 names+0.112
Neg logit contributions
 least-0.121
Little-0.110
ime-0.106
illy-0.101
Maria-0.097
Token says
Token ID1139
Feature activation+1.84e+00

Pos logit contributions
 badges+0.027
bones+0.026
 diapers+0.025
ages+0.025
 tricks+0.024
Neg logit contributions
 least-0.046
Little-0.041
ill-0.040
ime-0.039
illy-0.039
Token.
Token ID13
Feature activation+2.33e+00

Pos logit contributions
 badges+0.079
 diapers+0.073
 tricks+0.073
 names+0.072
cuts+0.072
Neg logit contributions
 least-0.048
ime-0.041
Little-0.041
ately-0.040
illy-0.039
Token
Token ID198
Feature activation+8.43e-01

Pos logit contributions
ows+0.095
 badges+0.094
 names+0.092
 tricks+0.089
 diapers+0.089
Neg logit contributions
 least-0.070
Little-0.060
ime-0.058
illy-0.055
ately-0.051
Token
Token ID198
Feature activation+8.35e-01

Pos logit contributions
ows+0.032
orts+0.031
 badges+0.031
 names+0.030
 tricks+0.030
Neg logit contributions
 least-0.028
ime-0.022
illy-0.022
Little-0.022
ately-0.022
TokenThey
Token ID2990
Feature activation+3.39e+00

Pos logit contributions
 badges+0.026
ows+0.025
 tricks+0.024
 names+0.023
 diapers+0.023
Neg logit contributions
 least-0.033
ime-0.029
illy-0.028
Little-0.028
ately-0.028
Token look
Token ID804
Feature activation+2.92e+00

Pos logit contributions
 badges+0.121
 diapers+0.118
ows+0.117
orts+0.116
 tricks+0.115
Neg logit contributions
 least-0.118
Little-0.097
ime-0.092
ill-0.088
ately-0.087
Token around
Token ID1088
Feature activation+4.86e-01

Pos logit contributions
bows+0.131
 preferences+0.128
ages+0.125
 badges+0.125
aches+0.125
Neg logit contributions
 least-0.066
 Little-0.052
Little-0.051
 again-0.049
 Jackie-0.049
Token
Token ID220
Feature activation-5.61e-01

Pos logit contributions
 least+0.032
ime+0.027
Little+0.027
illy+0.026
ately+0.024
Neg logit contributions
 badges-0.032
ows-0.032
 names-0.030
 diapers-0.030
 labels-0.029
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
 least+0.013
Little+0.011
ime+0.010
illy+0.010
ately+0.009
Neg logit contributions
 badges-0.026
ows-0.026
 tricks-0.025
 names-0.025
 diapers-0.024
Token
Token ID198
Feature activation-2.14e+00

Pos logit contributions
 least+0.081
ime+0.062
bul+0.061
ately+0.061
illy+0.059
Neg logit contributions
ows-0.074
 badges-0.072
orts-0.071
 names-0.070
 tricks-0.067
TokenJohn
Token ID7554
Feature activation-4.14e-01

Pos logit contributions
 least+0.064
ime+0.049
ately+0.047
illy+0.047
Little+0.045
Neg logit contributions
 badges-0.089
ows-0.085
 tricks-0.083
 helmets-0.082
 diapers-0.082
Token walked
Token ID6807
Feature activation-1.16e+00

Pos logit contributions
 least+0.013
Little+0.012
ime+0.011
illy+0.011
Maria+0.010
Neg logit contributions
 badges-0.016
ows-0.015
 tricks-0.015
 names-0.015
 diapers-0.014
Token up
Token ID510
Feature activation+2.98e+00

Pos logit contributions
 least+0.035
Little+0.032
ime+0.029
illy+0.029
Maria+0.028
Neg logit contributions
 badges-0.046
ows-0.045
 tricks-0.043
 diapers-0.043
 names-0.042
Token to
Token ID284
Feature activation-9.52e-02

Pos logit contributions
 badges+0.102
 labels+0.096
 tricks+0.096
ows+0.096
 chips+0.096
Neg logit contributions
 least-0.104
Little-0.093
ime-0.091
illy-0.088
ately-0.079
Token Jane
Token ID12091
Feature activation-2.21e+00

Pos logit contributions
 least+0.003
Little+0.003
ime+0.002
illy+0.002
ately+0.002
Neg logit contributions
 badges-0.004
ows-0.004
 tricks-0.003
 names-0.003
 diapers-0.003
Token and
Token ID290
Feature activation-1.10e-01

Pos logit contributions
 least+0.053
Little+0.047
ime+0.043
illy+0.041
Maria+0.038
Neg logit contributions
 badges-0.099
ows-0.098
 tricks-0.094
 names-0.094
 diapers-0.093
Token said
Token ID531
Feature activation-1.29e+00

Pos logit contributions
 least+0.004
Little+0.004
ime+0.004
illy+0.003
ately+0.003
Neg logit contributions
 badges-0.004
ows-0.004
 tricks-0.003
 names-0.003
 diapers-0.003
Token,
Token ID11
Feature activation-8.02e-01

Pos logit contributions
 least+0.017
Little+0.015
ime+0.014
illy+0.013
ful+0.011
Neg logit contributions
 badges-0.070
ows-0.067
cks-0.066
 diapers-0.065
 labels-0.064
Token scan
Token ID9367
Feature activation+3.53e-01

Pos logit contributions
 badges+0.031
ows+0.031
 tricks+0.029
 diapers+0.029
 facts+0.029
Neg logit contributions
 least-0.025
Little-0.021
ime-0.019
illy-0.017
ately-0.017
Token our
Token ID674
Feature activation+2.83e+00

Pos logit contributions
 badges+0.013
ows+0.013
 tricks+0.013
 diapers+0.012
 names+0.012
Neg logit contributions
 least-0.011
Little-0.010
ime-0.009
illy-0.009
ately-0.009
Token tickets
Token ID8587
Feature activation+1.43e+00

Pos logit contributions
ows+0.076
 badges+0.074
orts+0.069
 tricks+0.067
 diapers+0.066
Neg logit contributions
 least-0.119
Little-0.107
ime-0.106
ately-0.100
illy-0.097
Token and
Token ID290
Feature activation+1.26e+00

Pos logit contributions
 badges+0.063
ows+0.061
 tricks+0.060
 diapers+0.059
 names+0.059
Neg logit contributions
 least-0.036
Little-0.031
ime-0.029
illy-0.027
ately-0.026
Token our
Token ID674
Feature activation+3.63e+00

Pos logit contributions
ows+0.044
orts+0.041
 badges+0.041
 tricks+0.039
cuts+0.039
Neg logit contributions
 least-0.045
Little-0.038
ime-0.035
ately-0.034
 Little-0.033
Token bodies
Token ID5920
Feature activation+1.95e+00

Pos logit contributions
ows+0.100
 badges+0.091
orts+0.090
 diapers+0.085
bows+0.084
Neg logit contributions
 least-0.153
Little-0.133
ime-0.132
ately-0.126
 3-0.125
Token.
Token ID13
Feature activation+1.62e+00

Pos logit contributions
 badges+0.078
 tricks+0.072
ows+0.072
 diapers+0.072
 names+0.071
Neg logit contributions
 least-0.058
Little-0.049
ime-0.048
ately-0.044
illy-0.044
Token They
Token ID1119
Feature activation+2.83e+00

Pos logit contributions
 badges+0.051
ows+0.050
 tricks+0.048
 diapers+0.046
 names+0.046
Neg logit contributions
 least-0.062
Little-0.057
ime-0.054
illy-0.052
ately-0.050
Token will
Token ID481
Feature activation+8.27e-01

Pos logit contributions
 badges+0.101
 diapers+0.098
orts+0.097
ows+0.097
 tricks+0.095
Neg logit contributions
 least-0.102
Little-0.081
ime-0.077
ately-0.072
 3-0.068
Token make
Token ID787
Feature activation+2.04e-01

Pos logit contributions
ows+0.033
 badges+0.033
 diapers+0.031
orts+0.031
 facts+0.031
Neg logit contributions
 least-0.026
Little-0.021
ime-0.019
 mid-0.017
illy-0.017
Token sure
Token ID1654
Feature activation-2.84e+00

Pos logit contributions
 badges+0.008
ows+0.008
bows+0.007
orts+0.007
 diapers+0.007
Neg logit contributions
 least-0.006
Little-0.006
ime-0.005
 Little-0.005
illy-0.005
Token would
Token ID561
Feature activation-5.75e-01

Pos logit contributions
 least+0.056
Little+0.051
ime+0.049
illy+0.048
Maria+0.045
Neg logit contributions
 badges-0.062
ows-0.061
 tricks-0.060
 names-0.059
 diapers-0.057
Token struggle
Token ID6531
Feature activation+3.50e-01

Pos logit contributions
 least+0.020
Little+0.018
ime+0.018
illy+0.017
Maria+0.016
Neg logit contributions
 badges-0.020
ows-0.019
 diapers-0.018
 tricks-0.018
 names-0.018
Token to
Token ID284
Feature activation-5.16e-01

Pos logit contributions
 badges+0.015
ows+0.014
 tricks+0.014
 names+0.014
 diapers+0.014
Neg logit contributions
 least-0.010
Little-0.009
ime-0.008
illy-0.008
ately-0.007
Token practice
Token ID3357
Feature activation+2.33e-01

Pos logit contributions
 least+0.019
Little+0.017
ime+0.016
illy+0.015
Maria+0.015
Neg logit contributions
 badges-0.017
ows-0.017
 diapers-0.016
 names-0.016
 tricks-0.016
Token so
Token ID523
Feature activation+9.25e-01

Pos logit contributions
 badges+0.010
ows+0.009
 diapers+0.009
 names+0.009
 tricks+0.009
Neg logit contributions
 least-0.007
Little-0.006
ime-0.005
illy-0.005
ately-0.005
Token he
Token ID339
Feature activation-2.11e+00

Pos logit contributions
 badges+0.031
 tricks+0.030
ows+0.030
 diapers+0.028
 helmets+0.028
Neg logit contributions
 least-0.033
Little-0.030
ime-0.029
illy-0.028
Maria-0.027
Token could
Token ID714
Feature activation-2.13e+00

Pos logit contributions
 least+0.057
Little+0.051
ime+0.048
illy+0.046
Maria+0.043
Neg logit contributions
 badges-0.089
ows-0.088
 tricks-0.085
 names-0.084
 diapers-0.083
Token be
Token ID307
Feature activation-9.88e-01

Pos logit contributions
 least+0.074
Little+0.065
ime+0.062
illy+0.058
ill+0.057
Neg logit contributions
 badges-0.077
ows-0.073
 diapers-0.071
 labels-0.069
 names-0.068
Token the
Token ID262
Feature activation-9.94e-01

Pos logit contributions
 least+0.032
Little+0.029
ime+0.028
illy+0.026
Maria+0.025
Neg logit contributions
 badges-0.037
ows-0.036
 diapers-0.034
 names-0.034
 tricks-0.034
Token best
Token ID1266
Feature activation-1.85e+00

Pos logit contributions
 least+0.034
Little+0.032
ime+0.031
illy+0.030
ately+0.029
Neg logit contributions
 badges-0.034
ows-0.033
 tricks-0.033
 names-0.032
 diapers-0.031
Token musician
Token ID21623
Feature activation-9.01e-01

Pos logit contributions
 least+0.057
Little+0.052
ime+0.049
illy+0.047
ately+0.045
Neg logit contributions
 badges-0.072
ows-0.070
 tricks-0.068
 names-0.067
 diapers-0.067
Token said
Token ID531
Feature activation+7.94e-01

Pos logit contributions
 badges+0.061
ows+0.060
 tricks+0.058
 diapers+0.057
 names+0.057
Neg logit contributions
 least-0.059
Little-0.053
ime-0.050
illy-0.049
Maria-0.047
Token.
Token ID13
Feature activation+2.45e+00

Pos logit contributions
 badges+0.033
ows+0.031
 names+0.030
 tricks+0.030
 diapers+0.030
Neg logit contributions
 least-0.022
Little-0.020
ime-0.019
illy-0.018
ately-0.018
Token
Token ID198
Feature activation+5.30e-01

Pos logit contributions
 badges+0.106
ows+0.104
 tricks+0.101
 names+0.099
 diapers+0.099
Neg logit contributions
 least-0.067
Little-0.058
ime-0.056
illy-0.053
ately-0.050
Token
Token ID198
Feature activation+4.89e-01

Pos logit contributions
ows+0.023
 badges+0.022
 tricks+0.022
 names+0.021
orts+0.021
Neg logit contributions
 least-0.015
Little-0.012
ime-0.012
ately-0.011
illy-0.011
Token"
Token ID1
Feature activation+1.36e+00

Pos logit contributions
 badges+0.017
ows+0.017
 tricks+0.016
orts+0.016
 names+0.016
Neg logit contributions
 least-0.017
ime-0.015
illy-0.014
ately-0.014
Little-0.014
TokenI
Token ID40
Feature activation-8.61e-01

Pos logit contributions
 badges+0.051
 tricks+0.048
ows+0.048
 names+0.048
 diapers+0.047
Neg logit contributions
 least-0.045
ime-0.040
Little-0.039
illy-0.037
ately-0.036
Token love
Token ID1842
Feature activation-1.10e-01

Pos logit contributions
 least+0.030
Little+0.027
ime+0.026
illy+0.025
Maria+0.023
Neg logit contributions
 badges-0.031
ows-0.030
 tricks-0.029
 diapers-0.028
 names-0.028
Token you
Token ID345
Feature activation-9.89e-01

Pos logit contributions
 least+0.003
Little+0.002
illy+0.002
ime+0.002
Maria+0.002
Neg logit contributions
ows-0.005
 badges-0.005
 tricks-0.005
 names-0.005
 diapers-0.005
Token too
Token ID1165
Feature activation+4.53e+00

Pos logit contributions
 least+0.032
Little+0.029
ime+0.028
illy+0.027
ately+0.026
Neg logit contributions
 badges-0.037
ows-0.036
 tricks-0.035
 names-0.034
 diapers-0.034
Token,
Token ID11
Feature activation-3.15e-01

Pos logit contributions
 badges+0.186
ows+0.186
 tricks+0.177
 names+0.176
 diapers+0.176
Neg logit contributions
 least-0.128
Little-0.115
ime-0.108
illy-0.104
Maria-0.098
Token Ben
Token ID3932
Feature activation-4.49e-02

Pos logit contributions
 least+0.012
Little+0.012
ime+0.011
illy+0.011
ately+0.010
Neg logit contributions
 badges-0.009
ows-0.009
 tricks-0.009
 names-0.009
 diapers-0.009
Token to
Token ID284
Feature activation-7.23e-01

Pos logit contributions
 badges+0.034
ows+0.033
 tricks+0.032
 diapers+0.032
 names+0.031
Neg logit contributions
 least-0.020
Little-0.017
ime-0.016
illy-0.016
ately-0.015
Token explore
Token ID7301
Feature activation-3.13e-01

Pos logit contributions
 least+0.026
Little+0.023
ime+0.023
illy+0.022
Maria+0.020
Neg logit contributions
 badges-0.025
ows-0.025
orts-0.023
 diapers-0.023
cuts-0.022
Token.
Token ID13
Feature activation-8.57e-01

Pos logit contributions
 least+0.011
Little+0.009
ime+0.009
ately+0.009
illy+0.009
Neg logit contributions
 tricks-0.011
 badges-0.011
ows-0.011
 names-0.010
 helmets-0.010
Token One
Token ID1881
Feature activation+3.74e-02

Pos logit contributions
 least+0.040
Little+0.037
ime+0.037
ately+0.036
bul+0.035
Neg logit contributions
 names-0.019
ows-0.017
 name-0.017
 diapers-0.015
 badges-0.015
Token day
Token ID1110
Feature activation+8.81e-01

Pos logit contributions
 names+0.001
 name+0.001
 tricks+0.001
ows+0.001
 badges+0.001
Neg logit contributions
 least-0.001
ately-0.001
Little-0.001
ime-0.001
Em-0.001
Token she
Token ID673
Feature activation-1.35e+00

Pos logit contributions
 badges+0.036
ows+0.034
 tricks+0.034
 names+0.034
 diapers+0.034
Neg logit contributions
 least-0.026
Little-0.021
ime-0.021
ately-0.019
illy-0.019
Token was
Token ID373
Feature activation-1.10e+00

Pos logit contributions
 least+0.044
Little+0.040
ime+0.038
illy+0.037
ately+0.034
Neg logit contributions
 badges-0.048
 names-0.046
 hides-0.045
ows-0.044
 tricks-0.044
Token playing
Token ID2712
Feature activation+2.36e+00

Pos logit contributions
 least+0.035
Little+0.032
ime+0.030
illy+0.029
ately+0.028
Neg logit contributions
 badges-0.041
ows-0.041
 tricks-0.039
 names-0.039
 diapers-0.038
Token in
Token ID287
Feature activation-8.53e-01

Pos logit contributions
 badges+0.091
ows+0.089
 tricks+0.087
 names+0.085
 diapers+0.085
Neg logit contributions
 least-0.073
Little-0.066
ime-0.063
illy-0.060
ately-0.057
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
 least+0.031
ately+0.029
illy+0.029
Little+0.028
ime+0.028
Neg logit contributions
 badges-0.026
 labels-0.025
 diapers-0.025
 tricks-0.025
 helmets-0.025
Token backyard
Token ID24296
Feature activation-1.60e+00

Pos logit contributions
ately+0.047
 least+0.046
ime+0.043
Little+0.041
illy+0.040
Neg logit contributions
 badges-0.051
 names-0.050
 tricks-0.050
 diapers-0.049
 helmets-0.049
Token listen
Token ID6004
Feature activation+4.38e-01

Pos logit contributions
 least+0.001
Little+0.001
ime+0.001
illy+0.001
ill+0.001
Neg logit contributions
 badges-0.001
ows-0.001
 diapers-0.001
cks-0.001
 helmets-0.001
Token.
Token ID13
Feature activation-7.61e-01

Pos logit contributions
 badges+0.019
ows+0.018
orts+0.017
 diapers+0.017
 names+0.017
Neg logit contributions
 least-0.011
Little-0.010
ime-0.010
illy-0.009
ately-0.009
Token
Token ID198
Feature activation-1.95e+00

Pos logit contributions
 least+0.023
ime+0.020
Little+0.020
illy+0.019
ately+0.018
Neg logit contributions
 badges-0.030
ows-0.030
 names-0.028
 diapers-0.028
 tricks-0.028
Token
Token ID198
Feature activation-1.96e+00

Pos logit contributions
 least+0.070
ately+0.053
ime+0.052
illy+0.051
bul+0.050
Neg logit contributions
ows-0.071
orts-0.066
 names-0.065
 tricks-0.065
 badges-0.065
TokenTim
Token ID14967
Feature activation-2.27e+00

Pos logit contributions
 least+0.053
Little+0.047
ime+0.044
illy+0.042
ately+0.039
Neg logit contributions
 badges-0.084
ows-0.082
 tricks-0.080
 names-0.079
 diapers-0.078
Tokenmy
Token ID1820
Feature activation-8.57e-01

Pos logit contributions
 least+0.065
Little+0.059
ime+0.058
ately+0.055
Jess+0.054
Neg logit contributions
 badges-0.085
ows-0.083
 names-0.079
 hides-0.078
 homework-0.078
Token went
Token ID1816
Feature activation-1.62e+00

Pos logit contributions
 least+0.029
ime+0.026
Little+0.026
illy+0.024
Maria+0.023
Neg logit contributions
 badges-0.030
ows-0.029
 tricks-0.028
 names-0.027
 hides-0.027
Token outside
Token ID2354
Feature activation+6.28e-01

Pos logit contributions
 least+0.042
Little+0.037
ime+0.035
illy+0.033
ately+0.031
Neg logit contributions
 badges-0.070
ows-0.069
 tricks-0.067
 names-0.066
 diapers-0.066
Token and
Token ID290
Feature activation-8.52e-01

Pos logit contributions
 tricks+0.014
 homework+0.013
 hides+0.013
 pets+0.012
ashes+0.012
Neg logit contributions
Little-0.027
illy-0.027
 least-0.026
ime-0.026
enna-0.024
Token saw
Token ID2497
Feature activation-1.57e+00

Pos logit contributions
 least+0.022
Little+0.020
ime+0.019
illy+0.018
ately+0.017
Neg logit contributions
 badges-0.037
ows-0.036
 tricks-0.035
 names-0.035
 diapers-0.035
Token his
Token ID465
Feature activation+1.50e+00

Pos logit contributions
 least+0.052
Little+0.048
ime+0.046
illy+0.044
ately+0.043
Neg logit contributions
 badges-0.057
ows-0.055
 tricks-0.054
 names-0.053
 diapers-0.053
Token creative
Token ID7325
Feature activation-3.42e-01

Pos logit contributions
 least+0.037
Little+0.034
ime+0.033
illy+0.032
ately+0.031
Neg logit contributions
 badges-0.035
ows-0.034
 tricks-0.033
 names-0.033
 diapers-0.032
Token and
Token ID290
Feature activation-1.47e+00

Pos logit contributions
 least+0.008
Little+0.007
ime+0.006
illy+0.006
ately+0.006
Neg logit contributions
 badges-0.016
ows-0.015
 diapers-0.015
 names-0.015
 tricks-0.015
Token draw
Token ID3197
Feature activation-1.67e-01

Pos logit contributions
 least+0.052
Little+0.046
ime+0.044
illy+0.042
Maria+0.041
Neg logit contributions
 badges-0.051
ows-0.050
 diapers-0.047
 names-0.046
orts-0.046
Token beautiful
Token ID4950
Feature activation-7.92e-01

Pos logit contributions
 least+0.006
Little+0.005
ime+0.005
illy+0.005
Maria+0.005
Neg logit contributions
 badges-0.006
ows-0.006
 diapers-0.005
 tricks-0.005
 names-0.005
Token pictures
Token ID5986
Feature activation+2.39e-01

Pos logit contributions
 least+0.030
Little+0.028
ime+0.028
illy+0.026
 Little+0.025
Neg logit contributions
ows-0.024
 badges-0.024
orts-0.023
cks-0.022
cuts-0.021
Token that
Token ID326
Feature activation-1.66e+00

Pos logit contributions
 badges+0.010
ows+0.009
 tricks+0.009
 names+0.009
 diapers+0.009
Neg logit contributions
 least-0.007
Little-0.006
ime-0.006
illy-0.006
ately-0.005
Token he
Token ID339
Feature activation-1.87e+00

Pos logit contributions
 least+0.053
Little+0.050
illy+0.047
ime+0.047
ately+0.045
Neg logit contributions
 badges-0.059
 tricks-0.058
 names-0.057
ows-0.057
 labels-0.056
Token shared
Token ID4888
Feature activation+1.21e+00

Pos logit contributions
 least+0.056
Little+0.055
ime+0.052
illy+0.050
Maria+0.048
Neg logit contributions
 tricks-0.067
 badges-0.065
ows-0.065
 names-0.062
 labels-0.062
Token with
Token ID351
Feature activation+1.24e+00

Pos logit contributions
ows+0.051
 badges+0.051
orts+0.048
cuts+0.048
 gag+0.048
Neg logit contributions
 least-0.031
Little-0.027
ime-0.027
illy-0.025
ill-0.025
Token the
Token ID262
Feature activation-3.71e-01

Pos logit contributions
 badges+0.042
 tricks+0.041
ows+0.039
 names+0.039
 diapers+0.039
Neg logit contributions
 least-0.044
Little-0.041
ime-0.039
illy-0.037
ately-0.036
Token world
Token ID995
Feature activation-1.28e+00

Pos logit contributions
 least+0.012
Little+0.011
ime+0.011
illy+0.010
ately+0.009
Neg logit contributions
 badges-0.014
ows-0.014
 diapers-0.013
 tricks-0.013
orts-0.013
TokenThe
Token ID464
Feature activation+6.56e-02

Pos logit contributions
 least+0.057
ime+0.046
ately+0.045
illy+0.044
Little+0.041
Neg logit contributions
 badges-0.093
 tricks-0.091
ows-0.090
 names-0.088
 helmets-0.087
Token sun
Token ID4252
Feature activation-7.90e-01

Pos logit contributions
 badges+0.003
ows+0.003
 tricks+0.003
 diapers+0.002
 names+0.002
Neg logit contributions
 least-0.002
Little-0.002
ime-0.002
illy-0.002
ately-0.001
Token was
Token ID373
Feature activation-2.40e+00

Pos logit contributions
 least+0.023
Little+0.019
ime+0.019
illy+0.019
enny+0.018
Neg logit contributions
ows-0.031
 badges-0.031
 names-0.029
 tricks-0.029
 diapers-0.029
Token setting
Token ID4634
Feature activation-1.04e+00

Pos logit contributions
 least+0.080
enny+0.074
ately+0.072
Little+0.071
ime+0.071
Neg logit contributions
 badges-0.080
 names-0.077
ows-0.077
 tricks-0.076
 helmets-0.076
Token again
Token ID757
Feature activation-3.04e+00

Pos logit contributions
 least+0.033
ime+0.028
Little+0.028
illy+0.027
enny+0.027
Neg logit contributions
ows-0.040
 badges-0.038
 helmets-0.036
 tricks-0.036
 names-0.036
Token but
Token ID475
Feature activation-3.58e+00

Pos logit contributions
 least+0.099
enny+0.091
Maria+0.090
Little+0.090
ime+0.090
Neg logit contributions
ows-0.097
 tricks-0.091
bows-0.090
 badges-0.090
 names-0.089
Token it
Token ID340
Feature activation+2.04e-01

Pos logit contributions
 least+0.114
ime+0.114
Little+0.109
illy+0.108
enny+0.105
Neg logit contributions
 badges-0.115
ows-0.113
 tricks-0.113
 names-0.112
 diapers-0.110
Token was
Token ID373
Feature activation-2.17e+00

Pos logit contributions
ows+0.008
 tricks+0.007
 badges+0.007
 names+0.007
 diapers+0.007
Neg logit contributions
 least-0.006
illy-0.005
ime-0.005
Little-0.005
enny-0.005
Token okay
Token ID8788
Feature activation-1.42e+00

Pos logit contributions
 least+0.072
Little+0.066
ime+0.065
ately+0.065
illy+0.064
Neg logit contributions
 badges-0.072
ows-0.071
 names-0.070
 tricks-0.069
 diapers-0.068
Token.
Token ID13
Feature activation-1.25e+00

Pos logit contributions
 least+0.051
Little+0.048
ime+0.045
illy+0.043
Em+0.042
Neg logit contributions
ows-0.047
 badges-0.045
 tricks-0.045
 names-0.045
 diapers-0.043
Token The
Token ID383
Feature activation-7.33e-02

Pos logit contributions
 least+0.052
Little+0.048
ime+0.047
illy+0.046
ately+0.043
Neg logit contributions
ows-0.033
 badges-0.033
 names-0.033
 diapers-0.030
 name-0.030
Token more
Token ID517
Feature activation+1.13e+00

Pos logit contributions
 least+0.032
Little+0.028
ime+0.027
illy+0.025
Maria+0.024
Neg logit contributions
 badges-0.041
ows-0.040
 diapers-0.038
orts-0.038
 tricks-0.038
Token than
Token ID621
Feature activation-5.51e-01

Pos logit contributions
 badges+0.034
ows+0.033
 tricks+0.032
 names+0.031
 diapers+0.031
Neg logit contributions
 least-0.045
Little-0.041
ime-0.040
illy-0.039
ately-0.037
Token anything
Token ID1997
Feature activation+2.60e+00

Pos logit contributions
 least+0.018
Little+0.018
ime+0.016
illy+0.016
Em+0.016
Neg logit contributions
 badges-0.019
 tricks-0.018
ows-0.018
 names-0.018
 diapers-0.018
Token else
Token ID2073
Feature activation+4.16e-01

Pos logit contributions
ows+0.098
 badges+0.097
 tricks+0.094
 names+0.092
 diapers+0.091
Neg logit contributions
 least-0.082
Little-0.074
ime-0.070
illy-0.068
Maria-0.065
Token she
Token ID673
Feature activation-3.73e+00

Pos logit contributions
 badges+0.016
ows+0.016
 tricks+0.015
 names+0.015
 diapers+0.015
Neg logit contributions
 least-0.013
Little-0.012
ime-0.011
illy-0.011
Maria-0.010
Token had
Token ID550
Feature activation-3.91e+00

Pos logit contributions
 least+0.117
Little+0.108
ime+0.102
illy+0.100
Maria+0.094
Neg logit contributions
 badges-0.140
ows-0.137
 tricks-0.133
 names-0.132
 diapers-0.129
Token ever
Token ID1683
Feature activation-2.67e+00

Pos logit contributions
 least+0.114
Little+0.111
ime+0.100
illy+0.097
Maria+0.093
Neg logit contributions
ows-0.150
 badges-0.149
 tricks-0.148
 names-0.146
 labels-0.141
Token carried
Token ID5281
Feature activation-3.25e+00

Pos logit contributions
 least+0.085
Little+0.083
illy+0.075
ime+0.073
Em+0.072
Neg logit contributions
 badges-0.096
ows-0.094
 tricks-0.092
 names-0.092
 facts-0.089
Token.
Token ID13
Feature activation-1.71e+00

Pos logit contributions
 least+0.097
Little+0.087
ime+0.083
illy+0.080
ately+0.076
Neg logit contributions
 badges-0.128
ows-0.125
 tricks-0.120
 names-0.119
 diapers-0.119
Token
Token ID220
Feature activation-6.08e-01

Pos logit contributions
 least+0.061
ime+0.056
Little+0.056
illy+0.053
ately+0.050
Neg logit contributions
ows-0.055
 names-0.054
 badges-0.053
orts-0.051
 name-0.050
Token
Token ID198
Feature activation-2.86e+00

Pos logit contributions
 least+0.016
Little+0.013
ime+0.012
illy+0.012
ately+0.011
Neg logit contributions
ows-0.027
 badges-0.026
 names-0.025
 tricks-0.025
orts-0.025
Token have
Token ID423
Feature activation-1.96e+00

Pos logit contributions
 least+0.002
Little+0.002
ime+0.002
illy+0.002
ately+0.002
Neg logit contributions
 badges-0.001
 names-0.001
 tricks-0.001
 name-0.001
ows-0.001
Token such
Token ID884
Feature activation+2.34e+00

Pos logit contributions
 least+0.065
Little+0.059
ime+0.057
illy+0.054
ately+0.053
Neg logit contributions
 badges-0.073
 tricks-0.068
ows-0.068
 names-0.066
 labels-0.065
Token a
Token ID257
Feature activation-7.38e-01

Pos logit contributions
ows+0.109
orts+0.104
 badges+0.102
cks+0.100
cuts+0.100
Neg logit contributions
 least-0.060
Little-0.051
illy-0.044
 3-0.044
 Little-0.043
Token cool
Token ID3608
Feature activation-2.25e+00

Pos logit contributions
 least+0.029
ime+0.027
Little+0.027
illy+0.026
ately+0.026
Neg logit contributions
 badges-0.022
 tricks-0.021
ows-0.020
 names-0.020
 diapers-0.019
Token souven
Token ID45043
Feature activation+5.94e-01

Pos logit contributions
 least+0.063
Little+0.056
ime+0.053
illy+0.053
 3+0.047
Neg logit contributions
 badges-0.093
ows-0.092
cks-0.089
 tricks-0.088
 names-0.086
Tokenir
Token ID343
Feature activation-4.10e+00

Pos logit contributions
ows+0.023
cks+0.022
orts+0.022
aches+0.021
 badges+0.021
Neg logit contributions
 least-0.017
Little-0.016
 3-0.015
 Little-0.014
 Giant-0.014
Token from
Token ID422
Feature activation-3.87e-02

Pos logit contributions
 least+0.094
Little+0.082
ime+0.078
illy+0.073
ately+0.067
Neg logit contributions
 badges-0.192
ows-0.187
 tricks-0.181
 diapers-0.180
 names-0.180
Token their
Token ID511
Feature activation+1.36e+00

Pos logit contributions
 least+0.001
Little+0.001
ime+0.001
illy+0.001
ately+0.001
Neg logit contributions
 badges-0.002
ows-0.002
 tricks-0.001
 names-0.001
 diapers-0.001
Token exciting
Token ID7895
Feature activation-4.12e-01

Pos logit contributions
 badges+0.050
ows+0.047
 tricks+0.047
 names+0.047
 diapers+0.046
Neg logit contributions
 least-0.044
Little-0.041
ime-0.039
illy-0.038
Maria-0.036
Token adventure
Token ID8855
Feature activation-2.25e+00

Pos logit contributions
 least+0.010
Little+0.009
ime+0.009
illy+0.008
ately+0.007
Neg logit contributions
 badges-0.018
ows-0.018
 tricks-0.017
 diapers-0.017
 names-0.017
Token!
Token ID0
Feature activation-2.71e+00

Pos logit contributions
 least+0.070
Little+0.064
ime+0.060
illy+0.058
Maria+0.055
Neg logit contributions
 badges-0.085
ows-0.084
 tricks-0.081
 names-0.079
 diapers-0.079
Token He
Token ID679
Feature activation+1.91e-01

Pos logit contributions
 least+0.014
Little+0.013
ime+0.012
illy+0.012
ately+0.011
Neg logit contributions
 badges-0.014
ows-0.014
 tricks-0.013
 names-0.013
 diapers-0.013
Token lived
Token ID5615
Feature activation-1.57e-01

Pos logit contributions
 badges+0.007
ows+0.007
 tricks+0.006
 names+0.006
 diapers+0.006
Neg logit contributions
 least-0.006
Little-0.006
ime-0.006
illy-0.005
ately-0.005
Token a
Token ID257
Feature activation+2.87e-01

Pos logit contributions
 least+0.005
Little+0.005
ime+0.004
illy+0.004
Maria+0.004
Neg logit contributions
 badges-0.006
ows-0.006
 tricks-0.006
 names-0.005
 diapers-0.005
Token happy
Token ID3772
Feature activation-7.05e-01

Pos logit contributions
 tricks+0.009
 badges+0.009
 name+0.009
 names+0.008
 diapers+0.008
Neg logit contributions
 least-0.010
illy-0.009
Little-0.009
ill-0.009
ime-0.009
Token life
Token ID1204
Feature activation-1.40e+00

Pos logit contributions
 least+0.026
Little+0.024
Maria+0.024
ill+0.024
ately+0.023
Neg logit contributions
 name-0.023
 tricks-0.021
 teeth-0.021
 badges-0.021
 badge-0.020
Token but
Token ID475
Feature activation-3.61e+00

Pos logit contributions
 least+0.042
Little+0.037
ime+0.036
illy+0.034
ately+0.032
Neg logit contributions
 badges-0.056
ows-0.054
 tricks-0.052
 names-0.052
 diapers-0.052
Token something
Token ID1223
Feature activation+4.08e+00

Pos logit contributions
 least+0.108
Little+0.095
ime+0.090
illy+0.085
Maria+0.080
Neg logit contributions
 badges-0.148
ows-0.146
 names-0.136
 tricks-0.136
 diapers-0.136
Token was
Token ID373
Feature activation-2.83e+00

Pos logit contributions
 badges+0.154
ows+0.148
orts+0.143
 names+0.141
 diapers+0.138
Neg logit contributions
 least-0.128
ime-0.114
Little-0.114
illy-0.103
ately-0.097
Token missing
Token ID4814
Feature activation-5.93e-01

Pos logit contributions
 least+0.096
ime+0.078
Little+0.077
illy+0.076
 nowhere+0.074
Neg logit contributions
 badges-0.105
ows-0.103
cuts-0.098
 names-0.097
orts-0.096
Token.
Token ID13
Feature activation-7.09e-01

Pos logit contributions
 least+0.023
Little+0.022
Maria+0.021
ime+0.020
illy+0.020
Neg logit contributions
ows-0.018
 badges-0.017
 tricks-0.017
 names-0.016
 diapers-0.016
Token He
Token ID679
Feature activation+1.95e-01

Pos logit contributions
 least+0.026
Little+0.024
ime+0.023
illy+0.022
ately+0.021
Neg logit contributions
 badges-0.023
ows-0.023
 tricks-0.022
 names-0.022
 diapers-0.021
Token who
Token ID508
Feature activation+1.60e+00

Pos logit contributions
 least+0.003
ime+0.003
Little+0.003
illy+0.003
ately+0.003
Neg logit contributions
 badges-0.003
ows-0.003
 tricks-0.003
 diapers-0.003
 helmets-0.003
Token knew
Token ID2993
Feature activation-2.88e+00

Pos logit contributions
 badges+0.068
ows+0.067
 tricks+0.065
 names+0.064
 diapers+0.063
Neg logit contributions
 least-0.043
Little-0.037
ime-0.035
illy-0.034
ately-0.032
Token how
Token ID703
Feature activation+3.32e+00

Pos logit contributions
 least+0.104
Little+0.096
ime+0.094
illy+0.089
Maria+0.087
Neg logit contributions
ows-0.092
 badges-0.092
 tricks-0.090
 names-0.086
 helmets-0.084
Token disappointed
Token ID11679
Feature activation+9.10e-01

Pos logit contributions
 badges+0.126
 tricks+0.125
ows+0.123
 names+0.120
 diapers+0.118
Neg logit contributions
 least-0.104
Little-0.091
ime-0.085
illy-0.085
ately-0.080
Token Ted
Token ID11396
Feature activation-2.89e+00

Pos logit contributions
 badges+0.039
ows+0.038
orts+0.036
 names+0.036
 diapers+0.036
Neg logit contributions
 least-0.025
Little-0.022
ime-0.021
illy-0.020
 Little-0.019
Token was
Token ID373
Feature activation-3.75e+00

Pos logit contributions
 least+0.074
Little+0.065
ime+0.061
illy+0.058
ately+0.054
Neg logit contributions
 badges-0.127
ows-0.124
 tricks-0.120
 names-0.119
 diapers-0.118
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
 least+0.124
Little+0.116
ime+0.109
illy+0.106
Maria+0.104
Neg logit contributions
 badges-0.132
ows-0.130
 tricks-0.129
 names-0.125
 diapers-0.121
Token "
Token ID366
Feature activation-1.26e+00

Pos logit contributions
 least+0.047
ime+0.042
Little+0.041
illy+0.040
ately+0.037
Neg logit contributions
ows-0.047
 badges-0.046
 names-0.046
orts-0.044
 tricks-0.044
TokenWe
Token ID1135
Feature activation-1.60e+00

Pos logit contributions
 least+0.038
ime+0.033
illy+0.033
Little+0.031
ately+0.031
Neg logit contributions
 badges-0.044
 names-0.044
 tricks-0.043
ows-0.043
orts-0.043
Token can
Token ID460
Feature activation-1.31e+00

Pos logit contributions
 least+0.053
Little+0.047
ime+0.045
illy+0.043
ately+0.041
Neg logit contributions
 badges-0.060
ows-0.058
 tricks-0.056
 diapers-0.055
 names-0.054
Token try
Token ID1949
Feature activation+1.27e-01

Pos logit contributions
 least+0.046
Little+0.042
ime+0.041
illy+0.039
Maria+0.038
Neg logit contributions
 badges-0.045
ows-0.044
 tricks-0.042
 names-0.042
 diapers-0.041