TOP ACTIVATIONS
MAX = 16.733

before . " Un ic orn is a rare
books first ?" Un cle Tom laughed and said
sign that says : " Un ite the hipp os ".
. They said , " Un cle Tom , you are
not nice ." Un cle Tom laughed . He
little boy said , " Un cle , are you stealing
came to visit . " Un cle , I want to
my dog ?" Un cle Ben looked at Lily
down . Un cle looked at her and
the backyard . Un cle sprayed them with the
the coat . Un cle Mike said to himself
it back !" Un cle Jack laughed and threw
him . " Un cle , what are you
touched them and said " Un free ze !"
than Uncle ! Un cle was so happy he
shrink me !" Un cle Tom smiled and put
welcome here ." Un cle Jack gr umbled and
. Tim said , " Un cle Jack , let 's
's silly !" Un cle smiled and said ,
ement . Un able to believe his luck

MIN ACTIVATIONS
MIN = -16.115

day , a magical fire fly flew by and gave him
it . But the fire fly was too quick and flew
on a sunny day . Suddenly , he stumbled across something
a toy sword . He pretended it was a real weapon
and Lily followed the fire fly . They felt happy .
be safe . The fire fly was happy and thanked Tim
Mia was so excited . Suddenly , she heard something that
in awe as the dragon fly zoom ed around the room
a blue car . They pretended they were racing each other
Mom my was worried . Suddenly , Baby said , "
toy medical kit . She pretended to help her stuffed animals
walking in the park . Suddenly , Kim saw something that
playing with her toys . Suddenly she saw something brown pe
home Lucky saw a dragon fly . The dragon fly told
a big rocket that they pretended to fly to the moon
fun ! Suddenly , L ila heard a
on a blanket . She pretended they were having a tea
had so much fun ! Suddenly , they heard a loud
outside with his friends . Suddenly , another boy , who
on the jungle gym . Suddenly , he heard a very

INTERVAL 8.521 - 16.733
CONTAINS 1.757%

You are the best co - p ilot ever ." They
the butterfly could enjoy it too . She watched as the
, " You are getting too crazy , I don 't
said to her dad , " Look , monkeys ! Can
I have some water , please ?" the yellow flower asks

INTERVAL 0.309 - 8.521
CONTAINS 46.287%

swing , but not too high . We will be safe
pictures and words that their mom read to them every night
a shelter to hide from the rain . Twe ety saw
ball all day , and they became best friends . <|endoftext|>
bird in a tree . Beth couldn 't help but be

INTERVAL -7.903 - 0.309
CONTAINS 50.597%

sad and angry . They cried and shouted .
things . She told him that he should say sorry to
m ama loved him . They were happy ot ters .
look for sp oons in every corner . One day ,
started to run . But it was too late

INTERVAL -16.115 - -7.903
CONTAINS 1.358%

mom . Then he saw a huge neck - high patch
She gave it to me when I married your dad .
park , the mouse saw a big ball . The mouse
a time , there was a boy named Tim my .
with her mom and brought a sp ade . As they
Token before
Token ID878
Feature activation-4.73e+00

Pos logit contributions
 suddenly+0.162
 opened+0.158
 pretended+0.154
 Suddenly+0.152
 two+0.151
Neg logit contributions
 unatt-0.217
 forward-0.214
beh-0.212
ash-0.203
baby-0.202
Token.
Token ID13
Feature activation+1.87e+00

Pos logit contributions
 suddenly+0.100
 opened+0.094
 a+0.092
 two+0.088
 pretended+0.083
Neg logit contributions
beh-0.213
rav-0.197
ash-0.197
 unatt-0.196
 losers-0.192
Token
Token ID198
Feature activation+7.38e-01

Pos logit contributions
beh+0.066
 forward+0.065
 unatt+0.065
ash+0.064
rav+0.063
Neg logit contributions
 suddenly-0.046
 opened-0.044
 pretended-0.044
 two-0.041
 Suddenly-0.039
Token
Token ID198
Feature activation+7.58e-01

Pos logit contributions
baby+0.028
 forward+0.027
ash+0.027
rav+0.027
beh+0.027
Neg logit contributions
 pretended-0.016
 suddenly-0.016
 opened-0.015
 two-0.013
 Suddenly-0.012
Token"
Token ID1
Feature activation+8.14e+00

Pos logit contributions
beh+0.028
 unatt+0.027
ash+0.026
 forward+0.026
rav+0.025
Neg logit contributions
 suddenly-0.020
 opened-0.019
 two-0.018
 pretended-0.018
 Suddenly-0.017
TokenUn
Token ID3118
Feature activation+1.67e+01

Pos logit contributions
beh+0.265
 unatt+0.253
rav+0.245
 forward+0.244
ash+0.242
Neg logit contributions
 suddenly-0.228
 opened-0.221
 pretended-0.217
 Suddenly-0.212
 two-0.207
Tokenic
Token ID291
Feature activation+4.47e+00

Pos logit contributions
beh+0.434
 unatt+0.417
ash+0.405
 forward+0.402
rav+0.384
Neg logit contributions
 suddenly-0.597
 opened-0.574
 pretended-0.565
 two-0.555
 Suddenly-0.543
Tokenorn
Token ID1211
Feature activation-3.81e+00

Pos logit contributions
beh+0.165
 unatt+0.159
ash+0.158
 forward+0.158
rav+0.155
Neg logit contributions
 suddenly-0.108
 opened-0.101
 pretended-0.100
 Suddenly-0.097
 two-0.094
Token is
Token ID318
Feature activation+1.92e+00

Pos logit contributions
 suddenly+0.090
 opened+0.085
 pretended+0.084
 two+0.080
 Suddenly+0.080
Neg logit contributions
beh-0.141
 unatt-0.137
 forward-0.135
ash-0.134
rav-0.132
Token a
Token ID257
Feature activation-7.15e+00

Pos logit contributions
beh+0.071
 unatt+0.068
ash+0.067
 forward+0.066
rav+0.066
Neg logit contributions
 suddenly-0.048
 opened-0.046
 pretended-0.044
 two-0.043
 Suddenly-0.042
Token rare
Token ID4071
Feature activation+2.56e+00

Pos logit contributions
 suddenly+0.184
 opened+0.175
 pretended+0.171
 two+0.166
 Suddenly+0.161
Neg logit contributions
beh-0.257
 unatt-0.248
ash-0.244
 forward-0.242
rav-0.237
Token books
Token ID3835
Feature activation+2.93e+00

Pos logit contributions
beh+0.058
ash+0.056
 forward+0.055
 unatt+0.054
rav+0.054
Neg logit contributions
 suddenly-0.049
 opened-0.048
 pretended-0.048
 two-0.047
 a-0.046
Token first
Token ID717
Feature activation+3.33e-01

Pos logit contributions
beh+0.142
rav+0.127
ocol+0.125
chie+0.123
 mir+0.123
Neg logit contributions
 suddenly-0.061
 a-0.058
 opened-0.057
 two-0.051
 was-0.049
Token?"
Token ID1701
Feature activation-6.09e-01

Pos logit contributions
beh+0.016
rav+0.014
chie+0.014
ocol+0.014
aring+0.014
Neg logit contributions
 suddenly-0.007
 a-0.007
 opened-0.006
 two-0.006
 pretended-0.005
Token
Token ID198
Feature activation+6.56e-01

Pos logit contributions
 suddenly+0.011
 opened+0.011
 pretended+0.010
 two+0.010
 Suddenly+0.010
Neg logit contributions
beh-0.026
 unatt-0.025
ash-0.025
 forward-0.025
rav-0.025
Token
Token ID198
Feature activation+6.54e-01

Pos logit contributions
beh+0.028
 unatt+0.027
 forward+0.027
rav+0.027
baby+0.027
Neg logit contributions
 suddenly-0.012
 pretended-0.011
 opened-0.011
 two-0.010
 Suddenly-0.009
TokenUn
Token ID3118
Feature activation+1.66e+01

Pos logit contributions
beh+0.024
ash+0.024
 unatt+0.023
 forward+0.023
ocol+0.022
Neg logit contributions
 suddenly-0.017
 opened-0.016
 two-0.016
 pretended-0.015
 Suddenly-0.015
Tokencle
Token ID2375
Feature activation+6.65e-01

Pos logit contributions
beh+0.503
 unatt+0.481
ash+0.478
 losers+0.464
 forward+0.459
Neg logit contributions
 suddenly-0.539
 opened-0.500
 pretended-0.488
 two-0.487
 Suddenly-0.472
Token Tom
Token ID4186
Feature activation-3.49e-01

Pos logit contributions
baby+0.022
rav+0.022
beh+0.022
 unatt+0.021
aring+0.021
Neg logit contributions
 suddenly-0.016
 pretended-0.015
 Suddenly-0.014
 opened-0.014
 two-0.013
Token laughed
Token ID13818
Feature activation-2.25e+00

Pos logit contributions
 suddenly+0.007
 Suddenly+0.006
 pretended+0.006
 two+0.006
 opened+0.005
Neg logit contributions
beh-0.013
 unatt-0.013
 forward-0.013
aring-0.013
ash-0.013
Token and
Token ID290
Feature activation+1.61e+00

Pos logit contributions
 suddenly+0.034
 a+0.031
 two+0.030
 opened+0.029
 pretended+0.028
Neg logit contributions
beh-0.114
 unatt-0.106
ash-0.106
rav-0.105
 mir-0.105
Token said
Token ID531
Feature activation-3.96e+00

Pos logit contributions
beh+0.072
 unatt+0.069
 losers+0.068
 forward+0.068
rav+0.068
Neg logit contributions
 suddenly-0.024
 opened-0.020
 Suddenly-0.020
 two-0.019
 pretended-0.019
Token sign
Token ID1051
Feature activation-9.31e-01

Pos logit contributions
 suddenly+0.174
 opened+0.165
 pretended+0.164
 Suddenly+0.154
 two+0.154
Neg logit contributions
beh-0.264
 unatt-0.263
 forward-0.258
ash-0.253
baby-0.253
Token that
Token ID326
Feature activation-5.19e+00

Pos logit contributions
 suddenly+0.021
 pretended+0.020
 opened+0.019
 Suddenly+0.018
 two+0.018
Neg logit contributions
beh-0.035
 unatt-0.035
 forward-0.035
ash-0.034
aring-0.033
Token says
Token ID1139
Feature activation-4.47e+00

Pos logit contributions
 suddenly+0.122
 opened+0.113
 pretended+0.112
 two+0.108
 Suddenly+0.106
Neg logit contributions
beh-0.194
 unatt-0.188
 forward-0.186
ash-0.185
rav-0.182
Token:
Token ID25
Feature activation+1.46e+00

Pos logit contributions
 suddenly+0.109
 opened+0.107
 two+0.102
 a+0.101
 pretended+0.095
Neg logit contributions
beh-0.184
 unatt-0.174
ash-0.170
 forward-0.162
off-0.160
Token "
Token ID366
Feature activation+9.10e+00

Pos logit contributions
beh+0.059
 unatt+0.058
ash+0.056
agging+0.053
 losers+0.053
Neg logit contributions
 suddenly-0.035
 two-0.035
 a-0.034
 opened-0.033
 Suddenly-0.032
TokenUn
Token ID3118
Feature activation+1.66e+01

Pos logit contributions
beh+0.276
 unatt+0.275
 forward+0.264
ash+0.263
aring+0.255
Neg logit contributions
 suddenly-0.282
 opened-0.270
 two-0.263
 pretended-0.261
 Suddenly-0.252
Tokenite
Token ID578
Feature activation-4.82e-01

Pos logit contributions
beh+0.485
 unatt+0.485
ash+0.467
 forward+0.464
 losers+0.459
Neg logit contributions
 suddenly-0.530
 opened-0.503
 two-0.496
 pretended-0.493
 Suddenly-0.471
Token the
Token ID262
Feature activation+7.42e-01

Pos logit contributions
 opened+0.009
 a+0.009
 suddenly+0.009
 two+0.009
 was+0.009
Neg logit contributions
beh-0.021
 unatt-0.021
Acc-0.021
agging-0.020
ksh-0.019
Token hipp
Token ID18568
Feature activation+4.53e+00

Pos logit contributions
beh+0.024
 unatt+0.022
ash+0.022
 forward+0.022
rav+0.021
Neg logit contributions
 suddenly-0.023
 two-0.022
 opened-0.022
 pretended-0.021
 a-0.021
Tokenos
Token ID418
Feature activation+4.32e+00

Pos logit contributions
 unatt+0.154
beh+0.144
 forward+0.142
 future+0.139
 mir+0.138
Neg logit contributions
 two-0.125
 opened-0.122
 suddenly-0.121
 a-0.117
 was-0.115
Token".
Token ID1911
Feature activation+2.19e+00

Pos logit contributions
 unatt+0.166
beh+0.164
Acc+0.162
rav+0.153
 mir+0.151
Neg logit contributions
 two-0.113
 a-0.109
 opened-0.108
 suddenly-0.102
 spread-0.100
Token.
Token ID13
Feature activation+1.79e+00

Pos logit contributions
beh+0.131
ocol+0.126
 mir+0.124
rav+0.124
chie+0.123
Neg logit contributions
 a-0.052
 suddenly-0.052
 two-0.046
 was-0.045
 opened-0.044
Token They
Token ID1119
Feature activation-8.83e-01

Pos logit contributions
beh+0.079
 unatt+0.077
ash+0.073
 forward+0.072
rav+0.071
Neg logit contributions
 Suddenly-0.036
 suddenly-0.036
 opened-0.035
 two-0.034
 a-0.033
Token said
Token ID531
Feature activation-3.99e+00

Pos logit contributions
 suddenly+0.016
 Suddenly+0.015
 opened+0.014
 two+0.014
 pretended+0.014
Neg logit contributions
beh-0.036
 unatt-0.035
 forward-0.035
 losers-0.034
ash-0.034
Token,
Token ID11
Feature activation-5.38e-01

Pos logit contributions
 a+0.032
 suddenly+0.031
 two+0.027
 opened+0.019
 was+0.014
Neg logit contributions
beh-0.238
ash-0.236
 unatt-0.235
opl-0.229
ksh-0.226
Token "
Token ID366
Feature activation+9.16e+00

Pos logit contributions
 suddenly+0.007
 a+0.007
 Suddenly+0.007
 opened+0.007
 two+0.006
Neg logit contributions
beh-0.031
ash-0.029
 unatt-0.028
off-0.028
chie-0.027
TokenUn
Token ID3118
Feature activation+1.66e+01

Pos logit contributions
 unatt+0.291
beh+0.285
ash+0.279
 forward+0.278
aring+0.265
Neg logit contributions
 suddenly-0.291
 two-0.269
 pretended-0.266
 opened-0.261
 Suddenly-0.257
Tokencle
Token ID2375
Feature activation+5.77e-01

Pos logit contributions
 unatt+0.469
beh+0.463
ash+0.447
 losers+0.444
 forward+0.441
Neg logit contributions
 suddenly-0.550
 two-0.514
 opened-0.511
 pretended-0.508
 Suddenly-0.489
Token Tom
Token ID4186
Feature activation-3.76e-01

Pos logit contributions
beh+0.026
 unatt+0.026
ash+0.025
agging+0.025
 forward+0.025
Neg logit contributions
 suddenly-0.010
 two-0.010
 opened-0.010
 a-0.009
 pretended-0.009
Token,
Token ID11
Feature activation-5.82e-01

Pos logit contributions
 suddenly+0.005
 opened+0.005
 pretended+0.005
 two+0.005
 a+0.004
Neg logit contributions
beh-0.019
 unatt-0.018
ash-0.018
 forward-0.018
rav-0.017
Token you
Token ID345
Feature activation+9.07e+00

Pos logit contributions
 a+0.015
 two+0.014
 was+0.012
 opened+0.012
 there+0.012
Neg logit contributions
beh-0.026
agging-0.025
umpy-0.025
ivery-0.024
ags-0.024
Token are
Token ID389
Feature activation+2.83e+00

Pos logit contributions
beh+0.265
 losers+0.244
ash+0.242
aring+0.242
rav+0.238
Neg logit contributions
 suddenly-0.283
 Suddenly-0.267
 opened-0.257
 pretended-0.255
 two-0.242
Token not
Token ID407
Feature activation+9.83e-01

Pos logit contributions
rav+0.226
beh+0.226
 unatt+0.222
 forward+0.216
ash+0.216
Neg logit contributions
 suddenly-0.099
 a-0.098
 two-0.096
 opened-0.094
 pretended-0.085
Token nice
Token ID3621
Feature activation+8.04e+00

Pos logit contributions
rav+0.040
opl+0.040
 unatt+0.039
 forward+0.039
agging+0.039
Neg logit contributions
 a-0.027
 two-0.024
 opened-0.022
 used-0.019
 put-0.019
Token."
Token ID526
Feature activation+2.17e+00

Pos logit contributions
beh+0.369
 unatt+0.358
agging+0.356
chie+0.353
 forward+0.346
Neg logit contributions
 a-0.156
 two-0.153
 was-0.143
 suddenly-0.138
 opened-0.131
Token
Token ID198
Feature activation+6.71e-01

Pos logit contributions
beh+0.097
 unatt+0.092
ash+0.091
 forward+0.089
rav+0.089
Neg logit contributions
 suddenly-0.042
 opened-0.039
 two-0.037
 Suddenly-0.037
 pretended-0.036
Token
Token ID198
Feature activation+6.87e-01

Pos logit contributions
beh+0.029
 unatt+0.028
 forward+0.028
ash+0.028
baby+0.028
Neg logit contributions
 suddenly-0.012
 pretended-0.011
 opened-0.011
 two-0.010
 Suddenly-0.009
TokenUn
Token ID3118
Feature activation+1.66e+01

Pos logit contributions
beh+0.027
 unatt+0.026
ash+0.026
 forward+0.025
rav+0.024
Neg logit contributions
 suddenly-0.017
 two-0.016
 opened-0.016
 Suddenly-0.015
 a-0.015
Tokencle
Token ID2375
Feature activation+5.45e-01

Pos logit contributions
beh+0.518
 unatt+0.490
ash+0.478
 losers+0.477
 forward+0.470
Neg logit contributions
 suddenly-0.530
 opened-0.494
 two-0.484
 pretended-0.469
 Suddenly-0.465
Token Tom
Token ID4186
Feature activation-4.10e-01

Pos logit contributions
beh+0.019
baby+0.019
 unatt+0.019
 forward+0.019
ash+0.019
Neg logit contributions
 suddenly-0.013
 pretended-0.012
 opened-0.011
 Suddenly-0.011
 two-0.011
Token laughed
Token ID13818
Feature activation-2.48e+00

Pos logit contributions
 suddenly+0.007
 pretended+0.007
 opened+0.006
 Suddenly+0.006
 two+0.006
Neg logit contributions
beh-0.017
 unatt-0.017
 forward-0.017
ash-0.016
baby-0.016
Token.
Token ID13
Feature activation+1.83e+00

Pos logit contributions
 a+0.045
 two+0.042
 suddenly+0.042
 opened+0.035
 Suddenly+0.034
Neg logit contributions
beh-0.124
rav-0.117
chie-0.117
 mir-0.117
ocol-0.116
Token He
Token ID679
Feature activation-2.53e+00

Pos logit contributions
beh+0.083
 unatt+0.079
ash+0.076
rav+0.075
 forward+0.074
Neg logit contributions
 suddenly-0.036
 Suddenly-0.036
 opened-0.035
 two-0.034
 a-0.033
Token little
Token ID1310
Feature activation-4.78e+00

Pos logit contributions
baby+0.026
 ambulance+0.026
 unatt+0.025
 forward+0.025
 emergency+0.024
Neg logit contributions
 suddenly-0.015
 pretended-0.012
 opened-0.012
 clicked-0.012
 Suddenly-0.012
Token boy
Token ID2933
Feature activation-4.94e+00

Pos logit contributions
 suddenly+0.147
 clicked+0.142
 opened+0.138
 inserted+0.134
Suddenly+0.134
Neg logit contributions
baby-0.128
 ambulance-0.127
 unatt-0.124
 forward-0.124
 future-0.120
Token said
Token ID531
Feature activation-4.21e+00

Pos logit contributions
 suddenly+0.086
 pretended+0.075
 opened+0.075
 two+0.075
 Suddenly+0.072
Neg logit contributions
beh-0.208
 unatt-0.200
ash-0.199
 forward-0.199
aring-0.194
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
 suddenly+0.068
 a+0.062
 two+0.062
 opened+0.061
 Suddenly+0.054
Neg logit contributions
beh-0.210
ash-0.205
 unatt-0.203
opl-0.200
ksh-0.194
Token "
Token ID366
Feature activation+8.98e+00

Pos logit contributions
 suddenly+0.026
 two+0.024
 Suddenly+0.024
 opened+0.024
 a+0.024
Neg logit contributions
beh-0.053
ash-0.050
 unatt-0.050
opl-0.047
ocol-0.047
TokenUn
Token ID3118
Feature activation+1.65e+01

Pos logit contributions
beh+0.284
 unatt+0.280
ash+0.268
 forward+0.266
aring+0.261
Neg logit contributions
 suddenly-0.273
 opened-0.256
 pretended-0.253
 two-0.251
 Suddenly-0.246
Tokencle
Token ID2375
Feature activation+4.51e-01

Pos logit contributions
 unatt+0.466
ash+0.461
beh+0.456
 losers+0.442
 forward+0.432
Neg logit contributions
 suddenly-0.546
 opened-0.510
 two-0.509
 pretended-0.498
 Suddenly-0.487
Token,
Token ID11
Feature activation-1.20e+00

Pos logit contributions
beh+0.019
 unatt+0.019
ash+0.018
 forward+0.018
rav+0.017
Neg logit contributions
 suddenly-0.009
 opened-0.008
 pretended-0.008
 two-0.008
 Suddenly-0.008
Token are
Token ID389
Feature activation+2.72e+00

Pos logit contributions
 two+0.027
 a+0.027
 suddenly+0.026
 opened+0.026
 pretended+0.023
Neg logit contributions
beh-0.050
ash-0.048
agging-0.048
ags-0.047
opl-0.047
Token you
Token ID345
Feature activation+8.98e+00

Pos logit contributions
 unatt+0.069
beh+0.067
ash+0.065
agging+0.063
opl+0.063
Neg logit contributions
 two-0.099
 suddenly-0.099
 a-0.099
 opened-0.097
 pretended-0.093
Token stealing
Token ID16568
Feature activation+5.30e-01

Pos logit contributions
beh+0.363
 unatt+0.341
opl+0.337
ash+0.335
rav+0.330
Neg logit contributions
 two-0.221
 suddenly-0.217
 a-0.212
 opened-0.205
 pretended-0.193
Token came
Token ID1625
Feature activation+2.77e+00

Pos logit contributions
baby+0.029
beh+0.028
rav+0.028
 forward+0.028
 unatt+0.028
Neg logit contributions
 suddenly-0.018
 Suddenly-0.016
 pretended-0.016
 opened-0.016
 two-0.016
Token to
Token ID284
Feature activation+2.34e+00

Pos logit contributions
beh+0.079
 forward+0.076
 unatt+0.075
ash+0.074
baby+0.071
Neg logit contributions
 suddenly-0.092
 opened-0.087
 pretended-0.087
 Suddenly-0.083
 two-0.082
Token visit
Token ID3187
Feature activation+1.33e+00

Pos logit contributions
beh+0.087
 unatt+0.084
ash+0.083
 forward+0.083
rav+0.081
Neg logit contributions
 suddenly-0.058
 opened-0.055
 pretended-0.054
 two-0.052
 Suddenly-0.050
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
beh+0.061
rav+0.059
aring+0.058
chie+0.057
 losers+0.057
Neg logit contributions
 a-0.028
 suddenly-0.026
 opened-0.025
 two-0.023
 was-0.022
Token "
Token ID366
Feature activation+8.87e+00

Pos logit contributions
beh+0.054
 unatt+0.053
 forward+0.051
rav+0.050
ash+0.050
Neg logit contributions
 opened-0.021
 Suddenly-0.020
 a-0.019
 suddenly-0.019
 Under-0.018
TokenUn
Token ID3118
Feature activation+1.65e+01

Pos logit contributions
beh+0.285
 unatt+0.275
ash+0.270
 forward+0.268
rav+0.261
Neg logit contributions
 suddenly-0.265
 opened-0.252
 pretended-0.249
 two-0.243
 Suddenly-0.237
Tokencle
Token ID2375
Feature activation+4.35e-01

Pos logit contributions
beh+0.452
 unatt+0.451
ash+0.448
 losers+0.434
 forward+0.428
Neg logit contributions
 suddenly-0.554
 opened-0.522
 two-0.516
 pretended-0.514
 Suddenly-0.494
Token,
Token ID11
Feature activation-1.21e+00

Pos logit contributions
beh+0.019
 unatt+0.018
 forward+0.018
ash+0.018
rav+0.018
Neg logit contributions
 suddenly-0.008
 opened-0.007
 pretended-0.007
 two-0.007
 Suddenly-0.007
Token I
Token ID314
Feature activation+4.84e+00

Pos logit contributions
 suddenly+0.032
 opened+0.031
 two+0.031
 a+0.031
 pretended+0.030
Neg logit contributions
beh-0.044
ash-0.042
 unatt-0.042
agging-0.041
opl-0.040
Token want
Token ID765
Feature activation+2.79e+00

Pos logit contributions
beh+0.139
 unatt+0.132
 forward+0.132
ash+0.129
rav+0.127
Neg logit contributions
 suddenly-0.158
 opened-0.149
 pretended-0.146
 two-0.146
 Suddenly-0.145
Token to
Token ID284
Feature activation+2.28e+00

Pos logit contributions
beh+0.109
 forward+0.106
agging+0.104
opl+0.103
umpy+0.103
Neg logit contributions
 a-0.081
 two-0.075
 suddenly-0.069
 opened-0.069
 pretended-0.060
Token my
Token ID616
Feature activation+4.22e+00

Pos logit contributions
beh+0.202
 unatt+0.197
ash+0.191
 forward+0.188
rav+0.188
Neg logit contributions
 suddenly-0.191
 opened-0.182
 pretended-0.181
 two-0.178
 a-0.177
Token dog
Token ID3290
Feature activation+9.52e-01

Pos logit contributions
beh+0.141
 forward+0.141
 unatt+0.139
ash+0.136
baby+0.136
Neg logit contributions
 suddenly-0.113
 opened-0.110
 pretended-0.103
 Suddenly-0.101
 clicked-0.098
Token?"
Token ID1701
Feature activation-6.43e-01

Pos logit contributions
beh+0.040
rav+0.038
ash+0.037
ocol+0.037
 unatt+0.036
Neg logit contributions
 suddenly-0.022
 a-0.020
 pretended-0.020
 opened-0.020
 two-0.019
Token
Token ID198
Feature activation+6.06e-01

Pos logit contributions
 suddenly+0.012
 opened+0.012
 pretended+0.012
 two+0.011
 Suddenly+0.010
Neg logit contributions
beh-0.026
 unatt-0.026
 forward-0.026
ash-0.025
rav-0.025
Token
Token ID198
Feature activation+6.37e-01

Pos logit contributions
beh+0.026
 unatt+0.025
 forward+0.025
ash+0.025
baby+0.025
Neg logit contributions
 suddenly-0.011
 pretended-0.010
 opened-0.010
 two-0.009
 Suddenly-0.009
TokenUn
Token ID3118
Feature activation+1.65e+01

Pos logit contributions
beh+0.027
 unatt+0.026
ash+0.026
 forward+0.025
rav+0.024
Neg logit contributions
 suddenly-0.015
 opened-0.013
 two-0.013
 pretended-0.012
 Suddenly-0.012
Tokencle
Token ID2375
Feature activation+4.74e-01

Pos logit contributions
beh+0.484
ash+0.462
 unatt+0.460
 losers+0.444
 forward+0.444
Neg logit contributions
 suddenly-0.550
 opened-0.510
 pretended-0.499
 two-0.494
 Suddenly-0.481
Token Ben
Token ID3932
Feature activation-2.70e+00

Pos logit contributions
baby+0.015
rav+0.014
aring+0.014
ash+0.014
beh+0.014
Neg logit contributions
 suddenly-0.012
 pretended-0.011
 Suddenly-0.011
 opened-0.011
 blasted-0.010
Token looked
Token ID3114
Feature activation-4.00e+00

Pos logit contributions
 suddenly+0.048
 opened+0.043
 pretended+0.043
 two+0.041
 Suddenly+0.040
Neg logit contributions
beh-0.114
 unatt-0.112
 forward-0.110
ash-0.109
rav-0.108
Token at
Token ID379
Feature activation+3.19e+00

Pos logit contributions
 suddenly+0.124
 opened+0.122
 two+0.118
 pretended+0.118
 a+0.116
Neg logit contributions
beh-0.132
rav-0.122
 unatt-0.121
ash-0.116
aring-0.114
Token Lily
Token ID20037
Feature activation-7.84e-01

Pos logit contributions
 forward+0.105
 unatt+0.104
baby+0.104
overs+0.101
beh+0.099
Neg logit contributions
 suddenly-0.082
 opened-0.080
 pretended-0.079
 Suddenly-0.073
 clicked-0.073
Token down
Token ID866
Feature activation+3.07e+00

Pos logit contributions
beh+0.033
 unatt+0.032
 forward+0.031
ash+0.031
rav+0.030
Neg logit contributions
 suddenly-0.034
 opened-0.033
 pretended-0.032
 two-0.031
 Suddenly-0.031
Token.
Token ID13
Feature activation+1.33e+00

Pos logit contributions
beh+0.134
ash+0.128
 unatt+0.126
rav+0.125
aring+0.124
Neg logit contributions
 suddenly-0.065
 opened-0.061
 two-0.057
 a-0.056
 pretended-0.054
Token
Token ID220
Feature activation+2.11e+00

Pos logit contributions
beh+0.051
 unatt+0.050
 forward+0.049
ash+0.049
rav+0.048
Neg logit contributions
 suddenly-0.030
 opened-0.029
 pretended-0.028
 two-0.027
 Suddenly-0.026
Token
Token ID198
Feature activation+3.05e-01

Pos logit contributions
beh+0.089
 forward+0.087
ash+0.087
rav+0.085
 unatt+0.085
Neg logit contributions
 suddenly-0.039
 pretended-0.038
 opened-0.036
 two-0.032
 Suddenly-0.029
Token
Token ID198
Feature activation+3.12e-01

Pos logit contributions
beh+0.013
 forward+0.013
 unatt+0.013
ash+0.013
rav+0.013
Neg logit contributions
 suddenly-0.005
 pretended-0.005
 opened-0.005
 two-0.004
 Suddenly-0.004
TokenUn
Token ID3118
Feature activation+1.65e+01

Pos logit contributions
 unatt+0.013
beh+0.013
ash+0.013
 losers+0.012
overs+0.012
Neg logit contributions
 suddenly-0.007
 two-0.006
 opened-0.006
 Suddenly-0.006
 pretended-0.005
Tokencle
Token ID2375
Feature activation+5.80e-01

Pos logit contributions
beh+0.455
 unatt+0.448
ash+0.428
 losers+0.423
 forward+0.419
Neg logit contributions
 suddenly-0.569
 opened-0.535
 pretended-0.522
 two-0.520
 Suddenly-0.506
Token looked
Token ID3114
Feature activation-3.94e+00

Pos logit contributions
baby+0.021
rav+0.021
beh+0.021
 forward+0.021
ash+0.020
Neg logit contributions
 suddenly-0.012
 pretended-0.011
 Under-0.011
 opened-0.011
 Suddenly-0.011
Token at
Token ID379
Feature activation+3.17e+00

Pos logit contributions
 suddenly+0.120
 opened+0.116
 pretended+0.112
 two+0.110
 Suddenly+0.108
Neg logit contributions
beh-0.128
 unatt-0.120
ash-0.117
rav-0.117
aring-0.114
Token her
Token ID607
Feature activation+3.39e+00

Pos logit contributions
 forward+0.110
beh+0.110
 unatt+0.108
ash+0.107
baby+0.106
Neg logit contributions
 suddenly-0.080
 opened-0.077
 pretended-0.075
 Suddenly-0.071
 two-0.070
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
 unatt+0.130
 forward+0.129
beh+0.128
ash+0.123
aring+0.122
Neg logit contributions
 suddenly-0.071
 pretended-0.069
 opened-0.068
 Suddenly-0.063
 two-0.063
Token the
Token ID262
Feature activation+5.99e-01

Pos logit contributions
beh+0.103
 unatt+0.100
 forward+0.098
ash+0.098
rav+0.096
Neg logit contributions
 suddenly-0.048
 opened-0.045
 pretended-0.044
 two-0.042
 Suddenly-0.041
Token backyard
Token ID24296
Feature activation-2.48e+00

Pos logit contributions
beh+0.026
aring+0.024
ash+0.024
rav+0.024
 forward+0.023
Neg logit contributions
 suddenly-0.014
 two-0.013
 a-0.013
 opened-0.013
 pretended-0.012
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
 suddenly+0.061
 opened+0.058
 two+0.056
 pretended+0.055
 a+0.054
Neg logit contributions
beh-0.098
 unatt-0.092
rav-0.091
ash-0.090
 losers-0.090
Token
Token ID198
Feature activation+4.15e-01

Pos logit contributions
beh+0.055
 unatt+0.054
ash+0.052
 forward+0.052
rav+0.051
Neg logit contributions
 suddenly-0.032
 opened-0.030
 pretended-0.030
 two-0.029
 Suddenly-0.028
Token
Token ID198
Feature activation+4.31e-01

Pos logit contributions
 forward+0.016
beh+0.016
ash+0.016
rav+0.015
aring+0.015
Neg logit contributions
 pretended-0.009
 suddenly-0.008
 opened-0.008
 two-0.007
 clicked-0.007
TokenUn
Token ID3118
Feature activation+1.65e+01

Pos logit contributions
beh+0.019
 unatt+0.019
ash+0.018
 forward+0.018
baby+0.018
Neg logit contributions
 suddenly-0.008
 opened-0.007
 two-0.007
 pretended-0.007
 Suddenly-0.006
Tokencle
Token ID2375
Feature activation+3.89e-01

Pos logit contributions
beh+0.473
 unatt+0.462
ash+0.456
 forward+0.446
 losers+0.444
Neg logit contributions
 suddenly-0.562
 opened-0.516
 two-0.505
 pretended-0.499
 Suddenly-0.482
Token sprayed
Token ID35729
Feature activation-1.62e+00

Pos logit contributions
baby+0.014
rav+0.013
beh+0.013
ash+0.013
 forward+0.013
Neg logit contributions
 suddenly-0.008
 pretended-0.008
 Suddenly-0.008
 opened-0.007
 Under-0.007
Token them
Token ID606
Feature activation+6.73e+00

Pos logit contributions
 suddenly+0.037
 opened+0.034
 two+0.033
 pretended+0.033
 a+0.032
Neg logit contributions
beh-0.065
 unatt-0.063
aring-0.061
rav-0.061
ash-0.061
Token with
Token ID351
Feature activation-1.97e+00

Pos logit contributions
beh+0.284
 unatt+0.273
ash+0.269
rav+0.268
aring+0.264
Neg logit contributions
 suddenly-0.140
 opened-0.132
 two-0.126
 pretended-0.125
 a-0.120
Token the
Token ID262
Feature activation+6.91e-01

Pos logit contributions
 suddenly+0.042
 opened+0.040
 pretended+0.038
 two+0.037
 Suddenly+0.036
Neg logit contributions
beh-0.079
 unatt-0.077
ash-0.076
 forward-0.075
rav-0.074
Token the
Token ID262
Feature activation+8.62e-01

Pos logit contributions
 suddenly+0.081
 opened+0.077
 pretended+0.075
 Suddenly+0.070
 two+0.070
Neg logit contributions
beh-0.158
 unatt-0.155
 forward-0.151
ash-0.150
baby-0.147
Token coat
Token ID13209
Feature activation+5.38e-01

Pos logit contributions
beh+0.037
rav+0.034
aring+0.033
ash+0.033
 unatt+0.032
Neg logit contributions
 two-0.020
 suddenly-0.020
 opened-0.019
 a-0.019
 pretended-0.018
Token.
Token ID13
Feature activation+1.42e+00

Pos logit contributions
beh+0.022
rav+0.021
ash+0.020
 mir+0.020
ocol+0.020
Neg logit contributions
 suddenly-0.013
 opened-0.012
 two-0.011
 a-0.011
 pretended-0.011
Token
Token ID198
Feature activation+3.45e-01

Pos logit contributions
beh+0.060
 unatt+0.059
 forward+0.058
ash+0.058
rav+0.056
Neg logit contributions
 suddenly-0.027
 opened-0.025
 pretended-0.025
 two-0.024
 Suddenly-0.023
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
beh+0.014
 forward+0.014
ash+0.013
baby+0.013
 unatt+0.013
Neg logit contributions
 pretended-0.007
 suddenly-0.007
 opened-0.006
 two-0.006
 clicked-0.005
TokenUn
Token ID3118
Feature activation+1.64e+01

Pos logit contributions
 unatt+0.014
beh+0.014
ash+0.014
overs+0.013
rav+0.013
Neg logit contributions
 suddenly-0.008
 two-0.007
 opened-0.007
 Suddenly-0.007
Suddenly-0.007
Tokencle
Token ID2375
Feature activation+3.84e-01

Pos logit contributions
beh+0.469
 unatt+0.464
ash+0.447
 losers+0.444
 forward+0.434
Neg logit contributions
 suddenly-0.552
 opened-0.513
 two-0.499
 pretended-0.495
 Suddenly-0.483
Token Mike
Token ID4995
Feature activation+8.92e-01

Pos logit contributions
baby+0.014
beh+0.014
 forward+0.014
rav+0.014
ash+0.014
Neg logit contributions
 suddenly-0.008
 pretended-0.007
 opened-0.007
 Suddenly-0.007
 Under-0.007
Token said
Token ID531
Feature activation-4.00e+00

Pos logit contributions
beh+0.041
 unatt+0.040
 forward+0.040
ash+0.040
rav+0.039
Neg logit contributions
 suddenly-0.013
 opened-0.012
 pretended-0.012
 two-0.011
 Suddenly-0.011
Token to
Token ID284
Feature activation+2.48e+00

Pos logit contributions
 suddenly+0.066
 a+0.059
 two+0.053
 opened+0.051
 Suddenly+0.047
Neg logit contributions
beh-0.214
ash-0.211
opl-0.211
ags-0.201
ksh-0.199
Token himself
Token ID2241
Feature activation-1.68e+00

Pos logit contributions
beh+0.092
 unatt+0.089
ash+0.087
 forward+0.086
rav+0.085
Neg logit contributions
 suddenly-0.063
 opened-0.059
 two-0.057
 pretended-0.057
 Suddenly-0.055
Token it
Token ID340
Feature activation+3.85e+00

Pos logit contributions
beh+0.145
 unatt+0.139
ash+0.135
aring+0.134
rav+0.133
Neg logit contributions
 suddenly-0.095
 two-0.088
 opened-0.086
 a-0.086
 pretended-0.084
Token back
Token ID736
Feature activation+1.07e+01

Pos logit contributions
ocol+0.128
umm+0.124
beh+0.122
 mir+0.114
 impact+0.112
Neg logit contributions
 a-0.149
 two-0.132
 opened-0.119
 suddenly-0.117
 was-0.113
Token!"
Token ID2474
Feature activation-3.87e-01

Pos logit contributions
beh+0.378
 unatt+0.354
rav+0.351
 forward+0.346
ash+0.345
Neg logit contributions
 suddenly-0.300
 opened-0.288
 a-0.286
 two-0.285
 pretended-0.273
Token
Token ID198
Feature activation+5.24e-01

Pos logit contributions
 pretended+0.008
 suddenly+0.008
 opened+0.008
 two+0.007
 clicked+0.006
Neg logit contributions
 unatt-0.015
beh-0.015
 forward-0.015
baby-0.014
aring-0.014
Token
Token ID198
Feature activation+5.58e-01

Pos logit contributions
baby+0.018
aring+0.017
beh+0.017
 forward+0.017
 future+0.017
Neg logit contributions
 pretended-0.014
 opened-0.013
 suddenly-0.012
 spread-0.011
 blasted-0.011
TokenUn
Token ID3118
Feature activation+1.64e+01

Pos logit contributions
beh+0.018
 unatt+0.017
aring+0.016
 forward+0.016
baby+0.016
Neg logit contributions
 pretended-0.016
 opened-0.016
 suddenly-0.016
 two-0.014
 Suddenly-0.014
Tokencle
Token ID2375
Feature activation+3.82e-01

Pos logit contributions
beh+0.451
ash+0.435
 unatt+0.433
 forward+0.425
 losers+0.410
Neg logit contributions
 suddenly-0.565
 opened-0.531
 pretended-0.516
 two-0.515
 Suddenly-0.499
Token Jack
Token ID3619
Feature activation-2.76e+00

Pos logit contributions
baby+0.012
rav+0.012
aring+0.012
 unatt+0.012
beh+0.012
Neg logit contributions
 suddenly-0.009
 pretended-0.009
 Suddenly-0.008
 Under-0.008
 opened-0.008
Token laughed
Token ID13818
Feature activation-2.65e+00

Pos logit contributions
 suddenly+0.042
 Suddenly+0.039
 pretended+0.038
 two+0.037
 Under+0.037
Neg logit contributions
 forward-0.113
 unatt-0.112
beh-0.112
baby-0.111
ash-0.110
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
 suddenly+0.040
 a+0.039
 two+0.037
 opened+0.033
 pretended+0.032
Neg logit contributions
beh-0.137
rav-0.129
 mir-0.128
ocol-0.127
ash-0.127
Token threw
Token ID9617
Feature activation-2.00e+00

Pos logit contributions
beh+0.056
 unatt+0.055
 forward+0.053
 losers+0.053
ash+0.053
Neg logit contributions
 suddenly-0.018
 opened-0.016
 pretended-0.016
 Suddenly-0.015
 two-0.015
Token him
Token ID683
Feature activation+4.85e+00

Pos logit contributions
 suddenly+0.057
 opened+0.054
 pretended+0.052
 two+0.051
 Suddenly+0.049
Neg logit contributions
beh-0.097
 unatt-0.095
ash-0.093
 forward-0.092
rav-0.091
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
beh+0.153
 forward+0.153
 unatt+0.149
aring+0.147
ash+0.142
Neg logit contributions
 suddenly-0.137
 pretended-0.132
 opened-0.131
 two-0.125
 Suddenly-0.122
Token
Token ID198
Feature activation+1.74e-01

Pos logit contributions
beh+0.038
 forward+0.037
 unatt+0.037
ash+0.036
aring+0.036
Neg logit contributions
 suddenly-0.022
 pretended-0.021
 opened-0.020
 two-0.019
 clicked-0.017
Token
Token ID198
Feature activation+1.68e-01

Pos logit contributions
 forward+0.005
off+0.005
baby+0.005
aring+0.005
rav+0.005
Neg logit contributions
 pretended-0.005
 suddenly-0.004
 opened-0.004
 two-0.004
 clicked-0.004
Token"
Token ID1
Feature activation+7.31e+00

Pos logit contributions
beh+0.007
 unatt+0.007
 forward+0.007
ash+0.007
rav+0.007
Neg logit contributions
 suddenly-0.003
 opened-0.003
 pretended-0.003
 two-0.003
 Suddenly-0.003
TokenUn
Token ID3118
Feature activation+1.64e+01

Pos logit contributions
beh+0.204
 unatt+0.197
 forward+0.191
ash+0.190
rav+0.187
Neg logit contributions
 suddenly-0.245
 opened-0.237
 pretended-0.233
 two-0.227
 Suddenly-0.223
Tokencle
Token ID2375
Feature activation+2.90e-01

Pos logit contributions
beh+0.458
 unatt+0.451
ash+0.449
 losers+0.439
 forward+0.419
Neg logit contributions
 suddenly-0.551
 opened-0.521
 two-0.508
 pretended-0.507
 Suddenly-0.493
Token,
Token ID11
Feature activation-1.40e+00

Pos logit contributions
beh+0.011
 unatt+0.011
rav+0.011
 forward+0.011
ash+0.011
Neg logit contributions
 suddenly-0.006
 opened-0.005
 pretended-0.005
 Suddenly-0.005
 two-0.005
Token what
Token ID644
Feature activation-3.42e+00

Pos logit contributions
 suddenly+0.037
 opened+0.035
 pretended+0.034
 two+0.034
 a+0.032
Neg logit contributions
beh-0.050
 unatt-0.048
ash-0.047
 forward-0.047
agging-0.046
Token are
Token ID389
Feature activation+2.56e+00

Pos logit contributions
 suddenly+0.097
 opened+0.094
 two+0.091
 pretended+0.091
 a+0.087
Neg logit contributions
beh-0.113
 unatt-0.112
ash-0.107
 forward-0.107
rav-0.103
Token you
Token ID345
Feature activation+8.80e+00

Pos logit contributions
 unatt+0.066
ash+0.064
opl+0.063
 impact+0.062
beh+0.061
Neg logit contributions
 a-0.095
 two-0.094
 suddenly-0.093
 opened-0.092
 pretended-0.083
Token touched
Token ID12615
Feature activation-3.11e+00

Pos logit contributions
 suddenly+0.051
 opened+0.047
 pretended+0.045
 two+0.043
 Suddenly+0.042
Neg logit contributions
beh-0.132
 unatt-0.129
ash-0.127
 forward-0.127
rav-0.124
Token them
Token ID606
Feature activation+6.54e+00

Pos logit contributions
 a+0.053
 suddenly+0.050
 two+0.048
 was+0.039
 opened+0.038
Neg logit contributions
beh-0.153
 unatt-0.146
rav-0.144
aring-0.144
vern-0.143
Token and
Token ID290
Feature activation+9.79e-01

Pos logit contributions
beh+0.277
rav+0.263
ash+0.257
 unatt+0.256
 mir+0.253
Neg logit contributions
 suddenly-0.149
 opened-0.137
 two-0.131
 a-0.129
 pretended-0.128
Token said
Token ID531
Feature activation-4.26e+00

Pos logit contributions
beh+0.039
 unatt+0.038
ash+0.037
 forward+0.037
rav+0.036
Neg logit contributions
 suddenly-0.022
 opened-0.020
 pretended-0.020
 two-0.019
 Suddenly-0.018
Token "
Token ID366
Feature activation+8.92e+00

Pos logit contributions
 a+0.079
 suddenly+0.077
 two+0.068
 Suddenly+0.065
 opened+0.062
Neg logit contributions
beh-0.215
opl-0.208
ash-0.208
 unatt-0.205
ags-0.194
TokenUn
Token ID3118
Feature activation+1.63e+01

Pos logit contributions
 unatt+0.266
beh+0.263
 forward+0.255
overs+0.254
 mir+0.254
Neg logit contributions
 suddenly-0.292
 pretended-0.261
 two-0.258
 opened-0.257
 Suddenly-0.251
Tokenfree
Token ID5787
Feature activation+3.61e+00

Pos logit contributions
 unatt+0.459
beh+0.450
ash+0.444
 forward+0.439
agging+0.428
Neg logit contributions
 suddenly-0.540
 pretended-0.503
 two-0.500
 opened-0.497
 Suddenly-0.474
Tokenze
Token ID2736
Feature activation+1.46e+00

Pos logit contributions
beh+0.116
 unatt+0.111
 forward+0.108
ash+0.105
rav+0.099
Neg logit contributions
 suddenly-0.113
 two-0.106
 a-0.105
 pretended-0.103
 opened-0.101
Token!"
Token ID2474
Feature activation-7.45e-01

Pos logit contributions
beh+0.063
 unatt+0.060
ocol+0.059
 mir+0.058
opl+0.057
Neg logit contributions
 suddenly-0.032
 a-0.029
 two-0.028
 was-0.027
 Suddenly-0.026
Token
Token ID198
Feature activation+8.78e-02

Pos logit contributions
 suddenly+0.017
 opened+0.016
 pretended+0.016
 two+0.015
 Suddenly+0.014
Neg logit contributions
beh-0.028
 unatt-0.027
ash-0.027
 forward-0.027
aring-0.026
Token
Token ID198
Feature activation+9.79e-02

Pos logit contributions
ash+0.003
aring+0.003
baby+0.003
off+0.003
beh+0.003
Neg logit contributions
 pretended-0.002
 opened-0.002
 suddenly-0.002
 two-0.002
 spread-0.002
Token than
Token ID621
Feature activation+3.45e+00

Pos logit contributions
beh+0.051
 unatt+0.049
ash+0.048
 forward+0.048
rav+0.047
Neg logit contributions
 suddenly-0.051
 opened-0.048
 pretended-0.048
 two-0.046
 Suddenly-0.045
Token Uncle
Token ID23169
Feature activation+3.01e+00

Pos logit contributions
beh+0.141
 unatt+0.134
ash+0.133
aring+0.132
rav+0.130
Neg logit contributions
 suddenly-0.077
 opened-0.072
 two-0.069
 pretended-0.069
 a-0.067
Token!
Token ID0
Feature activation+8.00e-01

Pos logit contributions
beh+0.122
 unatt+0.119
ash+0.115
 forward+0.114
 losers+0.112
Neg logit contributions
 suddenly-0.068
 opened-0.065
 pretended-0.062
 two-0.061
 a-0.059
Token
Token ID198
Feature activation+3.99e-01

Pos logit contributions
beh+0.035
 unatt+0.035
ash+0.033
agging+0.033
rav+0.032
Neg logit contributions
 suddenly-0.016
 Suddenly-0.015
 two-0.015
 opened-0.014
 a-0.013
Token
Token ID198
Feature activation+4.04e-01

Pos logit contributions
beh+0.018
 unatt+0.018
 forward+0.017
ash+0.017
rav+0.017
Neg logit contributions
 suddenly-0.006
 opened-0.006
 pretended-0.006
 two-0.005
 Suddenly-0.005
TokenUn
Token ID3118
Feature activation+1.63e+01

Pos logit contributions
 unatt+0.016
beh+0.016
ash+0.016
ags+0.015
ocol+0.015
Neg logit contributions
 suddenly-0.010
 two-0.009
Suddenly-0.009
As-0.009
 Suddenly-0.009
Tokencle
Token ID2375
Feature activation+3.29e-01

Pos logit contributions
beh+0.470
 unatt+0.463
ash+0.445
 losers+0.443
 forward+0.432
Neg logit contributions
 suddenly-0.550
 opened-0.515
 two-0.506
 pretended-0.494
 Suddenly-0.487
Token was
Token ID373
Feature activation-1.52e+00

Pos logit contributions
beh+0.013
rav+0.012
baby+0.012
 forward+0.012
ash+0.012
Neg logit contributions
 suddenly-0.006
 pretended-0.006
 opened-0.006
 Suddenly-0.006
 two-0.005
Token so
Token ID523
Feature activation+8.84e-01

Pos logit contributions
 suddenly+0.040
 opened+0.038
 pretended+0.037
 two+0.036
 Suddenly+0.035
Neg logit contributions
beh-0.053
 unatt-0.052
 forward-0.051
ash-0.051
rav-0.049
Token happy
Token ID3772
Feature activation+4.91e+00

Pos logit contributions
beh+0.026
 unatt+0.026
ash+0.025
 forward+0.024
rav+0.024
Neg logit contributions
 suddenly-0.029
 opened-0.028
 two-0.027
 pretended-0.027
 Suddenly-0.026
Token he
Token ID339
Feature activation-6.19e-01

Pos logit contributions
beh+0.185
 unatt+0.179
 forward+0.176
ash+0.175
rav+0.172
Neg logit contributions
 suddenly-0.117
 opened-0.111
 pretended-0.108
 two-0.104
 Suddenly-0.102
Token shrink
Token ID22085
Feature activation-4.91e+00

Pos logit contributions
 two+0.031
 a+0.031
 opened+0.031
 suddenly+0.030
 pretended+0.028
Neg logit contributions
beh-0.045
agging-0.041
ash-0.041
 unatt-0.040
ags-0.039
Token me
Token ID502
Feature activation+8.92e+00

Pos logit contributions
 suddenly+0.109
 two+0.106
 a+0.105
 opened+0.101
 pretended+0.096
Neg logit contributions
beh-0.204
 unatt-0.193
rav-0.189
 forward-0.180
aring-0.179
Token!"
Token ID2474
Feature activation-7.74e-01

Pos logit contributions
beh+0.335
rav+0.324
 unatt+0.317
 mir+0.310
 losers+0.310
Neg logit contributions
 suddenly-0.218
 opened-0.213
 two-0.210
 a-0.209
 pretended-0.196
Token
Token ID198
Feature activation-4.30e-02

Pos logit contributions
 suddenly+0.018
 opened+0.017
 pretended+0.016
 two+0.016
 Suddenly+0.015
Neg logit contributions
beh-0.030
 unatt-0.029
 forward-0.029
ash-0.029
rav-0.028
Token
Token ID198
Feature activation-6.17e-02

Pos logit contributions
 pretended+0.001
 suddenly+0.001
 opened+0.001
 two+0.001
 clicked+0.001
Neg logit contributions
baby-0.002
beh-0.002
rav-0.002
 forward-0.002
 unatt-0.002
TokenUn
Token ID3118
Feature activation+1.63e+01

Pos logit contributions
 suddenly+0.002
 opened+0.001
 two+0.001
 pretended+0.001
 Suddenly+0.001
Neg logit contributions
beh-0.002
 unatt-0.002
ash-0.002
 forward-0.002
rav-0.002
Tokencle
Token ID2375
Feature activation+2.39e-01

Pos logit contributions
beh+0.482
 unatt+0.468
ash+0.462
 losers+0.447
 forward+0.441
Neg logit contributions
 suddenly-0.529
 opened-0.496
 pretended-0.484
 two-0.483
 Suddenly-0.466
Token Tom
Token ID4186
Feature activation-9.94e-01

Pos logit contributions
baby+0.008
rav+0.008
beh+0.008
aring+0.008
ash+0.008
Neg logit contributions
 suddenly-0.005
 pretended-0.005
 Suddenly-0.005
 opened-0.004
 Under-0.004
Token smiled
Token ID13541
Feature activation-1.18e+00

Pos logit contributions
 suddenly+0.017
 Suddenly+0.015
 two+0.014
 pretended+0.013
 Under+0.013
Neg logit contributions
beh-0.038
aring-0.038
 unatt-0.038
ash-0.037
 forward-0.037
Token and
Token ID290
Feature activation+8.26e-01

Pos logit contributions
 suddenly+0.021
 opened+0.020
 pretended+0.019
 two+0.019
 Suddenly+0.018
Neg logit contributions
beh-0.053
 unatt-0.051
ash-0.050
rav-0.049
 losers-0.049
Token put
Token ID1234
Feature activation-1.31e+00

Pos logit contributions
beh+0.036
 losers+0.034
 forward+0.034
rav+0.034
 unatt+0.034
Neg logit contributions
 suddenly-0.013
 Suddenly-0.011
 pretended-0.010
 opened-0.010
 two-0.010
Token welcome
Token ID7062
Feature activation+5.39e+00

Pos logit contributions
 unatt+0.022
ash+0.022
rav+0.022
overs+0.022
opl+0.021
Neg logit contributions
 a-0.022
 two-0.022
 opened-0.020
 suddenly-0.020
 pretended-0.020
Token here
Token ID994
Feature activation-7.36e-01

Pos logit contributions
beh+0.228
ash+0.220
opl+0.219
rav+0.214
 mir+0.213
Neg logit contributions
 a-0.128
 two-0.124
 suddenly-0.120
 there-0.103
 opened-0.098
Token."
Token ID526
Feature activation+1.59e+00

Pos logit contributions
 a+0.015
 suddenly+0.014
 two+0.013
 was+0.012
 opened+0.011
Neg logit contributions
beh-0.036
ocol-0.034
 mir-0.033
ash-0.033
opl-0.033
Token
Token ID198
Feature activation+2.61e-01

Pos logit contributions
beh+0.078
 unatt+0.075
ash+0.074
 forward+0.073
rav+0.073
Neg logit contributions
 suddenly-0.022
 opened-0.020
 two-0.018
 Suddenly-0.018
 pretended-0.018
Token
Token ID198
Feature activation+2.65e-01

Pos logit contributions
 unatt+0.010
beh+0.010
baby+0.010
 forward+0.010
ash+0.010
Neg logit contributions
 pretended-0.005
 suddenly-0.005
 opened-0.005
 two-0.004
 Suddenly-0.004
TokenUn
Token ID3118
Feature activation+1.63e+01

Pos logit contributions
beh+0.010
ash+0.010
 forward+0.010
 unatt+0.010
rav+0.010
Neg logit contributions
 suddenly-0.007
 opened-0.006
 two-0.006
 Suddenly-0.006
 pretended-0.006
Tokencle
Token ID2375
Feature activation+2.81e-01

Pos logit contributions
beh+0.472
 unatt+0.447
ash+0.446
 losers+0.434
 forward+0.432
Neg logit contributions
 suddenly-0.545
 opened-0.513
 two-0.501
 pretended-0.494
 Suddenly-0.481
Token Jack
Token ID3619
Feature activation-2.67e+00

Pos logit contributions
baby+0.010
beh+0.010
 unatt+0.009
rav+0.009
 forward+0.009
Neg logit contributions
 suddenly-0.006
 pretended-0.006
 Suddenly-0.006
 opened-0.006
 Under-0.006
Token gr
Token ID1036
Feature activation+1.11e+01

Pos logit contributions
 suddenly+0.049
 Suddenly+0.045
 pretended+0.044
 two+0.042
 opened+0.042
Neg logit contributions
beh-0.103
 unatt-0.102
baby-0.100
aring-0.100
 forward-0.099
Tokenumbled
Token ID11137
Feature activation-1.46e-01

Pos logit contributions
 unatt+0.273
 forward+0.263
beh+0.262
rav+0.250
 mir+0.246
Neg logit contributions
 suddenly-0.397
 opened-0.394
 two-0.382
 pretended-0.377
 Suddenly-0.374
Token and
Token ID290
Feature activation+1.13e+00

Pos logit contributions
 suddenly+0.003
 opened+0.003
 two+0.003
 a+0.003
 pretended+0.003
Neg logit contributions
beh-0.006
ash-0.006
rav-0.006
 unatt-0.006
 mir-0.006
Token.
Token ID13
Feature activation+1.38e+00

Pos logit contributions
 suddenly+0.049
 opened+0.046
 two+0.044
 pretended+0.043
 a+0.042
Neg logit contributions
beh-0.102
rav-0.098
 unatt-0.097
ash-0.096
baby-0.094
Token Tim
Token ID5045
Feature activation+1.04e+00

Pos logit contributions
ash+0.047
 forward+0.046
beh+0.046
 unatt+0.045
overs+0.045
Neg logit contributions
 suddenly-0.034
 opened-0.034
 pretended-0.033
 two-0.030
 clicked-0.028
Token said
Token ID531
Feature activation-4.39e+00

Pos logit contributions
ash+0.036
beh+0.035
baby+0.034
 unatt+0.034
off+0.033
Neg logit contributions
 suddenly-0.024
 two-0.022
 Suddenly-0.021
 opened-0.021
 a-0.021
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
 suddenly+0.055
 a+0.048
 two+0.046
 opened+0.044
 Suddenly+0.036
Neg logit contributions
beh-0.243
ash-0.235
 unatt-0.233
opl-0.231
ksh-0.226
Token "
Token ID366
Feature activation+8.85e+00

Pos logit contributions
 suddenly+0.023
 a+0.021
 Suddenly+0.021
 two+0.021
 opened+0.021
Neg logit contributions
beh-0.051
 unatt-0.048
ash-0.047
opl-0.046
off-0.045
TokenUn
Token ID3118
Feature activation+1.63e+01

Pos logit contributions
beh+0.318
 unatt+0.309
 forward+0.301
ash+0.301
rav+0.294
Neg logit contributions
 suddenly-0.230
 opened-0.218
 pretended-0.214
 two-0.208
 Suddenly-0.203
Tokencle
Token ID2375
Feature activation+1.56e-01

Pos logit contributions
 unatt+0.506
beh+0.506
ash+0.498
 forward+0.486
 losers+0.481
Neg logit contributions
 suddenly-0.492
 two-0.454
 opened-0.451
 pretended-0.446
 Suddenly-0.434
Token Jack
Token ID3619
Feature activation-2.96e+00

Pos logit contributions
beh+0.007
 unatt+0.007
ash+0.007
 forward+0.007
rav+0.006
Neg logit contributions
 suddenly-0.003
 opened-0.003
 pretended-0.002
 two-0.002
 Suddenly-0.002
Token,
Token ID11
Feature activation-1.23e+00

Pos logit contributions
 suddenly+0.042
 opened+0.040
 two+0.037
 pretended+0.037
 a+0.034
Neg logit contributions
beh-0.143
 unatt-0.140
 forward-0.136
ash-0.134
rav-0.132
Token let
Token ID1309
Feature activation-2.73e+00

Pos logit contributions
 a+0.031
 two+0.031
 suddenly+0.030
 opened+0.030
 pretended+0.028
Neg logit contributions
beh-0.048
agging-0.046
ash-0.045
 unatt-0.044
ags-0.044
Token's
Token ID338
Feature activation+4.81e+00

Pos logit contributions
 two+0.082
 a+0.079
 suddenly+0.075
 opened+0.071
 was+0.071
Neg logit contributions
beh-0.099
 unatt-0.098
agging-0.097
rav-0.096
aring-0.095
Token's
Token ID338
Feature activation+4.98e+00

Pos logit contributions
beh+0.081
 unatt+0.079
 forward+0.077
ash+0.077
rav+0.075
Neg logit contributions
 suddenly-0.057
 opened-0.054
 pretended-0.053
 two-0.052
 Suddenly-0.050
Token silly
Token ID14397
Feature activation+3.25e+00

Pos logit contributions
beh+0.192
 forward+0.187
 unatt+0.184
ash+0.181
 losers+0.178
Neg logit contributions
 suddenly-0.112
 opened-0.107
 pretended-0.105
 Suddenly-0.096
 two-0.091
Token!"
Token ID2474
Feature activation-8.20e-01

Pos logit contributions
 unatt+0.141
beh+0.138
 forward+0.130
ash+0.128
ocol+0.128
Neg logit contributions
 suddenly-0.064
 two-0.063
 a-0.061
 pretended-0.059
 opened-0.059
Token
Token ID198
Feature activation+1.08e-01

Pos logit contributions
 suddenly+0.014
 opened+0.013
 pretended+0.013
 two+0.012
 Suddenly+0.011
Neg logit contributions
beh-0.035
 forward-0.035
 unatt-0.035
ash-0.034
rav-0.034
Token
Token ID198
Feature activation+9.46e-02

Pos logit contributions
beh+0.005
 unatt+0.005
 forward+0.005
ash+0.005
rav+0.005
Neg logit contributions
 suddenly-0.002
 opened-0.001
 pretended-0.001
 two-0.001
 Suddenly-0.001
TokenUn
Token ID3118
Feature activation+1.62e+01

Pos logit contributions
beh+0.004
 unatt+0.004
ocol+0.003
ash+0.003
 losers+0.003
Neg logit contributions
 suddenly-0.002
 opened-0.002
 two-0.002
 Suddenly-0.002
Suddenly-0.002
Tokencle
Token ID2375
Feature activation+2.22e-01

Pos logit contributions
beh+0.473
 unatt+0.462
 losers+0.448
ash+0.445
 mir+0.434
Neg logit contributions
 suddenly-0.539
 opened-0.505
 pretended-0.492
 two-0.492
 Suddenly-0.476
Token smiled
Token ID13541
Feature activation-1.33e+00

Pos logit contributions
beh+0.008
baby+0.008
rav+0.008
 forward+0.008
ash+0.008
Neg logit contributions
 suddenly-0.005
 pretended-0.004
 opened-0.004
 Suddenly-0.004
 two-0.004
Token and
Token ID290
Feature activation+8.06e-01

Pos logit contributions
 suddenly+0.031
 opened+0.029
 pretended+0.028
 two+0.028
 Suddenly+0.027
Neg logit contributions
beh-0.052
 unatt-0.050
ash-0.049
 forward-0.049
rav-0.048
Token said
Token ID531
Feature activation-4.50e+00

Pos logit contributions
beh+0.037
 unatt+0.035
 forward+0.035
ash+0.035
rav+0.035
Neg logit contributions
 suddenly-0.012
 opened-0.010
 pretended-0.010
 two-0.010
 Suddenly-0.010
Token,
Token ID11
Feature activation-1.43e+00

Pos logit contributions
 suddenly+0.047
 a+0.040
 opened+0.038
 two+0.035
 Suddenly+0.033
Neg logit contributions
beh-0.249
opl-0.246
 unatt-0.243
ash-0.243
ags-0.233
Tokenement
Token ID972
Feature activation+1.99e+00

Pos logit contributions
 suddenly+0.158
 opened+0.153
 two+0.146
 pretended+0.145
 a+0.142
Neg logit contributions
beh-0.111
 unatt-0.103
ash-0.099
rav-0.099
 forward-0.098
Token.
Token ID13
Feature activation+8.25e-01

Pos logit contributions
beh+0.076
 unatt+0.074
ash+0.072
 forward+0.071
rav+0.071
Neg logit contributions
 suddenly-0.048
 opened-0.045
 pretended-0.043
 two-0.043
 a-0.041
Token
Token ID220
Feature activation+1.73e+00

Pos logit contributions
beh+0.032
 unatt+0.031
 forward+0.030
ash+0.030
rav+0.030
Neg logit contributions
 suddenly-0.019
 opened-0.018
 pretended-0.017
 two-0.017
 Suddenly-0.016
Token
Token ID198
Feature activation+1.98e-02

Pos logit contributions
beh+0.066
ash+0.065
aring+0.065
 forward+0.065
rav+0.063
Neg logit contributions
 pretended-0.037
 suddenly-0.037
 opened-0.035
 two-0.030
 spread-0.028
Token
Token ID198
Feature activation+3.51e-03

Pos logit contributions
aring+0.001
 forward+0.001
off+0.001
rav+0.001
beh+0.001
Neg logit contributions
 pretended-0.001
 suddenly-0.000
 opened-0.000
 two-0.000
 clicked-0.000
TokenUn
Token ID3118
Feature activation+1.62e+01

Pos logit contributions
beh+0.000
 unatt+0.000
ash+0.000
 forward+0.000
rav+0.000
Neg logit contributions
 suddenly-0.000
 opened-0.000
 pretended-0.000
 two-0.000
 Suddenly-0.000
Tokenable
Token ID540
Feature activation+1.93e+00

Pos logit contributions
beh+0.457
 unatt+0.442
ash+0.436
 forward+0.426
 losers+0.419
Neg logit contributions
 suddenly-0.548
 opened-0.516
 two-0.501
 pretended-0.492
 Suddenly-0.480
Token to
Token ID284
Feature activation+2.11e+00

Pos logit contributions
beh+0.063
aring+0.062
baby+0.062
 forward+0.061
rav+0.060
Neg logit contributions
 pretended-0.048
 suddenly-0.048
 Suddenly-0.045
 opened-0.045
 clicked-0.042
Token believe
Token ID1975
Feature activation-1.57e+00

Pos logit contributions
beh+0.076
 forward+0.074
 unatt+0.073
ash+0.071
 losers+0.071
Neg logit contributions
 suddenly-0.050
 pretended-0.049
 opened-0.048
 Suddenly-0.044
 clicked-0.043
Token his
Token ID465
Feature activation+2.10e+00

Pos logit contributions
 suddenly+0.032
 opened+0.029
 pretended+0.027
 two+0.026
 a+0.026
Neg logit contributions
beh-0.067
 unatt-0.065
ash-0.065
rav-0.063
 forward-0.063
Token luck
Token ID8458
Feature activation+3.13e+00

Pos logit contributions
beh+0.083
 unatt+0.081
ash+0.077
 forward+0.075
overs+0.074
Neg logit contributions
 two-0.050
 suddenly-0.049
 opened-0.049
 a-0.045
 pretended-0.045
Token day
Token ID1110
Feature activation-6.13e+00

Pos logit contributions
beh+0.158
 unatt+0.153
ash+0.149
 forward+0.148
rav+0.145
Neg logit contributions
 suddenly-0.121
 opened-0.117
 pretended-0.113
 two-0.112
 Suddenly-0.107
Token,
Token ID11
Feature activation-4.72e+00

Pos logit contributions
 suddenly+0.123
 opened+0.115
 pretended+0.112
 two+0.107
 Suddenly+0.104
Neg logit contributions
beh-0.252
 unatt-0.246
 forward-0.241
ash-0.241
rav-0.236
Token a
Token ID257
Feature activation-1.06e+01

Pos logit contributions
 suddenly+0.097
 opened+0.096
 pretended+0.092
 Suddenly+0.085
 clicked+0.085
Neg logit contributions
beh-0.177
 forward-0.176
 unatt-0.176
overs-0.169
ash-0.168
Token magical
Token ID10883
Feature activation-3.51e+00

Pos logit contributions
 suddenly+0.171
 two+0.156
 opened+0.155
 a+0.145
 pretended+0.141
Neg logit contributions
beh-0.523
ash-0.492
 unatt-0.483
opl-0.472
aring-0.471
Token fire
Token ID2046
Feature activation-1.00e+00

Pos logit contributions
 suddenly+0.091
 opened+0.087
 two+0.082
 pretended+0.082
 a+0.079
Neg logit contributions
beh-0.132
 unatt-0.123
ash-0.122
 forward-0.120
rav-0.119
Tokenfly
Token ID12254
Feature activation-1.42e+01

Pos logit contributions
 suddenly+0.025
 opened+0.023
 pretended+0.023
 two+0.022
 Suddenly+0.021
Neg logit contributions
beh-0.038
 unatt-0.037
ash-0.036
 forward-0.036
rav-0.035
Token flew
Token ID13112
Feature activation-3.68e+00

Pos logit contributions
 suddenly+0.271
 opened+0.253
 pretended+0.244
 two+0.230
 Suddenly+0.219
Neg logit contributions
beh-0.613
 unatt-0.596
ash-0.586
 forward-0.585
rav-0.577
Token by
Token ID416
Feature activation-2.22e-01

Pos logit contributions
 suddenly+0.090
 opened+0.086
 a+0.084
 two+0.082
 pretended+0.077
Neg logit contributions
beh-0.143
rav-0.136
 unatt-0.135
ash-0.133
aring-0.133
Token and
Token ID290
Feature activation+1.63e-01

Pos logit contributions
 suddenly+0.004
 opened+0.004
 pretended+0.004
 two+0.004
 Suddenly+0.004
Neg logit contributions
beh-0.009
 unatt-0.009
 forward-0.009
ash-0.009
rav-0.009
Token gave
Token ID2921
Feature activation-9.11e-02

Pos logit contributions
beh+0.007
 unatt+0.007
 forward+0.007
ash+0.007
 losers+0.007
Neg logit contributions
 suddenly-0.003
 opened-0.002
 pretended-0.002
 two-0.002
 Suddenly-0.002
Token him
Token ID683
Feature activation+4.27e+00

Pos logit contributions
 suddenly+0.002
 two+0.002
 opened+0.002
 a+0.002
 pretended+0.002
Neg logit contributions
beh-0.003
 unatt-0.003
aring-0.003
ash-0.003
rav-0.003
Token it
Token ID340
Feature activation+1.39e-01

Pos logit contributions
beh+0.160
 unatt+0.154
 forward+0.149
rav+0.142
aring+0.140
Neg logit contributions
 suddenly-0.260
 pretended-0.250
 opened-0.247
 Suddenly-0.244
 two-0.241
Token.
Token ID13
Feature activation-9.65e-01

Pos logit contributions
beh+0.006
 unatt+0.005
ash+0.005
rav+0.005
baby+0.005
Neg logit contributions
 suddenly-0.003
 opened-0.003
 pretended-0.003
 two-0.003
 a-0.003
Token But
Token ID887
Feature activation-6.29e+00

Pos logit contributions
 suddenly+0.022
 opened+0.021
 Suddenly+0.020
 pretended+0.020
 two+0.020
Neg logit contributions
beh-0.038
 unatt-0.037
ash-0.036
 forward-0.036
rav-0.035
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
 suddenly+0.124
 opened+0.119
 pretended+0.116
 two+0.110
 Suddenly+0.108
Neg logit contributions
beh-0.255
 unatt-0.251
 forward-0.246
ash-0.244
rav-0.239
Token fire
Token ID2046
Feature activation-4.20e-01

Pos logit contributions
 suddenly+0.034
 opened+0.032
 two+0.032
 pretended+0.031
 a+0.030
Neg logit contributions
beh-0.044
 unatt-0.042
ash-0.041
 forward-0.041
rav-0.040
Tokenfly
Token ID12254
Feature activation-1.37e+01

Pos logit contributions
 suddenly+0.009
 opened+0.008
 pretended+0.008
 two+0.008
 was+0.007
Neg logit contributions
beh-0.018
 unatt-0.018
 forward-0.017
agging-0.017
rav-0.017
Token was
Token ID373
Feature activation-2.76e+00

Pos logit contributions
 suddenly+0.262
 opened+0.245
 pretended+0.231
 two+0.216
 was+0.201
Neg logit contributions
beh-0.603
 unatt-0.594
 forward-0.580
rav-0.578
ash-0.577
Token too
Token ID1165
Feature activation+7.99e+00

Pos logit contributions
 suddenly+0.076
 opened+0.073
 two+0.070
 a+0.070
 pretended+0.068
Neg logit contributions
beh-0.099
rav-0.097
 unatt-0.094
ash-0.093
baby-0.091
Token quick
Token ID2068
Feature activation-2.49e-01

Pos logit contributions
beh+0.325
 unatt+0.312
rav+0.310
ash+0.306
 forward+0.296
Neg logit contributions
 suddenly-0.187
 opened-0.181
 two-0.177
 a-0.173
 pretended-0.158
Token and
Token ID290
Feature activation+4.78e-01

Pos logit contributions
 suddenly+0.004
 a+0.004
 opened+0.004
 two+0.004
 was+0.004
Neg logit contributions
beh-0.012
 unatt-0.011
ash-0.011
rav-0.011
ags-0.011
Token flew
Token ID13112
Feature activation-2.96e+00

Pos logit contributions
beh+0.020
ash+0.020
 unatt+0.020
agging+0.019
baby+0.019
Neg logit contributions
 suddenly-0.010
 opened-0.010
 pretended-0.009
 two-0.009
 a-0.009
Token on
Token ID319
Feature activation-4.42e+00

Pos logit contributions
baby+0.012
 forward+0.012
ash+0.012
 unatt+0.012
 future+0.012
Neg logit contributions
 suddenly-0.010
 pretended-0.010
 opened-0.009
 two-0.009
 clicked-0.008
Token a
Token ID257
Feature activation-1.12e+01

Pos logit contributions
 suddenly+0.087
 opened+0.081
 two+0.077
 pretended+0.077
 a+0.073
Neg logit contributions
beh-0.190
 unatt-0.183
ash-0.180
 forward-0.179
rav-0.178
Token sunny
Token ID27737
Feature activation+3.17e+00

Pos logit contributions
 suddenly+0.247
 opened+0.236
 a+0.221
 pretended+0.220
 two+0.218
Neg logit contributions
beh-0.490
ash-0.434
rav-0.430
aring-0.423
 unatt-0.421
Token day
Token ID1110
Feature activation-4.32e+00

Pos logit contributions
 unatt+0.082
ash+0.079
opl+0.078
overs+0.076
 future+0.076
Neg logit contributions
 suddenly-0.103
 pretended-0.102
 opened-0.099
 clicked-0.096
 two-0.094
Token.
Token ID13
Feature activation-4.35e-01

Pos logit contributions
 suddenly+0.098
 opened+0.092
 pretended+0.088
 two+0.087
 Suddenly+0.083
Neg logit contributions
beh-0.174
 unatt-0.167
ash-0.163
 forward-0.161
rav-0.161
Token Suddenly
Token ID24975
Feature activation-1.33e+01

Pos logit contributions
 suddenly+0.010
 opened+0.009
 pretended+0.009
 two+0.009
 Suddenly+0.008
Neg logit contributions
beh-0.016
 unatt-0.016
 forward-0.016
ash-0.016
rav-0.015
Token,
Token ID11
Feature activation-2.95e+00

Pos logit contributions
 pretended+0.251
 opened+0.241
 suddenly+0.235
 Suddenly+0.218
 clicked+0.211
Neg logit contributions
 forward-0.514
beh-0.487
 unatt-0.487
rav-0.477
baby-0.477
Token he
Token ID339
Feature activation-2.48e+00

Pos logit contributions
 pretended+0.057
 opened+0.056
 suddenly+0.052
 Suddenly+0.051
 clicked+0.049
Neg logit contributions
 forward-0.110
 unatt-0.107
beh-0.107
overs-0.103
 hurricane-0.101
Token stumbled
Token ID24241
Feature activation-3.91e+00

Pos logit contributions
 Under+0.038
 Suddenly+0.038
 pretended+0.037
 two+0.034
 suddenly+0.034
Neg logit contributions
 forward-0.097
 unatt-0.095
beh-0.090
 mir-0.090
ash-0.090
Token across
Token ID1973
Feature activation-1.32e+00

Pos logit contributions
 pretended+0.098
 suddenly+0.092
 opened+0.090
 Suddenly+0.086
 two+0.081
Neg logit contributions
 forward-0.140
 unatt-0.131
ash-0.129
agging-0.125
beh-0.125
Token something
Token ID1223
Feature activation-4.59e+00

Pos logit contributions
 pretended+0.018
 suddenly+0.016
 Suddenly+0.015
 opened+0.014
 clicked+0.013
Neg logit contributions
 unatt-0.056
beh-0.055
 permission-0.055
 forward-0.055
 future-0.055
Token a
Token ID257
Feature activation-1.18e+01

Pos logit contributions
 suddenly+0.054
 opened+0.050
 pretended+0.048
 two+0.046
 Suddenly+0.044
Neg logit contributions
beh-0.146
 unatt-0.142
 forward-0.140
ash-0.140
rav-0.137
Token toy
Token ID13373
Feature activation-4.70e+00

Pos logit contributions
 suddenly+0.299
 opened+0.284
 pretended+0.277
 two+0.271
 Suddenly+0.262
Neg logit contributions
beh-0.432
 unatt-0.416
ash-0.408
 forward-0.405
rav-0.398
Token sword
Token ID8429
Feature activation-8.25e+00

Pos logit contributions
 suddenly+0.118
 opened+0.111
 pretended+0.109
 two+0.106
 Suddenly+0.102
Neg logit contributions
beh-0.174
 unatt-0.166
ash-0.164
 forward-0.163
rav-0.161
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
 suddenly+0.202
 opened+0.191
 pretended+0.186
 two+0.182
 Suddenly+0.179
Neg logit contributions
beh-0.300
 unatt-0.294
 forward-0.286
ash-0.285
rav-0.278
Token He
Token ID679
Feature activation-4.59e+00

Pos logit contributions
 suddenly+0.000
 opened+0.000
 pretended+0.000
 two+0.000
 Suddenly+0.000
Neg logit contributions
beh-0.000
 unatt-0.000
 forward-0.000
ash-0.000
rav-0.000
Token pretended
Token ID36766
Feature activation-1.33e+01

Pos logit contributions
 suddenly+0.095
 Suddenly+0.086
 two+0.085
 source+0.079
As+0.076
Neg logit contributions
 losers-0.159
beh-0.152
 forward-0.151
 Go-0.148
 mir-0.148
Token it
Token ID340
Feature activation+2.81e+00

Pos logit contributions
 suddenly+0.343
 opened+0.327
 pretended+0.315
 two+0.308
 a+0.299
Neg logit contributions
beh-0.487
 unatt-0.466
ash-0.462
 forward-0.457
rav-0.448
Token was
Token ID373
Feature activation-2.45e+00

Pos logit contributions
 unatt+0.105
beh+0.104
baby+0.104
 forward+0.103
ash+0.100
Neg logit contributions
 Suddenly-0.043
 sudden-0.040
Suddenly-0.039
 suddenly-0.038
 two-0.038
Token a
Token ID257
Feature activation-8.79e+00

Pos logit contributions
 suddenly+0.027
 opened+0.024
 pretended+0.023
 Suddenly+0.022
 two+0.020
Neg logit contributions
beh-0.117
 forward-0.117
 unatt-0.116
 losers-0.113
ash-0.113
Token real
Token ID1103
Feature activation+3.42e+00

Pos logit contributions
 suddenly+0.206
 opened+0.196
 pretended+0.190
 two+0.184
 Suddenly+0.181
Neg logit contributions
beh-0.329
 unatt-0.323
 forward-0.317
ash-0.314
rav-0.309
Token weapon
Token ID4282
Feature activation-4.41e+00

Pos logit contributions
 forward+0.119
 unatt+0.118
 losers+0.116
baby+0.115
 mir+0.115
Neg logit contributions
 suddenly-0.081
 opened-0.079
 Suddenly-0.074
 pretended-0.073
 two-0.071
Token and
Token ID290
Feature activation+4.69e-01

Pos logit contributions
 suddenly+0.077
 opened+0.067
 two+0.066
 Suddenly+0.064
 pretended+0.064
Neg logit contributions
beh-0.158
ash-0.154
 unatt-0.154
 forward-0.153
aring-0.150
Token Lily
Token ID20037
Feature activation-1.66e+00

Pos logit contributions
beh+0.019
 unatt+0.019
 forward+0.018
ash+0.018
rav+0.018
Neg logit contributions
 suddenly-0.009
 opened-0.009
 pretended-0.008
 two-0.008
 Suddenly-0.008
Token followed
Token ID3940
Feature activation-3.82e+00

Pos logit contributions
 suddenly+0.037
 opened+0.032
 Suddenly+0.032
 two+0.031
 pretended+0.031
Neg logit contributions
beh-0.062
 unatt-0.060
 forward-0.060
ash-0.060
rav-0.058
Token the
Token ID262
Feature activation-6.91e-02

Pos logit contributions
 suddenly+0.086
 a+0.084
 two+0.079
 opened+0.075
 pretended+0.073
Neg logit contributions
beh-0.163
 unatt-0.160
aring-0.155
opl-0.154
rav-0.152
Token fire
Token ID2046
Feature activation+3.41e-01

Pos logit contributions
 suddenly+0.002
 two+0.001
 opened+0.001
 pretended+0.001
 a+0.001
Neg logit contributions
beh-0.003
 unatt-0.003
ash-0.003
 forward-0.003
overs-0.003
Tokenfly
Token ID12254
Feature activation-1.32e+01

Pos logit contributions
beh+0.012
 unatt+0.012
ash+0.011
 forward+0.011
rav+0.011
Neg logit contributions
 suddenly-0.009
 opened-0.009
 pretended-0.009
 two-0.008
 Suddenly-0.008
Token.
Token ID13
Feature activation+1.59e+00

Pos logit contributions
 suddenly+0.361
 opened+0.348
 pretended+0.339
 two+0.336
 a+0.330
Neg logit contributions
beh-0.471
 unatt-0.452
rav-0.445
ash-0.442
baby-0.438
Token They
Token ID1119
Feature activation-1.30e+00

Pos logit contributions
 forward+0.050
beh+0.050
ash+0.049
 unatt+0.049
overs+0.048
Neg logit contributions
 suddenly-0.044
 opened-0.042
 pretended-0.042
 two-0.039
 clicked-0.037
Token felt
Token ID2936
Feature activation-4.64e+00

Pos logit contributions
 Suddenly+0.023
 suddenly+0.022
 two+0.018
Suddenly+0.018
 Under+0.018
Neg logit contributions
 unatt-0.050
 forward-0.048
 losers-0.048
beh-0.048
 mir-0.048
Token happy
Token ID3772
Feature activation+4.16e+00

Pos logit contributions
 suddenly+0.125
 opened+0.119
 pretended+0.117
 two+0.113
 Suddenly+0.111
Neg logit contributions
beh-0.160
 unatt-0.156
 forward-0.153
ash-0.151
rav-0.148
Token.
Token ID13
Feature activation+1.71e+00

Pos logit contributions
beh+0.168
 unatt+0.161
ash+0.160
 forward+0.159
rav+0.156
Neg logit contributions
 suddenly-0.092
 opened-0.086
 pretended-0.084
 two-0.082
 Suddenly-0.078
Token be
Token ID307
Feature activation+5.09e+00

Pos logit contributions
beh+0.016
ash+0.016
 unatt+0.016
rav+0.015
 forward+0.015
Neg logit contributions
 suddenly-0.011
 opened-0.011
 two-0.010
 pretended-0.010
 a-0.010
Token safe
Token ID3338
Feature activation+6.41e+00

Pos logit contributions
beh+0.154
rav+0.149
ash+0.149
 unatt+0.145
aring+0.144
Neg logit contributions
 suddenly-0.166
 opened-0.157
 two-0.157
 pretended-0.157
 a-0.156
Token.
Token ID13
Feature activation+7.48e-01

Pos logit contributions
beh+0.279
ash+0.268
rav+0.264
opl+0.260
ocol+0.258
Neg logit contributions
 suddenly-0.139
 a-0.124
 two-0.122
 opened-0.116
 pretended-0.114
Token The
Token ID383
Feature activation-3.01e+00

Pos logit contributions
beh+0.030
 unatt+0.029
ash+0.028
 forward+0.028
rav+0.028
Neg logit contributions
 suddenly-0.016
 opened-0.015
 pretended-0.015
 two-0.014
 Suddenly-0.013
Token fire
Token ID2046
Feature activation+8.63e-02

Pos logit contributions
 suddenly+0.082
 opened+0.078
 pretended+0.077
 two+0.074
 Suddenly+0.073
Neg logit contributions
beh-0.102
 unatt-0.099
 forward-0.097
ash-0.097
rav-0.095
Tokenfly
Token ID12254
Feature activation-1.31e+01

Pos logit contributions
beh+0.004
 unatt+0.004
 forward+0.004
ash+0.004
rav+0.004
Neg logit contributions
 suddenly-0.001
 opened-0.001
 pretended-0.001
 two-0.001
 Suddenly-0.001
Token was
Token ID373
Feature activation-2.03e+00

Pos logit contributions
 suddenly+0.192
 opened+0.176
 pretended+0.168
 two+0.159
 Suddenly+0.150
Neg logit contributions
beh-0.616
 unatt-0.602
ash-0.591
 forward-0.590
rav-0.581
Token happy
Token ID3772
Feature activation+3.91e+00

Pos logit contributions
 suddenly+0.058
 opened+0.056
 pretended+0.053
 two+0.053
 a+0.052
Neg logit contributions
beh-0.069
 unatt-0.066
rav-0.066
ash-0.066
 forward-0.063
Token and
Token ID290
Feature activation+6.70e-01

Pos logit contributions
beh+0.157
 unatt+0.151
ash+0.150
 forward+0.147
rav+0.146
Neg logit contributions
 suddenly-0.090
 opened-0.083
 pretended-0.081
 two-0.079
 a-0.077
Token thanked
Token ID26280
Feature activation-4.60e+00

Pos logit contributions
beh+0.026
ash+0.025
 unatt+0.025
rav+0.024
agging+0.024
Neg logit contributions
 suddenly-0.016
 opened-0.016
 pretended-0.015
 two-0.015
 a-0.014
Token Tim
Token ID5045
Feature activation+7.62e-01

Pos logit contributions
 suddenly+0.086
 a+0.080
 two+0.079
 opened+0.074
 Suddenly+0.068
Neg logit contributions
beh-0.215
 unatt-0.206
aring-0.203
ash-0.202
rav-0.196
Token Mia
Token ID32189
Feature activation-7.39e+00

Pos logit contributions
 suddenly+0.017
 Suddenly+0.015
 two+0.015
 pretended+0.013
 a+0.013
Neg logit contributions
beh-0.035
off-0.033
ash-0.032
 forward-0.032
 unatt-0.032
Token was
Token ID373
Feature activation-4.94e+00

Pos logit contributions
 suddenly+0.144
 opened+0.134
 pretended+0.129
 two+0.126
 Suddenly+0.122
Neg logit contributions
beh-0.304
 unatt-0.296
ash-0.293
 forward-0.292
rav-0.286
Token so
Token ID523
Feature activation-2.28e+00

Pos logit contributions
 suddenly+0.144
 opened+0.140
 pretended+0.139
 Suddenly+0.131
 two+0.129
Neg logit contributions
beh-0.152
 unatt-0.150
 forward-0.149
ash-0.142
 losers-0.141
Token excited
Token ID6568
Feature activation-2.11e+00

Pos logit contributions
 suddenly+0.070
 opened+0.067
 two+0.064
 pretended+0.064
 Suddenly+0.063
Neg logit contributions
beh-0.073
 unatt-0.071
ash-0.070
rav-0.068
baby-0.067
Token.
Token ID13
Feature activation-7.20e-02

Pos logit contributions
 suddenly+0.049
 opened+0.046
 pretended+0.044
 two+0.043
 Suddenly+0.042
Neg logit contributions
beh-0.082
 unatt-0.080
ash-0.078
 forward-0.078
rav-0.077
Token Suddenly
Token ID24975
Feature activation-1.31e+01

Pos logit contributions
 suddenly+0.002
 opened+0.002
 pretended+0.002
 two+0.002
 Suddenly+0.002
Neg logit contributions
beh-0.002
 unatt-0.002
 forward-0.002
ash-0.002
rav-0.002
Token,
Token ID11
Feature activation-2.74e+00

Pos logit contributions
 pretended+0.271
 opened+0.252
 suddenly+0.248
 Suddenly+0.246
 Under+0.237
Neg logit contributions
 forward-0.475
overs-0.444
beh-0.440
 unatt-0.440
ash-0.439
Token she
Token ID673
Feature activation-1.56e+00

Pos logit contributions
 pretended+0.065
 Suddenly+0.063
 opened+0.062
 suddenly+0.061
 clicked+0.058
Neg logit contributions
 forward-0.089
beh-0.084
overs-0.083
 unatt-0.083
ash-0.080
Token heard
Token ID2982
Feature activation-7.34e+00

Pos logit contributions
 Suddenly+0.024
 Under+0.023
 pretended+0.022
 two+0.022
 suddenly+0.021
Neg logit contributions
 unatt-0.062
 forward-0.061
beh-0.059
ash-0.059
baby-0.059
Token something
Token ID1223
Feature activation-4.47e+00

Pos logit contributions
 pretended+0.081
 suddenly+0.076
 opened+0.067
 Suddenly+0.059
 clicked+0.051
Neg logit contributions
beh-0.343
 forward-0.340
 unatt-0.337
baby-0.335
ash-0.334
Token that
Token ID326
Feature activation-6.49e+00

Pos logit contributions
 suddenly+0.117
 opened+0.111
 pretended+0.110
 two+0.106
 Suddenly+0.104
Neg logit contributions
beh-0.156
 unatt-0.152
 forward-0.149
ash-0.148
rav-0.144
Token in
Token ID287
Feature activation-3.01e+00

Pos logit contributions
 suddenly+0.081
 opened+0.076
 pretended+0.074
 two+0.071
 Suddenly+0.069
Neg logit contributions
beh-0.165
 unatt-0.161
 forward-0.158
ash-0.157
rav-0.154
Token awe
Token ID25030
Feature activation-6.67e+00

Pos logit contributions
 suddenly+0.069
 opened+0.065
 pretended+0.063
 two+0.062
 Suddenly+0.059
Neg logit contributions
beh-0.119
 unatt-0.114
ash-0.113
 forward-0.111
rav-0.111
Token as
Token ID355
Feature activation-6.39e+00

Pos logit contributions
 suddenly+0.149
 opened+0.141
 two+0.136
 a+0.136
 pretended+0.131
Neg logit contributions
beh-0.275
 unatt-0.257
rav-0.256
ash-0.253
baby-0.247
Token the
Token ID262
Feature activation-4.53e-01

Pos logit contributions
 suddenly+0.124
 pretended+0.123
 opened+0.120
 Suddenly+0.112
 two+0.105
Neg logit contributions
 forward-0.252
beh-0.246
 unatt-0.243
 losers-0.235
overs-0.234
Token dragon
Token ID10441
Feature activation-3.63e+00

Pos logit contributions
 suddenly+0.014
 pretended+0.013
 opened+0.013
 Suddenly+0.013
 clicked+0.012
Neg logit contributions
 forward-0.013
beh-0.013
 unatt-0.013
 losers-0.013
ash-0.012
Tokenfly
Token ID12254
Feature activation-1.31e+01

Pos logit contributions
 suddenly+0.089
 opened+0.084
 Suddenly+0.084
 two+0.083
 pretended+0.082
Neg logit contributions
beh-0.126
 forward-0.120
 unatt-0.120
ash-0.119
aring-0.118
Token zoom
Token ID19792
Feature activation-1.44e+00

Pos logit contributions
 suddenly+0.264
 opened+0.248
 pretended+0.240
 two+0.231
 Suddenly+0.221
Neg logit contributions
beh-0.543
 unatt-0.530
ash-0.519
 forward-0.516
rav-0.509
Tokened
Token ID276
Feature activation-2.62e+00

Pos logit contributions
 suddenly+0.037
 opened+0.035
 pretended+0.034
 two+0.033
 Suddenly+0.033
Neg logit contributions
beh-0.051
 forward-0.049
 unatt-0.049
ash-0.049
rav-0.048
Token around
Token ID1088
Feature activation-6.84e-01

Pos logit contributions
 suddenly+0.066
 opened+0.063
 pretended+0.061
 two+0.060
 a+0.059
Neg logit contributions
beh-0.099
 unatt-0.095
ash-0.092
rav-0.091
aring-0.090
Token the
Token ID262
Feature activation-2.92e-02

Pos logit contributions
 suddenly+0.013
 opened+0.011
 a+0.011
 pretended+0.011
 two+0.011
Neg logit contributions
beh-0.032
 unatt-0.030
ash-0.030
rav-0.030
aring-0.030
Token room
Token ID2119
Feature activation-3.79e+00

Pos logit contributions
 suddenly+0.001
 opened+0.001
 pretended+0.001
 two+0.001
 Suddenly+0.001
Neg logit contributions
beh-0.001
 unatt-0.001
 forward-0.001
ash-0.001
rav-0.001
Token a
Token ID257
Feature activation-1.17e+01

Pos logit contributions
 suddenly+0.144
 opened+0.134
 two+0.130
 a+0.126
 pretended+0.125
Neg logit contributions
beh-0.339
 unatt-0.329
ash-0.327
aring-0.323
rav-0.323
Token blue
Token ID4171
Feature activation-4.45e+00

Pos logit contributions
 suddenly+0.318
 opened+0.304
 pretended+0.297
 two+0.289
 Suddenly+0.282
Neg logit contributions
beh-0.398
 unatt-0.386
 forward-0.376
ash-0.376
rav-0.367
Token car
Token ID1097
Feature activation-1.89e+00

Pos logit contributions
 suddenly+0.116
 opened+0.112
 pretended+0.109
 two+0.105
 Suddenly+0.104
Neg logit contributions
beh-0.152
 unatt-0.150
 forward-0.147
ash-0.147
rav-0.143
Token.
Token ID13
Feature activation-1.59e-01

Pos logit contributions
 suddenly+0.046
 opened+0.044
 pretended+0.043
 two+0.042
 Suddenly+0.041
Neg logit contributions
beh-0.068
 unatt-0.067
 forward-0.065
ash-0.065
aring-0.063
Token They
Token ID1119
Feature activation-2.58e+00

Pos logit contributions
 suddenly+0.004
 opened+0.004
 pretended+0.004
 two+0.004
 Suddenly+0.003
Neg logit contributions
beh-0.006
 unatt-0.006
 forward-0.006
ash-0.005
rav-0.005
Token pretended
Token ID36766
Feature activation-1.31e+01

Pos logit contributions
 suddenly+0.050
 Suddenly+0.047
 two+0.044
 opened+0.041
Suddenly+0.040
Neg logit contributions
 forward-0.097
beh-0.094
 losers-0.094
 unatt-0.092
ash-0.090
Token they
Token ID484
Feature activation+5.01e-01

Pos logit contributions
 suddenly+0.385
 opened+0.369
 pretended+0.360
 two+0.352
 Suddenly+0.342
Neg logit contributions
beh-0.426
 unatt-0.411
ash-0.402
 forward-0.399
rav-0.389
Token were
Token ID547
Feature activation-1.51e+00

Pos logit contributions
beh+0.018
 unatt+0.018
 forward+0.018
rav+0.017
baby+0.017
Neg logit contributions
 suddenly-0.011
 Suddenly-0.011
 two-0.010
 opened-0.009
 Under-0.009
Token racing
Token ID11717
Feature activation+1.19e+00

Pos logit contributions
 suddenly+0.043
 opened+0.041
 pretended+0.040
 two+0.039
 Suddenly+0.039
Neg logit contributions
beh-0.049
 unatt-0.048
 forward-0.047
ash-0.046
rav-0.045
Token each
Token ID1123
Feature activation+6.53e+00

Pos logit contributions
beh+0.048
 unatt+0.046
ash+0.046
 forward+0.045
rav+0.044
Neg logit contributions
 suddenly-0.027
 opened-0.025
 pretended-0.024
 two-0.024
 a-0.023
Token other
Token ID584
Feature activation+3.76e+00

Pos logit contributions
beh+0.224
 forward+0.223
 unatt+0.220
ash+0.218
 losers+0.211
Neg logit contributions
 suddenly-0.167
 opened-0.162
 pretended-0.156
 Suddenly-0.150
 two-0.148
Token Mom
Token ID11254
Feature activation+3.68e-01

Pos logit contributions
 suddenly+0.171
 opened+0.163
 pretended+0.160
 two+0.152
 Suddenly+0.150
Neg logit contributions
beh-0.310
 unatt-0.303
 forward-0.297
ash-0.294
rav-0.289
Tokenmy
Token ID1820
Feature activation-5.13e+00

Pos logit contributions
beh+0.016
 unatt+0.016
 mir+0.015
rav+0.015
 losers+0.015
Neg logit contributions
 suddenly-0.008
 opened-0.007
 pretended-0.006
 two-0.006
 was-0.006
Token was
Token ID373
Feature activation-3.63e+00

Pos logit contributions
 suddenly+0.076
 opened+0.069
 pretended+0.062
 two+0.056
 was+0.056
Neg logit contributions
beh-0.251
 unatt-0.250
rav-0.242
ash-0.242
 forward-0.240
Token worried
Token ID7960
Feature activation-8.95e-01

Pos logit contributions
 suddenly+0.102
 opened+0.098
 two+0.097
 a+0.095
 pretended+0.091
Neg logit contributions
beh-0.129
rav-0.126
ash-0.124
 unatt-0.121
aring-0.119
Token.
Token ID13
Feature activation+3.57e-01

Pos logit contributions
 suddenly+0.016
 a+0.016
 two+0.014
 was+0.014
 opened+0.013
Neg logit contributions
beh-0.043
rav-0.041
 unatt-0.041
 mir-0.040
 losers-0.040
Token Suddenly
Token ID24975
Feature activation-1.31e+01

Pos logit contributions
beh+0.015
 unatt+0.014
ash+0.014
 forward+0.014
rav+0.013
Neg logit contributions
 suddenly-0.008
 opened-0.007
 Suddenly-0.007
 two-0.007
 pretended-0.007
Token,
Token ID11
Feature activation-2.51e+00

Pos logit contributions
 suddenly+0.228
 pretended+0.222
 opened+0.219
 Suddenly+0.203
 two+0.196
Neg logit contributions
beh-0.528
 forward-0.528
 unatt-0.526
rav-0.511
baby-0.510
Token Baby
Token ID14801
Feature activation+1.06e+00

Pos logit contributions
 pretended+0.052
 opened+0.051
 Suddenly+0.050
 suddenly+0.050
 clicked+0.045
Neg logit contributions
 forward-0.090
 unatt-0.089
beh-0.089
baby-0.085
 losers-0.085
Token said
Token ID531
Feature activation-5.52e+00

Pos logit contributions
beh+0.043
 unatt+0.042
baby+0.042
 forward+0.042
ash+0.042
Neg logit contributions
 suddenly-0.018
 opened-0.017
 pretended-0.017
 Suddenly-0.016
 two-0.016
Token,
Token ID11
Feature activation-2.36e+00

Pos logit contributions
 suddenly+0.105
 a+0.096
 opened+0.092
 two+0.084
 Suddenly+0.081
Neg logit contributions
beh-0.271
ash-0.267
opl-0.265
 unatt-0.254
off-0.253
Token "
Token ID366
Feature activation+7.72e+00

Pos logit contributions
 suddenly+0.053
 a+0.049
 opened+0.049
 Suddenly+0.049
 two+0.047
Neg logit contributions
beh-0.110
 unatt-0.102
ash-0.102
opl-0.101
off-0.098
Token toy
Token ID13373
Feature activation-4.57e+00

Pos logit contributions
 suddenly+0.019
 opened+0.018
 pretended+0.018
 two+0.017
 Suddenly+0.017
Neg logit contributions
beh-0.024
 unatt-0.023
 forward-0.023
ash-0.022
rav-0.022
Token medical
Token ID3315
Feature activation+2.04e+00

Pos logit contributions
 suddenly+0.114
 opened+0.106
 pretended+0.104
 two+0.103
 a+0.097
Neg logit contributions
beh-0.173
 unatt-0.164
ash-0.162
 forward-0.161
rav-0.159
Token kit
Token ID6220
Feature activation-6.33e+00

Pos logit contributions
beh+0.073
 unatt+0.069
rav+0.068
aring+0.067
ash+0.067
Neg logit contributions
 suddenly-0.054
 opened-0.051
 two-0.051
 pretended-0.050
 a-0.048
Token.
Token ID13
Feature activation+2.37e-01

Pos logit contributions
 suddenly+0.143
 opened+0.132
 two+0.128
 pretended+0.127
 a+0.125
Neg logit contributions
beh-0.257
 unatt-0.244
rav-0.241
ash-0.240
 mir-0.238
Token She
Token ID1375
Feature activation-2.91e+00

Pos logit contributions
beh+0.009
 unatt+0.009
 forward+0.009
ash+0.009
rav+0.008
Neg logit contributions
 suddenly-0.006
 opened-0.005
 pretended-0.005
 two-0.005
 Suddenly-0.005
Token pretended
Token ID36766
Feature activation-1.31e+01

Pos logit contributions
 suddenly+0.048
 Suddenly+0.042
 two+0.042
 pretended+0.040
 opened+0.039
Neg logit contributions
beh-0.117
 losers-0.114
 forward-0.114
ash-0.111
 unatt-0.111
Token to
Token ID284
Feature activation+9.43e-01

Pos logit contributions
 suddenly+0.302
 opened+0.284
 pretended+0.269
 a+0.265
 two+0.263
Neg logit contributions
beh-0.530
ash-0.506
 unatt-0.504
 forward-0.494
rav-0.490
Token help
Token ID1037
Feature activation-3.67e-01

Pos logit contributions
beh+0.036
 unatt+0.036
 forward+0.035
ash+0.035
rav+0.034
Neg logit contributions
 suddenly-0.022
 opened-0.021
 pretended-0.020
 two-0.020
 a-0.019
Token her
Token ID607
Feature activation+2.40e+00

Pos logit contributions
 suddenly+0.008
 a+0.008
 opened+0.008
 two+0.007
 pretended+0.007
Neg logit contributions
beh-0.015
 unatt-0.015
rav-0.015
agging-0.014
ash-0.014
Token stuffed
Token ID22259
Feature activation+1.34e+00

Pos logit contributions
beh+0.084
 unatt+0.082
 forward+0.080
ash+0.079
baby+0.078
Neg logit contributions
 suddenly-0.061
 opened-0.058
 pretended-0.056
 Suddenly-0.055
 two-0.054
Token animals
Token ID4695
Feature activation-9.44e-01

Pos logit contributions
beh+0.046
 unatt+0.044
ash+0.043
 forward+0.043
baby+0.042
Neg logit contributions
 suddenly-0.037
 opened-0.035
 pretended-0.034
 Suddenly-0.033
 two-0.032
Token walking
Token ID6155
Feature activation-1.31e+00

Pos logit contributions
 suddenly+0.103
 two+0.097
 opened+0.097
 a+0.093
 pretended+0.093
Neg logit contributions
beh-0.137
 unatt-0.131
ash-0.131
rav-0.131
aring-0.128
Token in
Token ID287
Feature activation-4.67e+00

Pos logit contributions
 suddenly+0.032
 opened+0.031
 pretended+0.030
 two+0.029
 Suddenly+0.028
Neg logit contributions
beh-0.047
 forward-0.046
 unatt-0.046
ash-0.045
rav-0.044
Token the
Token ID262
Feature activation-1.77e+00

Pos logit contributions
 pretended+0.101
 suddenly+0.093
 opened+0.091
 Suddenly+0.086
 clicked+0.085
Neg logit contributions
 forward-0.176
 unatt-0.164
 future-0.161
overs-0.161
ash-0.158
Token park
Token ID3952
Feature activation-3.15e+00

Pos logit contributions
 pretended+0.050
 suddenly+0.049
 opened+0.048
 clicked+0.044
 Suddenly+0.043
Neg logit contributions
 unatt-0.055
 forward-0.055
beh-0.054
 future-0.052
ash-0.052
Token.
Token ID13
Feature activation+1.55e-01

Pos logit contributions
 suddenly+0.066
 opened+0.062
 pretended+0.060
 two+0.058
 Suddenly+0.056
Neg logit contributions
beh-0.127
 unatt-0.124
 forward-0.122
ash-0.121
rav-0.119
Token Suddenly
Token ID24975
Feature activation-1.31e+01

Pos logit contributions
 forward+0.006
beh+0.006
ash+0.006
 unatt+0.006
overs+0.006
Neg logit contributions
 suddenly-0.003
 pretended-0.003
 opened-0.003
 two-0.003
 clicked-0.003
Token,
Token ID11
Feature activation-2.79e+00

Pos logit contributions
 pretended+0.281
 opened+0.256
 pressed+0.239
 clicked+0.239
 suddenly+0.236
Neg logit contributions
 forward-0.466
 unatt-0.422
rav-0.419
overs-0.419
beh-0.418
Token Kim
Token ID6502
Feature activation-1.61e+00

Pos logit contributions
 pretended+0.060
 opened+0.059
 clicked+0.053
 Suddenly+0.053
 inserted+0.053
Neg logit contributions
 forward-0.097
 unatt-0.093
beh-0.090
overs-0.089
 hurricane-0.087
Token saw
Token ID2497
Feature activation-7.11e+00

Pos logit contributions
 two+0.025
 Suddenly+0.025
 pretended+0.025
 Under+0.025
 suddenly+0.025
Neg logit contributions
 unatt-0.062
baby-0.060
 forward-0.059
ash-0.059
beh-0.058
Token something
Token ID1223
Feature activation-4.52e+00

Pos logit contributions
 pretended+0.117
 opened+0.104
 Under+0.093
 suddenly+0.091
 Suddenly+0.086
Neg logit contributions
 unatt-0.292
 ambulance-0.288
beh-0.283
 permission-0.280
baby-0.280
Token that
Token ID326
Feature activation-6.49e+00

Pos logit contributions
 suddenly+0.111
 pretended+0.107
 opened+0.107
 two+0.101
 Suddenly+0.101
Neg logit contributions
beh-0.161
 unatt-0.158
 forward-0.156
ash-0.154
baby-0.149
Token playing
Token ID2712
Feature activation-2.23e+00

Pos logit contributions
beh+0.009
 forward+0.009
 unatt+0.009
ash+0.009
baby+0.009
Neg logit contributions
 suddenly-0.003
 opened-0.003
 pretended-0.003
 two-0.003
 Suddenly-0.003
Token with
Token ID351
Feature activation-5.73e+00

Pos logit contributions
 suddenly+0.039
 a+0.037
 pretended+0.035
 two+0.034
 opened+0.033
Neg logit contributions
beh-0.105
aring-0.099
rav-0.098
 unatt-0.098
 mir-0.096
Token her
Token ID607
Feature activation+4.38e-01

Pos logit contributions
 suddenly+0.151
 opened+0.146
 pretended+0.141
 Suddenly+0.136
 two+0.135
Neg logit contributions
beh-0.197
 unatt-0.193
ash-0.188
 forward-0.187
 losers-0.182
Token toys
Token ID14958
Feature activation-1.75e+00

Pos logit contributions
beh+0.016
 unatt+0.015
 forward+0.015
ash+0.015
rav+0.015
Neg logit contributions
 suddenly-0.011
 opened-0.011
 pretended-0.010
 two-0.010
 Suddenly-0.010
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
 suddenly+0.036
 opened+0.033
 pretended+0.032
 two+0.032
 a+0.031
Neg logit contributions
beh-0.077
rav-0.073
ash-0.071
 forward-0.070
aring-0.070
Token Suddenly
Token ID24975
Feature activation-1.31e+01

Pos logit contributions
 suddenly+0.003
 opened+0.003
 pretended+0.003
 two+0.003
 Suddenly+0.003
Neg logit contributions
beh-0.005
 unatt-0.005
 forward-0.005
ash-0.005
rav-0.005
Token she
Token ID673
Feature activation-1.91e+00

Pos logit contributions
 pretended+0.253
 suddenly+0.246
 opened+0.242
 Suddenly+0.226
 clicked+0.214
Neg logit contributions
 forward-0.494
beh-0.484
 unatt-0.480
rav-0.472
baby-0.471
Token saw
Token ID2497
Feature activation-7.22e+00

Pos logit contributions
 Suddenly+0.030
 Under+0.029
As+0.028
 two+0.028
 suddenly+0.027
Neg logit contributions
 unatt-0.073
 forward-0.072
baby-0.072
ash-0.070
 losers-0.070
Token something
Token ID1223
Feature activation-4.53e+00

Pos logit contributions
 pretended+0.129
 opened+0.120
 blasted+0.109
 Under+0.109
 suddenly+0.105
Neg logit contributions
 ambulance-0.274
 unatt-0.274
 permission-0.270
baby-0.268
beh-0.264
Token brown
Token ID7586
Feature activation-3.48e-01

Pos logit contributions
 suddenly+0.109
 opened+0.104
 pretended+0.102
 two+0.099
 Suddenly+0.097
Neg logit contributions
beh-0.167
 unatt-0.163
 forward-0.160
ash-0.159
rav-0.155
Token pe
Token ID613
Feature activation+2.40e-01

Pos logit contributions
 suddenly+0.008
 pretended+0.008
 opened+0.008
 Suddenly+0.007
 two+0.007
Neg logit contributions
 unatt-0.013
beh-0.012
 forward-0.012
ash-0.012
baby-0.012
Token home
Token ID1363
Feature activation+1.95e+00

Pos logit contributions
 suddenly+0.174
 opened+0.168
 pretended+0.164
 two+0.163
 Suddenly+0.161
Neg logit contributions
beh-0.090
 unatt-0.083
ash-0.080
 forward-0.076
rav-0.076
Token Lucky
Token ID27963
Feature activation-1.15e+00

Pos logit contributions
 forward+0.071
 unatt+0.070
aring+0.068
beh+0.068
overs+0.067
Neg logit contributions
 pretended-0.042
 suddenly-0.039
 two-0.037
 Suddenly-0.036
 Under-0.036
Token saw
Token ID2497
Feature activation-6.23e+00

Pos logit contributions
 suddenly+0.022
 opened+0.020
 pretended+0.020
 two+0.019
 Suddenly+0.019
Neg logit contributions
beh-0.047
 unatt-0.047
 forward-0.045
ash-0.045
rav-0.044
Token a
Token ID257
Feature activation-8.11e+00

Pos logit contributions
 pretended+0.165
 opened+0.160
 suddenly+0.154
 clicked+0.147
 blasted+0.144
Neg logit contributions
baby-0.199
 unatt-0.195
 ambulance-0.193
beh-0.190
 forward-0.189
Token dragon
Token ID10441
Feature activation-3.60e+00

Pos logit contributions
 suddenly+0.171
 opened+0.160
 two+0.152
 pretended+0.148
 a+0.144
Neg logit contributions
beh-0.356
ash-0.335
 unatt-0.326
 forward-0.323
off-0.317
Tokenfly
Token ID12254
Feature activation-1.31e+01

Pos logit contributions
 suddenly+0.093
 pretended+0.091
 Suddenly+0.090
 opened+0.089
 two+0.088
Neg logit contributions
 unatt-0.118
beh-0.117
 forward-0.113
aring-0.111
baby-0.110
Token.
Token ID13
Feature activation+4.85e-01

Pos logit contributions
 suddenly+0.320
 opened+0.304
 pretended+0.294
 two+0.287
 Suddenly+0.278
Neg logit contributions
beh-0.487
 unatt-0.471
ash-0.463
 forward-0.460
rav-0.454
Token The
Token ID383
Feature activation-3.34e+00

Pos logit contributions
beh+0.019
 unatt+0.018
ash+0.018
 forward+0.017
rav+0.017
Neg logit contributions
 suddenly-0.012
 opened-0.011
 Suddenly-0.011
 pretended-0.011
 two-0.011
Token dragon
Token ID10441
Feature activation-3.62e+00

Pos logit contributions
 suddenly+0.125
 Suddenly+0.122
 pretended+0.122
 opened+0.118
 clicked+0.118
Neg logit contributions
 losers-0.071
 unatt-0.070
 future-0.068
 forward-0.065
 ambulance-0.063
Tokenfly
Token ID12254
Feature activation-1.31e+01

Pos logit contributions
 Suddenly+0.102
 two+0.099
 suddenly+0.097
 Under+0.096
 pretended+0.092
Neg logit contributions
beh-0.102
aring-0.101
baby-0.098
 unatt-0.093
ash-0.090
Token told
Token ID1297
Feature activation-2.13e+00

Pos logit contributions
 suddenly+0.179
 Suddenly+0.172
 pretended+0.164
 two+0.160
 opened+0.150
Neg logit contributions
beh-0.556
 unatt-0.535
 losers-0.535
aring-0.532
 mir-0.527
Token a
Token ID257
Feature activation-1.18e+01

Pos logit contributions
 opened+0.072
 suddenly+0.071
 two+0.067
 pretended+0.066
 a+0.065
Neg logit contributions
beh-0.128
ash-0.127
 unatt-0.127
rav-0.124
 forward-0.123
Token big
Token ID1263
Feature activation-5.37e+00

Pos logit contributions
 suddenly+0.299
 opened+0.284
 pretended+0.277
 two+0.271
 Suddenly+0.262
Neg logit contributions
beh-0.432
 unatt-0.416
ash-0.408
 forward-0.405
rav-0.398
Token rocket
Token ID10701
Feature activation-6.99e+00

Pos logit contributions
 suddenly+0.130
 opened+0.127
 two+0.123
 a+0.120
 pretended+0.119
Neg logit contributions
beh-0.222
ash-0.200
rav-0.199
 unatt-0.196
aring-0.194
Token that
Token ID326
Feature activation-7.77e+00

Pos logit contributions
 suddenly+0.170
 opened+0.161
 pretended+0.157
 two+0.151
 Suddenly+0.145
Neg logit contributions
beh-0.266
 unatt-0.253
ash-0.251
 forward-0.249
rav-0.247
Token they
Token ID484
Feature activation+1.27e-01

Pos logit contributions
 suddenly+0.125
 opened+0.115
 pretended+0.111
 two+0.105
 Suddenly+0.101
Neg logit contributions
beh-0.352
 unatt-0.344
 forward-0.338
ash-0.337
rav-0.332
Token pretended
Token ID36766
Feature activation-1.30e+01

Pos logit contributions
beh+0.005
 unatt+0.005
 forward+0.005
ash+0.005
rav+0.005
Neg logit contributions
 suddenly-0.002
 opened-0.002
 pretended-0.002
 two-0.002
 Suddenly-0.002
Token to
Token ID284
Feature activation+8.89e-01

Pos logit contributions
 suddenly+0.370
 opened+0.353
 pretended+0.339
 a+0.334
 two+0.331
Neg logit contributions
beh-0.459
 unatt-0.437
ash-0.432
 forward-0.424
rav-0.414
Token fly
Token ID6129
Feature activation-9.72e-01

Pos logit contributions
beh+0.030
 unatt+0.030
 forward+0.029
 losers+0.029
ash+0.028
Neg logit contributions
 suddenly-0.022
 opened-0.021
 pretended-0.021
 Suddenly-0.020
 two-0.020
Token to
Token ID284
Feature activation+1.26e+00

Pos logit contributions
 suddenly+0.023
 opened+0.021
 pretended+0.021
 a+0.021
 two+0.020
Neg logit contributions
beh-0.039
 unatt-0.037
ash-0.036
aring-0.036
rav-0.036
Token the
Token ID262
Feature activation-2.28e-01

Pos logit contributions
beh+0.059
 unatt+0.057
ash+0.056
 forward+0.055
aring+0.055
Neg logit contributions
 suddenly-0.020
 opened-0.019
 pretended-0.018
 two-0.018
 a-0.017
Token moon
Token ID8824
Feature activation-7.11e+00

Pos logit contributions
 suddenly+0.005
 opened+0.005
 pretended+0.005
 two+0.005
 Suddenly+0.005
Neg logit contributions
beh-0.009
 unatt-0.008
ash-0.008
 forward-0.008
rav-0.008
Token fun
Token ID1257
Feature activation+2.30e+00

Pos logit contributions
beh+0.080
rav+0.078
ash+0.077
 forward+0.075
 unatt+0.075
Neg logit contributions
 suddenly-0.064
 opened-0.061
 two-0.059
 a-0.058
 pretended-0.057
Token!
Token ID0
Feature activation-1.29e+00

Pos logit contributions
beh+0.091
 unatt+0.085
ash+0.084
 forward+0.084
aring+0.082
Neg logit contributions
 suddenly-0.057
 pretended-0.051
 two-0.050
 opened-0.050
 a-0.050
Token
Token ID220
Feature activation-9.89e-02

Pos logit contributions
 suddenly+0.030
 opened+0.028
 pretended+0.028
 two+0.027
 Suddenly+0.027
Neg logit contributions
beh-0.049
 unatt-0.048
ash-0.047
 forward-0.047
rav-0.046
Token
Token ID198
Feature activation-1.38e+00

Pos logit contributions
 suddenly+0.001
 opened+0.001
 pretended+0.001
 two+0.001
 Suddenly+0.001
Neg logit contributions
beh-0.005
 unatt-0.005
 forward-0.004
ash-0.004
rav-0.004
Token
Token ID198
Feature activation-1.19e+00

Pos logit contributions
 suddenly+0.029
 pretended+0.029
 opened+0.029
 two+0.025
 clicked+0.024
Neg logit contributions
beh-0.053
ash-0.052
 forward-0.051
 unatt-0.051
baby-0.051
TokenSuddenly
Token ID38582
Feature activation-1.30e+01

Pos logit contributions
 suddenly+0.026
 opened+0.025
 pretended+0.024
 two+0.023
 Suddenly+0.023
Neg logit contributions
beh-0.047
 unatt-0.046
ash-0.045
 forward-0.045
rav-0.044
Token,
Token ID11
Feature activation-2.64e+00

Pos logit contributions
 pretended+0.240
 suddenly+0.235
 opened+0.229
 Suddenly+0.214
 clicked+0.200
Neg logit contributions
 forward-0.509
beh-0.495
 unatt-0.491
rav-0.485
baby-0.479
Token L
Token ID406
Feature activation-1.45e+00

Pos logit contributions
 pretended+0.053
 opened+0.052
 suddenly+0.051
 Suddenly+0.051
 clicked+0.047
Neg logit contributions
 forward-0.098
beh-0.095
 unatt-0.094
overs-0.091
 losers-0.091
Tokenila
Token ID10102
Feature activation-3.09e+00

Pos logit contributions
 pretended+0.050
 suddenly+0.050
 opened+0.047
 Suddenly+0.047
 two+0.046
Neg logit contributions
ash-0.039
beh-0.037
rav-0.036
baby-0.036
aring-0.036
Token heard
Token ID2982
Feature activation-7.17e+00

Pos logit contributions
 suddenly+0.047
 pretended+0.044
 opened+0.043
 Suddenly+0.042
 two+0.042
Neg logit contributions
 unatt-0.132
beh-0.132
 forward-0.128
ash-0.127
aring-0.126
Token a
Token ID257
Feature activation-8.62e+00

Pos logit contributions
 suddenly+0.083
 pretended+0.083
 opened+0.076
 Suddenly+0.064
 two+0.058
Neg logit contributions
beh-0.336
 forward-0.329
 unatt-0.329
baby-0.326
ash-0.325
Token on
Token ID319
Feature activation-4.42e+00

Pos logit contributions
aring+0.005
baby+0.005
beh+0.005
 unatt+0.005
 losers+0.005
Neg logit contributions
 suddenly-0.002
 two-0.002
 pretended-0.002
 Suddenly-0.002
 opened-0.002
Token a
Token ID257
Feature activation-1.12e+01

Pos logit contributions
 suddenly+0.087
 opened+0.081
 two+0.077
 pretended+0.077
 a+0.073
Neg logit contributions
beh-0.190
 unatt-0.183
ash-0.180
 forward-0.179
rav-0.178
Token blanket
Token ID18447
Feature activation-3.09e+00

Pos logit contributions
 suddenly+0.247
 opened+0.236
 a+0.221
 pretended+0.220
 two+0.218
Neg logit contributions
beh-0.490
ash-0.434
rav-0.430
aring-0.423
 unatt-0.421
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
 suddenly+0.070
 opened+0.066
 pretended+0.064
 two+0.062
 Suddenly+0.060
Neg logit contributions
beh-0.120
 unatt-0.116
ash-0.114
 forward-0.114
rav-0.112
Token She
Token ID1375
Feature activation-3.26e+00

Pos logit contributions
 suddenly+0.003
 opened+0.003
 pretended+0.003
 two+0.003
 Suddenly+0.003
Neg logit contributions
beh-0.005
 unatt-0.005
 forward-0.005
ash-0.005
rav-0.005
Token pretended
Token ID36766
Feature activation-1.30e+01

Pos logit contributions
 suddenly+0.060
 Suddenly+0.054
 two+0.052
 pretended+0.049
 opened+0.048
Neg logit contributions
beh-0.123
ash-0.121
 losers-0.121
 mir-0.120
 forward-0.120
Token they
Token ID484
Feature activation+6.61e-01

Pos logit contributions
 suddenly+0.355
 opened+0.340
 pretended+0.325
 two+0.321
 a+0.317
Neg logit contributions
beh-0.463
 unatt-0.442
ash-0.438
 forward-0.432
rav-0.422
Token were
Token ID547
Feature activation-1.34e+00

Pos logit contributions
beh+0.026
 unatt+0.025
 forward+0.025
ash+0.024
rav+0.024
Neg logit contributions
 suddenly-0.013
 Suddenly-0.013
 opened-0.012
 two-0.012
 pretended-0.012
Token having
Token ID1719
Feature activation-1.57e+00

Pos logit contributions
 suddenly+0.035
 opened+0.033
 pretended+0.033
 two+0.032
 Suddenly+0.031
Neg logit contributions
beh-0.048
 unatt-0.046
ash-0.045
 forward-0.045
rav-0.045
Token a
Token ID257
Feature activation-8.69e+00

Pos logit contributions
 suddenly+0.024
 opened+0.022
 pretended+0.022
 two+0.021
 a+0.020
Neg logit contributions
beh-0.074
 unatt-0.072
ash-0.071
 forward-0.070
aring-0.070
Token tea
Token ID8887
Feature activation-4.42e-01

Pos logit contributions
 suddenly+0.273
 opened+0.262
 pretended+0.256
 two+0.251
 Suddenly+0.247
Neg logit contributions
beh-0.256
 unatt-0.250
 forward-0.245
ash-0.242
rav-0.237
Token had
Token ID550
Feature activation-6.28e+00

Pos logit contributions
 suddenly+0.073
 opened+0.070
 pretended+0.068
 two+0.064
 Suddenly+0.061
Neg logit contributions
beh-0.161
 unatt-0.156
ash-0.154
 forward-0.153
rav-0.151
Token so
Token ID523
Feature activation-1.54e+00

Pos logit contributions
 suddenly+0.097
 two+0.094
 opened+0.093
 a+0.093
 pretended+0.088
Neg logit contributions
beh-0.301
 unatt-0.293
ash-0.291
rav-0.289
aring-0.289
Token much
Token ID881
Feature activation+4.96e+00

Pos logit contributions
 suddenly+0.052
 opened+0.051
 pretended+0.050
 two+0.049
 Suddenly+0.048
Neg logit contributions
beh-0.042
 unatt-0.041
ash-0.040
 forward-0.039
rav-0.038
Token fun
Token ID1257
Feature activation+5.07e+00

Pos logit contributions
beh+0.142
 unatt+0.137
ash+0.133
 forward+0.133
rav+0.129
Neg logit contributions
 suddenly-0.165
 opened-0.158
 pretended-0.155
 two-0.152
 Suddenly-0.149
Token!
Token ID0
Feature activation-5.16e-01

Pos logit contributions
beh+0.202
 unatt+0.196
ash+0.192
rav+0.191
 forward+0.189
Neg logit contributions
 suddenly-0.119
 pretended-0.105
 opened-0.105
 two-0.104
 a-0.101
Token Suddenly
Token ID24975
Feature activation-1.30e+01

Pos logit contributions
 suddenly+0.010
 opened+0.010
 pretended+0.009
 two+0.009
 Suddenly+0.009
Neg logit contributions
beh-0.021
 unatt-0.021
ash-0.020
 forward-0.020
rav-0.020
Token,
Token ID11
Feature activation-2.39e+00

Pos logit contributions
 suddenly+0.233
 opened+0.227
 pretended+0.226
 Suddenly+0.208
 two+0.196
Neg logit contributions
beh-0.523
 forward-0.523
 unatt-0.516
rav-0.507
ash-0.504
Token they
Token ID484
Feature activation+5.03e-01

Pos logit contributions
 opened+0.052
 suddenly+0.051
 pretended+0.051
 Suddenly+0.049
 clicked+0.045
Neg logit contributions
 forward-0.085
beh-0.085
 unatt-0.083
 losers-0.081
overs-0.081
Token heard
Token ID2982
Feature activation-7.28e+00

Pos logit contributions
 unatt+0.022
 forward+0.022
beh+0.021
ash+0.021
baby+0.021
Neg logit contributions
 Suddenly-0.007
 suddenly-0.007
 pretended-0.006
 opened-0.006
 two-0.006
Token a
Token ID257
Feature activation-8.82e+00

Pos logit contributions
 suddenly+0.073
 pretended+0.066
 opened+0.065
 Suddenly+0.053
 two+0.050
Neg logit contributions
beh-0.360
 forward-0.351
 unatt-0.351
ash-0.349
baby-0.347
Token loud
Token ID7812
Feature activation+1.06e+00

Pos logit contributions
 suddenly+0.196
 opened+0.190
 two+0.176
 a+0.174
 was+0.161
Neg logit contributions
beh-0.381
ash-0.368
 unatt-0.357
overs-0.349
ags-0.344
Token outside
Token ID2354
Feature activation-4.45e+00

Pos logit contributions
 suddenly+0.014
 pretended+0.013
 opened+0.012
 Suddenly+0.011
 clicked+0.010
Neg logit contributions
 forward-0.043
beh-0.043
 unatt-0.043
overs-0.042
ash-0.042
Token with
Token ID351
Feature activation-5.38e+00

Pos logit contributions
 suddenly+0.096
 opened+0.090
 pretended+0.086
 two+0.085
 Suddenly+0.081
Neg logit contributions
beh-0.183
 unatt-0.175
ash-0.172
 forward-0.171
rav-0.170
Token his
Token ID465
Feature activation-8.16e-01

Pos logit contributions
 suddenly+0.121
 opened+0.114
 pretended+0.111
 two+0.109
 Suddenly+0.103
Neg logit contributions
beh-0.211
 unatt-0.205
ash-0.201
 forward-0.200
rav-0.198
Token friends
Token ID2460
Feature activation-1.41e+00

Pos logit contributions
 suddenly+0.021
 opened+0.020
 pretended+0.020
 two+0.019
 Suddenly+0.019
Neg logit contributions
beh-0.028
 unatt-0.028
 forward-0.027
ash-0.027
rav-0.026
Token.
Token ID13
Feature activation+1.72e-02

Pos logit contributions
 suddenly+0.034
 opened+0.032
 pretended+0.031
 two+0.030
 a+0.029
Neg logit contributions
beh-0.055
 unatt-0.052
ash-0.051
rav-0.051
 forward-0.051
Token Suddenly
Token ID24975
Feature activation-1.30e+01

Pos logit contributions
beh+0.001
 unatt+0.001
 forward+0.001
ash+0.001
rav+0.001
Neg logit contributions
 suddenly-0.000
 opened-0.000
 pretended-0.000
 two-0.000
 Suddenly-0.000
Token,
Token ID11
Feature activation-2.79e+00

Pos logit contributions
 pretended+0.247
 opened+0.244
 suddenly+0.241
 Suddenly+0.223
 clicked+0.217
Neg logit contributions
 forward-0.492
beh-0.475
 unatt-0.471
rav-0.463
overs-0.458
Token another
Token ID1194
Feature activation-2.71e+00

Pos logit contributions
 opened+0.060
 pretended+0.057
 Suddenly+0.055
 clicked+0.054
 inserted+0.054
Neg logit contributions
 forward-0.097
beh-0.094
 unatt-0.094
 hurricane-0.091
overs-0.090
Token boy
Token ID2933
Feature activation-6.04e+00

Pos logit contributions
 suddenly+0.054
 opened+0.052
 pretended+0.051
 Suddenly+0.048
 two+0.046
Neg logit contributions
beh-0.106
 forward-0.105
 unatt-0.103
ash-0.103
baby-0.102
Token,
Token ID11
Feature activation-2.32e+00

Pos logit contributions
 two+0.099
 suddenly+0.097
 Suddenly+0.092
 pretended+0.091
 opened+0.091
Neg logit contributions
beh-0.242
 unatt-0.240
 forward-0.238
ash-0.233
baby-0.231
Token who
Token ID508
Feature activation-5.17e+00

Pos logit contributions
 suddenly+0.045
 pretended+0.045
 opened+0.044
 Suddenly+0.042
 two+0.041
Neg logit contributions
 forward-0.086
beh-0.085
 unatt-0.084
baby-0.080
rav-0.079
Token on
Token ID319
Feature activation-2.29e+00

Pos logit contributions
 suddenly+0.018
 opened+0.017
 pretended+0.017
 two+0.016
 Suddenly+0.016
Neg logit contributions
beh-0.038
 unatt-0.037
ash-0.036
 forward-0.036
rav-0.035
Token the
Token ID262
Feature activation-1.84e+00

Pos logit contributions
 suddenly+0.038
 opened+0.034
 two+0.033
 a+0.031
 pretended+0.031
Neg logit contributions
beh-0.108
 unatt-0.103
ash-0.102
rav-0.102
aring-0.101
Token jungle
Token ID20712
Feature activation-5.29e+00

Pos logit contributions
 suddenly+0.041
 two+0.039
 opened+0.038
 a+0.037
 pretended+0.036
Neg logit contributions
beh-0.077
rav-0.071
aring-0.071
ash-0.071
 unatt-0.070
Token gym
Token ID11550
Feature activation-2.02e+00

Pos logit contributions
 suddenly+0.124
 opened+0.118
 two+0.112
 pretended+0.111
 a+0.109
Neg logit contributions
beh-0.209
rav-0.199
 unatt-0.197
ash-0.196
 forward-0.194
Token.
Token ID13
Feature activation+1.10e-01

Pos logit contributions
 suddenly+0.047
 opened+0.044
 pretended+0.042
 two+0.041
 Suddenly+0.040
Neg logit contributions
beh-0.080
 unatt-0.076
ash-0.075
rav-0.075
 forward-0.074
Token Suddenly
Token ID24975
Feature activation-1.29e+01

Pos logit contributions
beh+0.004
 unatt+0.004
ash+0.004
 forward+0.004
rav+0.004
Neg logit contributions
 suddenly-0.002
 opened-0.002
 pretended-0.002
 two-0.002
 Suddenly-0.002
Token,
Token ID11
Feature activation-2.63e+00

Pos logit contributions
 suddenly+0.230
 pretended+0.225
 opened+0.221
 Suddenly+0.202
 two+0.192
Neg logit contributions
beh-0.517
 forward-0.516
 unatt-0.512
rav-0.499
ash-0.498
Token he
Token ID339
Feature activation-2.12e+00

Pos logit contributions
 opened+0.053
 pretended+0.052
 suddenly+0.050
 Suddenly+0.049
 clicked+0.047
Neg logit contributions
 forward-0.095
 unatt-0.095
beh-0.094
overs-0.091
 losers-0.090
Token heard
Token ID2982
Feature activation-7.27e+00

Pos logit contributions
 suddenly+0.030
 pretended+0.029
 Suddenly+0.029
 opened+0.029
 two+0.028
Neg logit contributions
 unatt-0.087
 forward-0.086
beh-0.084
ash-0.084
 mir-0.083
Token a
Token ID257
Feature activation-8.89e+00

Pos logit contributions
 suddenly+0.073
 pretended+0.073
 opened+0.065
 Suddenly+0.052
 clicked+0.048
Neg logit contributions
beh-0.346
 unatt-0.343
baby-0.340
 forward-0.339
ash-0.334
Token very
Token ID845
Feature activation+6.46e+00

Pos logit contributions
 suddenly+0.200
 opened+0.196
 two+0.180
 a+0.177
 Suddenly+0.168
Neg logit contributions
beh-0.373
ash-0.364
 unatt-0.352
overs-0.349
ags-0.341
Token You
Token ID921
Feature activation+3.41e+00

Pos logit contributions
beh+0.027
 unatt+0.025
 forward+0.025
ash+0.024
rav+0.024
Neg logit contributions
 suddenly-0.056
 opened-0.055
 pretended-0.054
 two-0.052
 Suddenly-0.051
Token are
Token ID389
Feature activation+2.66e+00

Pos logit contributions
 losers+0.076
beh+0.073
 unatt+0.071
rav+0.071
 forward+0.070
Neg logit contributions
 suddenly-0.129
 Suddenly-0.124
Suddenly-0.112
 pretended-0.111
 opened-0.110
Token the
Token ID262
Feature activation+5.65e-01

Pos logit contributions
beh+0.105
 unatt+0.103
 forward+0.102
 losers+0.099
ash+0.098
Neg logit contributions
 suddenly-0.058
 opened-0.054
 pretended-0.053
 Suddenly-0.051
 two-0.049
Token best
Token ID1266
Feature activation+2.56e+00

Pos logit contributions
beh+0.020
ash+0.019
 unatt+0.019
aring+0.019
rav+0.018
Neg logit contributions
 two-0.016
 suddenly-0.016
 a-0.014
 opened-0.014
 pretended-0.014
Token co
Token ID763
Feature activation+6.53e+00

Pos logit contributions
beh+0.090
 unatt+0.086
ash+0.084
 forward+0.081
rav+0.080
Neg logit contributions
 suddenly-0.073
 two-0.069
 opened-0.069
 pretended-0.067
 a-0.065
Token-
Token ID12
Feature activation+1.38e+01

Pos logit contributions
beh+0.194
 unatt+0.192
 mir+0.189
 future+0.189
ash+0.187
Neg logit contributions
 suddenly-0.200
 two-0.185
 opened-0.185
 a-0.181
 pretended-0.181
Tokenp
Token ID79
Feature activation-3.80e-01

Pos logit contributions
 unatt+0.309
beh+0.299
ash+0.294
 mir+0.283
agging+0.282
Neg logit contributions
 suddenly-0.526
 opened-0.513
 two-0.504
 a-0.501
 pretended-0.494
Tokenilot
Token ID23439
Feature activation-7.86e+00

Pos logit contributions
 suddenly+0.009
 two+0.009
 opened+0.009
 a+0.009
 pretended+0.008
Neg logit contributions
beh-0.015
 unatt-0.014
ash-0.013
 forward-0.013
 future-0.013
Token ever
Token ID1683
Feature activation+5.30e+00

Pos logit contributions
 suddenly+0.194
 a+0.194
 two+0.193
 was+0.176
 pretended+0.176
Neg logit contributions
beh-0.322
ocol-0.304
ash-0.301
 unatt-0.285
 mir-0.284
Token."
Token ID526
Feature activation+1.58e+00

Pos logit contributions
beh+0.175
ash+0.164
 unatt+0.164
 forward+0.160
rav+0.159
Neg logit contributions
 suddenly-0.156
 opened-0.151
 pretended-0.148
 two-0.145
 a-0.141
Token They
Token ID1119
Feature activation-1.16e+00

Pos logit contributions
 forward+0.058
ash+0.056
 unatt+0.056
beh+0.055
overs+0.055
Neg logit contributions
 suddenly-0.038
 opened-0.035
 pretended-0.035
 clicked-0.030
 two-0.030
Token the
Token ID262
Feature activation+4.92e-01

Pos logit contributions
 suddenly+0.011
 opened+0.010
 two+0.009
 pretended+0.009
 a+0.009
Neg logit contributions
beh-0.026
ash-0.025
 unatt-0.025
aring-0.024
agging-0.024
Token butterfly
Token ID35113
Feature activation-2.17e+00

Pos logit contributions
beh+0.017
 unatt+0.017
ash+0.016
 forward+0.016
rav+0.016
Neg logit contributions
 suddenly-0.013
 opened-0.013
 two-0.012
 pretended-0.012
 a-0.012
Token could
Token ID714
Feature activation-1.09e+00

Pos logit contributions
 suddenly+0.023
 opened+0.021
 pretended+0.018
 was+0.015
 two+0.014
Neg logit contributions
beh-0.117
ash-0.114
 unatt-0.113
rav-0.113
 forward-0.112
Token enjoy
Token ID2883
Feature activation+1.43e+00

Pos logit contributions
 suddenly+0.026
 opened+0.025
 pretended+0.023
 two+0.023
 a+0.022
Neg logit contributions
beh-0.044
ash-0.043
 unatt-0.042
 forward-0.041
baby-0.041
Token it
Token ID340
Feature activation+4.06e+00

Pos logit contributions
beh+0.072
ash+0.070
aring+0.069
rav+0.068
baby+0.068
Neg logit contributions
 suddenly-0.025
 a-0.024
 two-0.021
 opened-0.019
 was-0.017
Token too
Token ID1165
Feature activation+9.23e+00

Pos logit contributions
beh+0.181
rav+0.177
 mir+0.174
baby+0.172
ocol+0.172
Neg logit contributions
 suddenly-0.083
 a-0.080
 two-0.075
 opened-0.074
 pretended-0.065
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
beh+0.383
 unatt+0.364
rav+0.363
ash+0.362
 losers+0.357
Neg logit contributions
 suddenly-0.211
 opened-0.197
 two-0.191
 a-0.189
 Suddenly-0.174
Token She
Token ID1375
Feature activation-1.64e+00

Pos logit contributions
beh+0.050
 unatt+0.049
 forward+0.048
ash+0.048
rav+0.047
Neg logit contributions
 suddenly-0.036
 opened-0.035
 pretended-0.034
 two-0.033
 Suddenly-0.031
Token watched
Token ID7342
Feature activation-2.40e+00

Pos logit contributions
 suddenly+0.030
 two+0.029
 Suddenly+0.029
 pretended+0.027
 opened+0.027
Neg logit contributions
beh-0.062
 unatt-0.061
 forward-0.060
 losers-0.059
 mir-0.058
Token as
Token ID355
Feature activation-5.18e+00

Pos logit contributions
 suddenly+0.044
 opened+0.040
 pretended+0.038
 two+0.038
 Suddenly+0.036
Neg logit contributions
beh-0.107
 unatt-0.103
ash-0.102
rav-0.100
 forward-0.099
Token the
Token ID262
Feature activation+5.84e-01

Pos logit contributions
 suddenly+0.105
 pretended+0.104
 opened+0.103
 Suddenly+0.096
 two+0.090
Neg logit contributions
 forward-0.201
beh-0.199
 unatt-0.196
rav-0.191
overs-0.189
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
 suddenly+0.050
 a+0.046
 two+0.044
 opened+0.040
 Suddenly+0.036
Neg logit contributions
beh-0.222
ash-0.216
 unatt-0.216
opl-0.216
ksh-0.208
Token "
Token ID366
Feature activation+8.96e+00

Pos logit contributions
 suddenly+0.024
 Suddenly+0.023
 opened+0.022
 two+0.022
 a+0.022
Neg logit contributions
beh-0.058
 unatt-0.054
ash-0.054
opl-0.051
off-0.051
TokenYou
Token ID1639
Feature activation+3.91e+00

Pos logit contributions
beh+0.282
 unatt+0.278
 forward+0.267
ash+0.266
aring+0.259
Neg logit contributions
 suddenly-0.272
 opened-0.255
 pretended-0.254
 two-0.250
 Suddenly-0.245
Token are
Token ID389
Feature activation+2.83e+00

Pos logit contributions
beh+0.110
 losers+0.108
 forward+0.105
 unatt+0.101
ash+0.099
Neg logit contributions
 suddenly-0.124
 Suddenly-0.116
 opened-0.111
 pretended-0.110
 clicked-0.104
Token getting
Token ID1972
Feature activation+6.88e+00

Pos logit contributions
beh+0.112
 unatt+0.109
ash+0.108
rav+0.108
aring+0.106
Neg logit contributions
 suddenly-0.063
 opened-0.062
 two-0.061
 a-0.060
 pretended-0.059
Token too
Token ID1165
Feature activation+9.28e+00

Pos logit contributions
beh+0.267
rav+0.262
 unatt+0.260
ash+0.259
opl+0.259
Neg logit contributions
 suddenly-0.160
 opened-0.152
 two-0.150
 a-0.148
 pretended-0.142
Token crazy
Token ID7165
Feature activation+3.37e+00

Pos logit contributions
beh+0.337
 unatt+0.328
ash+0.320
rav+0.316
 forward+0.314
Neg logit contributions
 suddenly-0.241
 opened-0.233
 two-0.226
 pretended-0.219
 a-0.214
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
beh+0.134
 unatt+0.129
rav+0.126
ash+0.124
 mir+0.124
Neg logit contributions
 suddenly-0.077
 two-0.071
 opened-0.070
 pretended-0.070
 a-0.069
Token I
Token ID314
Feature activation+5.09e+00

Pos logit contributions
 suddenly+0.023
 two+0.022
 opened+0.021
 a+0.021
 pretended+0.021
Neg logit contributions
beh-0.050
 unatt-0.047
ash-0.046
opl-0.045
rav-0.045
Token don
Token ID836
Feature activation+4.63e+00

Pos logit contributions
beh+0.165
 unatt+0.160
ash+0.156
 forward+0.156
rav+0.152
Neg logit contributions
 suddenly-0.148
 opened-0.141
 pretended-0.138
 two-0.135
 Suddenly-0.132
Token't
Token ID470
Feature activation+7.53e-03

Pos logit contributions
 unatt+0.224
beh+0.217
ash+0.215
 mir+0.215
rav+0.212
Neg logit contributions
 suddenly-0.075
 two-0.072
 a-0.066
 opened-0.062
 was-0.055
Token said
Token ID531
Feature activation-4.78e+00

Pos logit contributions
 suddenly+0.040
 two+0.039
 pretended+0.036
 Suddenly+0.036
 opened+0.036
Neg logit contributions
beh-0.096
 losers-0.091
 mir-0.090
rav-0.089
ash-0.089
Token to
Token ID284
Feature activation+1.84e+00

Pos logit contributions
 suddenly+0.066
 a+0.059
 two+0.056
 opened+0.055
 Suddenly+0.045
Neg logit contributions
beh-0.256
ash-0.256
 unatt-0.249
opl-0.248
ksh-0.239
Token her
Token ID607
Feature activation+2.87e+00

Pos logit contributions
beh+0.062
 unatt+0.060
 forward+0.059
ash+0.059
baby+0.058
Neg logit contributions
 suddenly-0.050
 opened-0.048
 pretended-0.047
 two-0.044
 Suddenly-0.044
Token dad
Token ID9955
Feature activation+3.00e+00

Pos logit contributions
 forward+0.079
 ambulance+0.078
 unatt+0.077
baby+0.076
beh+0.075
Neg logit contributions
 suddenly-0.087
 Suddenly-0.083
 pretended-0.082
 opened-0.081
 clicked-0.078
Token,
Token ID11
Feature activation-1.35e+00

Pos logit contributions
beh+0.148
 unatt+0.144
ash+0.140
 losers+0.138
 forward+0.137
Neg logit contributions
 suddenly-0.041
 opened-0.037
 two-0.035
 pretended-0.034
 a-0.032
Token "
Token ID366
Feature activation+8.69e+00

Pos logit contributions
 suddenly+0.032
 opened+0.029
 a+0.029
 two+0.029
 Suddenly+0.029
Neg logit contributions
beh-0.058
ash-0.055
 unatt-0.054
off-0.052
rav-0.051
TokenLook
Token ID8567
Feature activation-4.52e+00

Pos logit contributions
beh+0.297
 unatt+0.289
ash+0.279
 forward+0.278
aring+0.271
Neg logit contributions
 suddenly-0.247
 opened-0.230
 pretended-0.227
 two-0.224
 Suddenly-0.219
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
 suddenly+0.088
 opened+0.081
 pretended+0.078
 two+0.077
 a+0.073
Neg logit contributions
beh-0.195
 unatt-0.187
ash-0.183
 forward-0.180
rav-0.179
Token monkeys
Token ID26697
Feature activation-6.73e-01

Pos logit contributions
 suddenly+0.030
 opened+0.028
 two+0.028
 pretended+0.027
 a+0.026
Neg logit contributions
beh-0.044
 unatt-0.041
ash-0.041
 forward-0.040
agging-0.039
Token!
Token ID0
Feature activation+8.33e-01

Pos logit contributions
 suddenly+0.008
 opened+0.008
 two+0.007
 a+0.007
 pretended+0.007
Neg logit contributions
beh-0.034
 unatt-0.033
ash-0.032
 forward-0.032
ksh-0.032
Token Can
Token ID1680
Feature activation+2.36e+00

Pos logit contributions
beh+0.027
 unatt+0.026
ash+0.025
 forward+0.025
agging+0.024
Neg logit contributions
 suddenly-0.025
 opened-0.024
 two-0.023
 pretended-0.023
 Suddenly-0.023
Token I
Token ID314
Feature activation+5.06e+00

Pos logit contributions
beh+0.085
ash+0.083
 forward+0.078
opl+0.078
agging+0.077
Neg logit contributions
 suddenly-0.088
 opened-0.083
 two-0.080
 a-0.079
 pretended-0.077
Token have
Token ID423
Feature activation-5.01e-03

Pos logit contributions
beh+0.218
 unatt+0.209
ash+0.200
rav+0.199
opl+0.199
Neg logit contributions
 opened-0.114
 suddenly-0.112
 pretended-0.103
 a-0.100
 two-0.100
Token some
Token ID617
Feature activation-5.52e-01

Pos logit contributions
 suddenly+0.000
 opened+0.000
 pretended+0.000
 two+0.000
 Suddenly+0.000
Neg logit contributions
beh-0.000
 unatt-0.000
 forward-0.000
ash-0.000
rav-0.000
Token water
Token ID1660
Feature activation-5.97e-01

Pos logit contributions
 suddenly+0.013
 opened+0.012
 two+0.012
 pretended+0.011
 a+0.011
Neg logit contributions
beh-0.022
 unatt-0.021
 forward-0.021
rav-0.021
ash-0.021
Token,
Token ID11
Feature activation-5.06e-01

Pos logit contributions
 suddenly+0.012
 a+0.012
 opened+0.011
 two+0.011
 pretended+0.010
Neg logit contributions
beh-0.028
rav-0.025
opl-0.025
aring-0.025
agging-0.024
Token please
Token ID3387
Feature activation+9.28e+00

Pos logit contributions
 suddenly+0.012
 opened+0.011
 two+0.011
 pretended+0.011
 a+0.011
Neg logit contributions
beh-0.021
 unatt-0.020
ash-0.019
 forward-0.019
rav-0.019
Token?"
Token ID1701
Feature activation-6.09e-01

Pos logit contributions
beh+0.293
 unatt+0.286
 forward+0.279
ash+0.279
rav+0.272
Neg logit contributions
 suddenly-0.268
 opened-0.255
 pretended-0.253
 two-0.244
 Suddenly-0.244
Token the
Token ID262
Feature activation+9.98e-01

Pos logit contributions
 inserted+0.017
 pretended+0.017
 opened+0.017
 suddenly+0.017
 clicked+0.016
Neg logit contributions
 Go-0.016
baby-0.015
 losers-0.015
 ambulance-0.015
 future-0.015
Token yellow
Token ID7872
Feature activation-4.91e-01

Pos logit contributions
 unatt+0.031
beh+0.030
 forward+0.030
baby+0.030
ash+0.029
Neg logit contributions
 suddenly-0.028
 pretended-0.027
 opened-0.026
 Suddenly-0.025
 clicked-0.024
Token flower
Token ID15061
Feature activation-1.93e+00

Pos logit contributions
 suddenly+0.013
 opened+0.012
 pretended+0.012
 two+0.011
 Suddenly+0.011
Neg logit contributions
beh-0.018
 unatt-0.017
ash-0.017
 forward-0.017
rav-0.016
Token asks
Token ID7893
Feature activation-2.51e+00

Pos logit contributions
 suddenly+0.044
 opened+0.042
 pretended+0.040
 two+0.039
 Suddenly+0.037
Neg logit contributions
beh-0.076
 unatt-0.073
ash-0.072
 forward-0.071
rav-0.070
Token swing
Token ID9628
Feature activation-2.53e-02

Pos logit contributions
beh+0.095
 unatt+0.092
 forward+0.090
ash+0.090
rav+0.088
Neg logit contributions
 suddenly-0.068
 opened-0.065
 pretended-0.064
 two-0.062
 Suddenly-0.060
Token,
Token ID11
Feature activation-6.05e-01

Pos logit contributions
 a+0.001
 suddenly+0.001
 two+0.000
 pretended+0.000
 opened+0.000
Neg logit contributions
beh-0.001
 mir-0.001
ife-0.001
aring-0.001
ash-0.001
Token but
Token ID475
Feature activation-3.65e+00

Pos logit contributions
 a+0.014
 suddenly+0.013
 two+0.013
 opened+0.013
 pretended+0.013
Neg logit contributions
beh-0.027
ash-0.026
opl-0.025
agging-0.024
ocol-0.024
Token not
Token ID407
Feature activation+9.57e-01

Pos logit contributions
 suddenly+0.106
 two+0.102
 opened+0.100
 a+0.098
 pretended+0.094
Neg logit contributions
beh-0.129
ash-0.124
 unatt-0.120
opl-0.120
agging-0.116
Token too
Token ID1165
Feature activation+9.14e+00

Pos logit contributions
beh+0.035
ash+0.034
 forward+0.034
overs+0.034
 unatt+0.034
Neg logit contributions
 suddenly-0.024
 opened-0.023
 two-0.023
 a-0.023
 pretended-0.022
Token high
Token ID1029
Feature activation+2.35e+00

Pos logit contributions
beh+0.383
ksh+0.379
ash+0.379
rav+0.374
 unatt+0.371
Neg logit contributions
 a-0.207
 two-0.204
 opened-0.190
 suddenly-0.183
 little-0.167
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
beh+0.089
ash+0.083
rav+0.082
 unatt+0.082
 mir+0.082
Neg logit contributions
 suddenly-0.060
 two-0.057
 a-0.057
 pretended-0.054
 opened-0.053
Token We
Token ID775
Feature activation+4.94e+00

Pos logit contributions
beh+0.048
 unatt+0.047
ash+0.044
 forward+0.043
agging+0.043
Neg logit contributions
 suddenly-0.056
 two-0.054
 opened-0.054
 Suddenly-0.053
 pretended-0.053
Token will
Token ID481
Feature activation+2.58e+00

Pos logit contributions
 unatt+0.179
beh+0.179
ash+0.174
overs+0.171
baby+0.169
Neg logit contributions
 opened-0.127
 suddenly-0.126
 pretended-0.123
 two-0.121
 a-0.116
Token be
Token ID307
Feature activation+6.18e+00

Pos logit contributions
beh+0.097
 unatt+0.094
ash+0.092
 forward+0.092
rav+0.090
Neg logit contributions
 suddenly-0.063
 opened-0.060
 pretended-0.058
 two-0.057
 Suddenly-0.055
Token safe
Token ID3338
Feature activation+7.62e+00

Pos logit contributions
rav+0.205
ash+0.197
umm+0.195
baby+0.195
beh+0.191
Neg logit contributions
 two-0.195
 a-0.195
 suddenly-0.187
 opened-0.181
 pretended-0.176
Token pictures
Token ID5986
Feature activation-2.37e+00

Pos logit contributions
 suddenly+0.046
 pretended+0.041
 Suddenly+0.041
 opened+0.041
 two+0.039
Neg logit contributions
beh-0.038
 unatt-0.038
baby-0.037
 forward-0.037
ash-0.037
Token and
Token ID290
Feature activation+8.38e-01

Pos logit contributions
 suddenly+0.060
 opened+0.057
 pretended+0.056
 two+0.054
 Suddenly+0.053
Neg logit contributions
beh-0.086
 unatt-0.083
ash-0.081
 forward-0.081
rav-0.079
Token words
Token ID2456
Feature activation-1.46e+00

Pos logit contributions
beh+0.022
 losers+0.021
 mir+0.021
baby+0.021
rav+0.021
Neg logit contributions
 suddenly-0.026
 Suddenly-0.024
 opened-0.024
 pretended-0.023
 two-0.022
Token that
Token ID326
Feature activation-5.65e+00

Pos logit contributions
 suddenly+0.033
 opened+0.031
 pretended+0.030
 two+0.030
 a+0.028
Neg logit contributions
beh-0.059
 unatt-0.058
ash-0.056
rav-0.055
 forward-0.054
Token their
Token ID511
Feature activation+4.32e+00

Pos logit contributions
 suddenly+0.104
 opened+0.100
 pretended+0.095
 two+0.092
 a+0.085
Neg logit contributions
beh-0.248
 unatt-0.243
ash-0.239
 forward-0.237
aring-0.233
Token mom
Token ID1995
Feature activation+4.12e+00

Pos logit contributions
beh+0.154
 unatt+0.145
ash+0.144
 forward+0.141
aring+0.138
Neg logit contributions
 suddenly-0.116
 opened-0.116
 pretended-0.114
 two-0.112
 a-0.108
Token read
Token ID1100
Feature activation-2.58e+00

Pos logit contributions
beh+0.177
 unatt+0.170
ash+0.170
baby+0.169
aring+0.167
Neg logit contributions
 suddenly-0.068
 Suddenly-0.061
 two-0.057
 opened-0.054
 pretended-0.054
Token to
Token ID284
Feature activation+2.15e+00

Pos logit contributions
 suddenly+0.055
 a+0.054
 opened+0.053
 two+0.051
 pretended+0.050
Neg logit contributions
beh-0.114
 unatt-0.107
aring-0.104
rav-0.104
ash-0.104
Token them
Token ID606
Feature activation+6.52e+00

Pos logit contributions
beh+0.083
 unatt+0.080
ash+0.079
rav+0.078
aring+0.078
Neg logit contributions
 suddenly-0.053
 opened-0.051
 a-0.050
 two-0.050
 pretended-0.049
Token every
Token ID790
Feature activation-2.52e+00

Pos logit contributions
beh+0.269
 unatt+0.259
rav+0.253
ash+0.250
 mir+0.250
Neg logit contributions
 suddenly-0.143
 opened-0.135
 a-0.133
 two-0.132
 pretended-0.131
Token night
Token ID1755
Feature activation-3.11e+00

Pos logit contributions
 suddenly+0.073
 opened+0.071
 pretended+0.068
 two+0.068
 a+0.066
Neg logit contributions
beh-0.086
 unatt-0.081
rav-0.079
ash-0.079
aring-0.078
Token a
Token ID257
Feature activation-7.53e+00

Pos logit contributions
 unatt+0.170
beh+0.170
 mir+0.163
 forward+0.161
 losers+0.159
Neg logit contributions
 suddenly-0.096
 pretended-0.092
 opened-0.088
 Suddenly-0.085
 two-0.079
Token shelter
Token ID11772
Feature activation+1.13e+00

Pos logit contributions
 suddenly+0.208
 pretended+0.194
 Suddenly+0.191
 opened+0.190
 two+0.190
Neg logit contributions
 mir-0.228
 unatt-0.228
 forward-0.223
 hurricane-0.217
rav-0.217
Token to
Token ID284
Feature activation+2.37e+00

Pos logit contributions
beh+0.038
 unatt+0.038
 forward+0.037
ash+0.036
aring+0.035
Neg logit contributions
 suddenly-0.030
 opened-0.029
 pretended-0.028
 two-0.028
 Suddenly-0.027
Token hide
Token ID7808
Feature activation+9.58e-01

Pos logit contributions
beh+0.074
 unatt+0.073
 forward+0.070
ash+0.069
rav+0.067
Neg logit contributions
 suddenly-0.070
 opened-0.066
 pretended-0.066
 two-0.064
 Suddenly-0.064
Token from
Token ID422
Feature activation-1.40e+00

Pos logit contributions
beh+0.041
 unatt+0.040
ash+0.039
 forward+0.039
rav+0.039
Neg logit contributions
 suddenly-0.018
 opened-0.017
 pretended-0.017
 two-0.016
 Suddenly-0.015
Token the
Token ID262
Feature activation+7.24e-01

Pos logit contributions
 pretended+0.034
 suddenly+0.034
 opened+0.034
 clicked+0.032
 Suddenly+0.032
Neg logit contributions
 unatt-0.050
 future-0.045
 forward-0.045
 mir-0.044
beh-0.043
Token rain
Token ID6290
Feature activation+5.77e+00

Pos logit contributions
beh+0.029
ash+0.027
rav+0.027
aring+0.026
 forward+0.026
Neg logit contributions
 suddenly-0.019
 opened-0.018
 two-0.018
 a-0.017
 pretended-0.016
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
beh+0.209
 unatt+0.201
 forward+0.198
ash+0.198
rav+0.194
Neg logit contributions
 suddenly-0.147
 opened-0.140
 pretended-0.137
 two-0.132
 Suddenly-0.129
Token Twe
Token ID24205
Feature activation+7.93e+00

Pos logit contributions
beh+0.048
 unatt+0.046
 forward+0.046
aring+0.045
baby+0.044
Neg logit contributions
 suddenly-0.033
 pretended-0.032
 opened-0.030
 two-0.029
 pressed-0.027
Tokenety
Token ID2963
Feature activation-1.25e+00

Pos logit contributions
beh+0.181
 unatt+0.161
ash+0.160
aring+0.153
baby+0.149
Neg logit contributions
 suddenly-0.324
 opened-0.315
 pretended-0.308
 two-0.305
 Suddenly-0.298
Token saw
Token ID2497
Feature activation-5.61e+00

Pos logit contributions
 Two+0.023
 Melvin+0.022
 Under+0.022
 disc+0.022
growth+0.022
Neg logit contributions
 unatt-0.043
beh-0.042
 mir-0.042
aring-0.041
off-0.040
Token ball
Token ID2613
Feature activation+2.70e-01

Pos logit contributions
 forward+0.144
 unatt+0.143
ash+0.140
 losers+0.140
beh+0.140
Neg logit contributions
 suddenly-0.178
 opened-0.174
 pretended-0.168
 Suddenly-0.161
 clicked-0.158
Token all
Token ID477
Feature activation+4.11e+00

Pos logit contributions
beh+0.010
 unatt+0.010
ash+0.009
rav+0.009
 forward+0.009
Neg logit contributions
 suddenly-0.007
 opened-0.006
 pretended-0.006
 two-0.006
 Suddenly-0.006
Token day
Token ID1110
Feature activation-2.49e+00

Pos logit contributions
 forward+0.105
beh+0.105
ash+0.103
 unatt+0.103
baby+0.096
Neg logit contributions
 suddenly-0.145
 opened-0.139
 pretended-0.136
 two-0.132
 Suddenly-0.132
Token,
Token ID11
Feature activation-1.25e+00

Pos logit contributions
 suddenly+0.054
 opened+0.051
 pretended+0.050
 two+0.048
 Suddenly+0.046
Neg logit contributions
beh-0.099
 unatt-0.096
 forward-0.094
ash-0.094
rav-0.092
Token and
Token ID290
Feature activation+1.08e+00

Pos logit contributions
 suddenly+0.029
 opened+0.027
 pretended+0.026
 two+0.026
 Suddenly+0.025
Neg logit contributions
beh-0.048
 unatt-0.047
 forward-0.046
ash-0.046
rav-0.045
Token they
Token ID484
Feature activation+1.30e+00

Pos logit contributions
beh+0.037
 forward+0.037
 unatt+0.037
 losers+0.036
rav+0.036
Neg logit contributions
 opened-0.025
 suddenly-0.025
 two-0.023
 pretended-0.023
 Suddenly-0.023
Token became
Token ID2627
Feature activation-7.89e-01

Pos logit contributions
beh+0.050
 unatt+0.049
 forward+0.048
ash+0.047
rav+0.047
Neg logit contributions
 suddenly-0.028
 opened-0.026
 Suddenly-0.025
 two-0.025
 pretended-0.025
Token best
Token ID1266
Feature activation+2.39e+00

Pos logit contributions
 suddenly+0.023
 opened+0.022
 pretended+0.022
 two+0.022
 a+0.021
Neg logit contributions
beh-0.025
 unatt-0.025
ash-0.024
 forward-0.024
rav-0.024
Token friends
Token ID2460
Feature activation+8.64e-01

Pos logit contributions
 unatt+0.102
beh+0.099
ash+0.097
ife+0.094
ksh+0.093
Neg logit contributions
 two-0.049
 suddenly-0.048
 opened-0.044
 pretended-0.044
 a-0.044
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
beh+0.039
ash+0.037
ocol+0.037
 unatt+0.037
 mir+0.037
Neg logit contributions
 suddenly-0.016
 a-0.016
 two-0.015
 pretended-0.014
 opened-0.014
Token<|endoftext|>
Token ID50256
Feature activation+1.75e-01

Pos logit contributions
beh+0.045
 forward+0.043
ash+0.043
 unatt+0.043
rav+0.042
Neg logit contributions
 suddenly-0.025
 opened-0.024
 pretended-0.024
 two-0.021
 Suddenly-0.020
Token bird
Token ID6512
Feature activation-1.45e+00

Pos logit contributions
agging+0.032
opl+0.032
ash+0.032
 unatt+0.031
baby+0.030
Neg logit contributions
 pretended-0.031
 suddenly-0.030
 opened-0.029
 Suddenly-0.027
 led-0.027
Token in
Token ID287
Feature activation-1.72e+00

Pos logit contributions
 pretended+0.039
 suddenly+0.039
 opened+0.038
 two+0.037
 Suddenly+0.036
Neg logit contributions
beh-0.048
 unatt-0.046
aring-0.045
ash-0.044
 forward-0.044
Token a
Token ID257
Feature activation-7.69e+00

Pos logit contributions
 pretended+0.037
 suddenly+0.032
 Suddenly+0.032
 opened+0.030
 clicked+0.030
Neg logit contributions
 forward-0.062
 public-0.061
 unatt-0.061
overs-0.061
 future-0.060
Token tree
Token ID5509
Feature activation-5.62e-01

Pos logit contributions
 suddenly+0.184
 opened+0.175
 two+0.168
 a+0.162
 Suddenly+0.156
Neg logit contributions
beh-0.329
rav-0.301
ash-0.298
aring-0.290
 unatt-0.290
Token.
Token ID13
Feature activation+1.05e+00

Pos logit contributions
 suddenly+0.015
 pretended+0.015
 opened+0.015
 two+0.014
 Suddenly+0.014
Neg logit contributions
beh-0.019
 unatt-0.018
 forward-0.018
ash-0.018
aring-0.017
Token Beth
Token ID19223
Feature activation+3.55e-01

Pos logit contributions
beh+0.032
 forward+0.031
baby+0.031
 unatt+0.030
ash+0.030
Neg logit contributions
 pretended-0.029
 suddenly-0.029
 opened-0.027
 two-0.026
 imagined-0.024
Token couldn
Token ID3521
Feature activation-1.70e+00

Pos logit contributions
beh+0.014
aring+0.013
baby+0.013
 unatt+0.013
off+0.013
Neg logit contributions
 two-0.005
 pretended-0.005
 suddenly-0.005
 a-0.005
 Under-0.005
Token't
Token ID470
Feature activation-4.46e-01

Pos logit contributions
 suddenly+0.034
 opened+0.031
 two+0.030
 a+0.030
 Suddenly+0.028
Neg logit contributions
beh-0.075
 unatt-0.075
ash-0.072
rav-0.070
 forward-0.070
Token help
Token ID1037
Feature activation+8.47e-01

Pos logit contributions
 suddenly+0.015
 opened+0.014
 pretended+0.014
 two+0.014
 Suddenly+0.014
Neg logit contributions
beh-0.012
 unatt-0.012
 forward-0.012
ash-0.011
aring-0.011
Token but
Token ID475
Feature activation-4.05e+00

Pos logit contributions
beh+0.039
 unatt+0.038
ash+0.037
rav+0.037
 forward+0.037
Neg logit contributions
 suddenly-0.014
 opened-0.013
 pretended-0.012
 two-0.012
 a-0.011
Token be
Token ID307
Feature activation+5.83e+00

Pos logit contributions
 suddenly+0.096
 opened+0.091
 pretended+0.089
 two+0.086
 Suddenly+0.084
Neg logit contributions
beh-0.154
 unatt-0.150
ash-0.147
 forward-0.146
rav-0.143
Token sad
Token ID6507
Feature activation+2.76e+00

Pos logit contributions
beh+0.251
ash+0.247
 unatt+0.247
rav+0.237
 forward+0.234
Neg logit contributions
 suddenly-0.229
 opened-0.227
 two-0.217
 pretended-0.214
 a-0.209
Token and
Token ID290
Feature activation+1.66e+00

Pos logit contributions
beh+0.089
 unatt+0.088
 forward+0.086
ash+0.085
aring+0.084
Neg logit contributions
 suddenly-0.079
 opened-0.075
 pretended-0.074
 Suddenly-0.071
 two-0.070
Token angry
Token ID7954
Feature activation+6.18e+00

Pos logit contributions
beh+0.044
 unatt+0.042
 forward+0.042
 losers+0.039
baby+0.039
Neg logit contributions
 suddenly-0.058
 opened-0.055
 pretended-0.054
 Suddenly-0.054
 two-0.054
Token.
Token ID13
Feature activation+1.82e+00

Pos logit contributions
beh+0.229
 unatt+0.223
ash+0.218
 forward+0.215
rav+0.213
Neg logit contributions
 suddenly-0.154
 opened-0.145
 pretended-0.142
 two-0.141
 Suddenly-0.135
Token They
Token ID1119
Feature activation-7.81e-01

Pos logit contributions
beh+0.051
 forward+0.050
baby+0.049
overs+0.049
ash+0.048
Neg logit contributions
 suddenly-0.059
 opened-0.056
 pretended-0.055
 two-0.052
 clicked-0.050
Token cried
Token ID16896
Feature activation-9.17e-01

Pos logit contributions
 suddenly+0.018
 Suddenly+0.017
 two+0.016
 Melvin+0.014
 Far+0.014
Neg logit contributions
 losers-0.026
beh-0.025
 unatt-0.024
 forward-0.024
 dishonest-0.024
Token and
Token ID290
Feature activation+1.69e+00

Pos logit contributions
 a+0.013
 two+0.013
 suddenly+0.012
 opened+0.011
 pretended+0.011
Neg logit contributions
beh-0.046
 unatt-0.044
opl-0.043
ash-0.043
rav-0.043
Token shouted
Token ID17293
Feature activation-3.17e+00

Pos logit contributions
beh+0.067
 unatt+0.064
 losers+0.063
 forward+0.063
baby+0.060
Neg logit contributions
 suddenly-0.035
 Suddenly-0.032
 two-0.030
 opened-0.030
 pretended-0.030
Token.
Token ID13
Feature activation+1.81e+00

Pos logit contributions
 a+0.070
 two+0.058
 suddenly+0.052
 Suddenly+0.050
 was+0.049
Neg logit contributions
beh-0.162
umm-0.150
opl-0.149
 mir-0.148
chie-0.148
Token
Token ID198
Feature activation+7.02e-01

Pos logit contributions
beh+0.058
 unatt+0.057
 forward+0.056
ash+0.055
rav+0.054
Neg logit contributions
 suddenly-0.052
 opened-0.050
 pretended-0.049
 two-0.047
 Suddenly-0.045
Token
Token ID198
Feature activation+6.79e-01

Pos logit contributions
 forward+0.025
beh+0.025
aring+0.025
baby+0.025
rav+0.025
Neg logit contributions
 pretended-0.016
 suddenly-0.015
 opened-0.015
 clicked-0.012
 two-0.012
Token things
Token ID1243
Feature activation+2.14e-01

Pos logit contributions
beh+0.056
rav+0.054
aring+0.054
opl+0.053
baby+0.052
Neg logit contributions
 suddenly-0.029
 two-0.028
 a-0.027
 opened-0.027
 pretended-0.025
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
beh+0.010
rav+0.010
ash+0.010
ksh+0.009
baby+0.009
Neg logit contributions
 suddenly-0.004
 opened-0.004
 a-0.004
 was-0.003
 two-0.003
Token She
Token ID1375
Feature activation-3.19e+00

Pos logit contributions
 suddenly+0.002
 opened+0.002
 Suddenly+0.002
 two+0.002
 pretended+0.002
Neg logit contributions
beh-0.005
 unatt-0.005
ash-0.005
 forward-0.005
rav-0.005
Token told
Token ID1297
Feature activation-2.86e+00

Pos logit contributions
 suddenly+0.050
 opened+0.046
 pretended+0.044
 two+0.042
 Suddenly+0.040
Neg logit contributions
beh-0.145
 unatt-0.142
ash-0.139
 forward-0.139
rav-0.137
Token him
Token ID683
Feature activation+4.03e+00

Pos logit contributions
 suddenly+0.068
 a+0.065
 two+0.065
 opened+0.064
 pretended+0.059
Neg logit contributions
beh-0.113
 unatt-0.110
ash-0.107
rav-0.106
 forward-0.105
Token that
Token ID326
Feature activation-6.44e+00

Pos logit contributions
beh+0.147
 unatt+0.144
ash+0.141
 forward+0.139
rav+0.136
Neg logit contributions
 suddenly-0.102
 opened-0.097
 pretended-0.094
 two-0.093
 Suddenly-0.089
Token he
Token ID339
Feature activation-1.74e+00

Pos logit contributions
 suddenly+0.127
 a+0.115
 two+0.114
 opened+0.109
 pretended+0.100
Neg logit contributions
beh-0.292
ash-0.292
agging-0.291
ags-0.284
ksh-0.283
Token should
Token ID815
Feature activation-3.35e+00

Pos logit contributions
 suddenly+0.033
 opened+0.030
 pretended+0.029
 two+0.028
 Suddenly+0.028
Neg logit contributions
beh-0.074
 unatt-0.072
 forward-0.071
ash-0.071
rav-0.069
Token say
Token ID910
Feature activation-2.84e+00

Pos logit contributions
 suddenly+0.077
 opened+0.073
 two+0.071
 pretended+0.067
 a+0.066
Neg logit contributions
beh-0.136
 unatt-0.135
ash-0.134
 forward-0.131
rav-0.131
Token sorry
Token ID7926
Feature activation+4.48e+00

Pos logit contributions
 a+0.074
 two+0.069
 suddenly+0.069
 opened+0.060
 pretended+0.056
Neg logit contributions
beh-0.121
ash-0.115
ksh-0.112
umm-0.109
 unatt-0.108
Token to
Token ID284
Feature activation+2.00e+00

Pos logit contributions
beh+0.172
 unatt+0.166
opl+0.163
ocol+0.162
agging+0.159
Neg logit contributions
 suddenly-0.112
 a-0.107
 pretended-0.105
 opened-0.104
 two-0.103
Token m
Token ID285
Feature activation+9.36e+00

Pos logit contributions
beh+0.095
 unatt+0.086
ash+0.085
aring+0.085
off+0.084
Neg logit contributions
 two-0.056
 suddenly-0.054
 a-0.053
 pretended-0.051
 opened-0.051
Tokenama
Token ID1689
Feature activation+1.18e+00

Pos logit contributions
 unatt+0.315
beh+0.313
 forward+0.312
 losers+0.301
 dishonest+0.274
Neg logit contributions
 suddenly-0.253
 two-0.241
 opened-0.232
 Suddenly-0.227
 was-0.219
Token loved
Token ID6151
Feature activation+8.98e-01

Pos logit contributions
beh+0.050
 unatt+0.048
ash+0.047
rav+0.046
 forward+0.046
Neg logit contributions
 suddenly-0.024
 opened-0.023
 pretended-0.023
 two-0.023
 a-0.022
Token him
Token ID683
Feature activation+4.86e+00

Pos logit contributions
beh+0.032
 unatt+0.030
ash+0.030
aring+0.030
rav+0.029
Neg logit contributions
 suddenly-0.026
 a-0.026
 two-0.024
 opened-0.024
 pretended-0.023
Token.
Token ID13
Feature activation+1.31e+00

Pos logit contributions
beh+0.206
rav+0.195
ash+0.193
ocol+0.192
off+0.190
Neg logit contributions
 a-0.118
 suddenly-0.111
 two-0.107
 opened-0.099
 pretended-0.096
Token They
Token ID1119
Feature activation-1.22e+00

Pos logit contributions
beh+0.056
 unatt+0.054
 forward+0.054
ash+0.053
rav+0.053
Neg logit contributions
 suddenly-0.024
 opened-0.023
 pretended-0.022
 two-0.021
 Suddenly-0.019
Token were
Token ID547
Feature activation-6.87e-01

Pos logit contributions
 suddenly+0.023
 opened+0.022
 pretended+0.021
 two+0.020
 Suddenly+0.020
Neg logit contributions
beh-0.051
 unatt-0.050
 forward-0.049
ash-0.049
rav-0.048
Token happy
Token ID3772
Feature activation+4.66e+00

Pos logit contributions
 suddenly+0.020
 opened+0.019
 pretended+0.018
 two+0.018
 a+0.017
Neg logit contributions
beh-0.023
 unatt-0.022
ash-0.022
 forward-0.021
rav-0.021
Token ot
Token ID30972
Feature activation-2.11e+00

Pos logit contributions
beh+0.205
ash+0.196
 unatt+0.195
 forward+0.188
opl+0.186
Neg logit contributions
 suddenly-0.095
 two-0.086
 opened-0.086
 pretended-0.085
 a-0.085
Tokenters
Token ID1010
Feature activation-3.06e+00

Pos logit contributions
 two+0.058
 suddenly+0.058
 opened+0.054
 pretended+0.053
 a+0.052
Neg logit contributions
 unatt-0.069
opl-0.065
beh-0.064
 forward-0.064
 mir-0.063
Token.
Token ID13
Feature activation+1.29e+00

Pos logit contributions
 a+0.048
 suddenly+0.045
 two+0.045
 was+0.042
 opened+0.042
Neg logit contributions
beh-0.151
ash-0.142
rav-0.141
ocol-0.139
 unatt-0.139
Token look
Token ID804
Feature activation-1.65e+00

Pos logit contributions
beh+0.049
 unatt+0.047
ash+0.046
 forward+0.046
rav+0.045
Neg logit contributions
 suddenly-0.034
 opened-0.033
 pretended-0.032
 two-0.031
 Suddenly-0.030
Token for
Token ID329
Feature activation+4.49e+00

Pos logit contributions
 suddenly+0.049
 opened+0.048
 pretended+0.047
 a+0.046
 two+0.046
Neg logit contributions
beh-0.054
rav-0.051
 unatt-0.050
ash-0.049
opl-0.048
Token sp
Token ID599
Feature activation+2.11e-01

Pos logit contributions
beh+0.144
 unatt+0.141
ash+0.138
 forward+0.137
baby+0.133
Neg logit contributions
 suddenly-0.127
 opened-0.121
 pretended-0.118
 Suddenly-0.116
 two-0.113
Tokenoons
Token ID13022
Feature activation+1.42e+00

Pos logit contributions
beh+0.007
 unatt+0.007
rav+0.007
 forward+0.007
baby+0.006
Neg logit contributions
 suddenly-0.006
 opened-0.006
 pretended-0.005
 two-0.005
 a-0.005
Token in
Token ID287
Feature activation-1.60e+00

Pos logit contributions
beh+0.069
rav+0.065
opl+0.063
aring+0.063
ife+0.062
Neg logit contributions
 a-0.024
 suddenly-0.024
 two-0.023
 pretended-0.023
 opened-0.022
Token every
Token ID790
Feature activation-1.82e+00

Pos logit contributions
 suddenly+0.034
 opened+0.033
 pretended+0.033
 Suddenly+0.032
 clicked+0.029
Neg logit contributions
 unatt-0.061
 forward-0.060
beh-0.059
overs-0.058
baby-0.058
Token corner
Token ID5228
Feature activation-8.65e-01

Pos logit contributions
 suddenly+0.052
 opened+0.051
 two+0.049
 pretended+0.048
 a+0.047
Neg logit contributions
beh-0.064
aring-0.060
rav-0.059
 unatt-0.059
agging-0.058
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
 suddenly+0.019
 opened+0.018
 a+0.017
 pretended+0.017
 two+0.017
Neg logit contributions
beh-0.036
rav-0.035
 losers-0.034
 unatt-0.034
agging-0.034
Token One
Token ID1881
Feature activation-1.45e+00

Pos logit contributions
beh+0.057
 unatt+0.056
ash+0.055
 forward+0.055
rav+0.054
Neg logit contributions
 suddenly-0.029
 opened-0.027
 pretended-0.026
 two-0.025
 Suddenly-0.024
Token day
Token ID1110
Feature activation-1.99e+00

Pos logit contributions
 suddenly+0.048
 opened+0.046
 pretended+0.045
 two+0.044
 Suddenly+0.043
Neg logit contributions
beh-0.042
 unatt-0.040
ash-0.039
 forward-0.039
rav-0.038
Token,
Token ID11
Feature activation-1.14e+00

Pos logit contributions
 pretended+0.047
 opened+0.047
 inserted+0.045
 clicked+0.045
 suddenly+0.045
Neg logit contributions
 forward-0.065
baby-0.060
rav-0.060
overs-0.059
ocol-0.058
Token started
Token ID2067
Feature activation-5.12e-01

Pos logit contributions
beh+0.025
 unatt+0.024
ash+0.024
rav+0.024
 forward+0.024
Neg logit contributions
 suddenly-0.010
 opened-0.010
 pretended-0.009
 two-0.009
 Suddenly-0.008
Token to
Token ID284
Feature activation+1.95e+00

Pos logit contributions
 suddenly+0.015
 opened+0.014
 a+0.014
 two+0.013
 pretended+0.013
Neg logit contributions
ash-0.018
rav-0.018
 unatt-0.018
beh-0.018
ife-0.018
Token run
Token ID1057
Feature activation+4.44e+00

Pos logit contributions
beh+0.057
 unatt+0.055
 forward+0.053
ash+0.052
rav+0.051
Neg logit contributions
 suddenly-0.062
 opened-0.059
 pretended-0.058
 two-0.057
 Suddenly-0.057
Token.
Token ID13
Feature activation+7.09e-01

Pos logit contributions
beh+0.126
 unatt+0.119
ash+0.118
rav+0.116
 forward+0.111
Neg logit contributions
 suddenly-0.152
 opened-0.145
 pretended-0.143
 two-0.139
 Suddenly-0.138
Token
Token ID198
Feature activation-2.50e-01

Pos logit contributions
beh+0.030
 unatt+0.029
ash+0.028
 forward+0.028
rav+0.028
Neg logit contributions
 suddenly-0.014
 opened-0.013
 pretended-0.013
 two-0.013
 Suddenly-0.012
Token
Token ID198
Feature activation-2.59e-01

Pos logit contributions
 pretended+0.007
 opened+0.006
 suddenly+0.006
 two+0.005
 clicked+0.005
Neg logit contributions
 forward-0.008
aring-0.008
off-0.008
ash-0.008
baby-0.008
TokenBut
Token ID1537
Feature activation-5.01e+00

Pos logit contributions
 suddenly+0.005
 opened+0.004
 two+0.004
 pretended+0.004
 Suddenly+0.004
Neg logit contributions
beh-0.012
 unatt-0.011
ash-0.011
 forward-0.011
rav-0.011
Token it
Token ID340
Feature activation+3.36e+00

Pos logit contributions
 pretended+0.074
 opened+0.072
 suddenly+0.064
 clicked+0.063
 Under+0.061
Neg logit contributions
 forward-0.218
 unatt-0.215
beh-0.204
 losers-0.196
overs-0.195
Token was
Token ID373
Feature activation-2.01e+00

Pos logit contributions
beh+0.149
 unatt+0.147
 forward+0.146
ash+0.142
 losers+0.142
Neg logit contributions
 Suddenly-0.039
 pretended-0.038
 suddenly-0.038
 two-0.037
 opened-0.037
Token too
Token ID1165
Feature activation+8.64e+00

Pos logit contributions
 suddenly+0.066
 opened+0.063
 two+0.061
 a+0.061
 pretended+0.060
Neg logit contributions
beh-0.062
rav-0.059
ash-0.059
 unatt-0.059
aring-0.057
Token late
Token ID2739
Feature activation-1.62e+00

Pos logit contributions
beh+0.245
 unatt+0.235
ash+0.229
 forward+0.226
rav+0.224
Neg logit contributions
 suddenly-0.291
 opened-0.281
 pretended-0.273
 two-0.271
 Suddenly-0.263
Token mom
Token ID1995
Feature activation+3.81e+00

Pos logit contributions
beh+0.079
ash+0.075
ife+0.071
aring+0.071
rav+0.070
Neg logit contributions
 suddenly-0.044
 two-0.042
 opened-0.041
 a-0.041
 pretended-0.038
Token.
Token ID13
Feature activation+6.06e-01

Pos logit contributions
beh+0.152
rav+0.148
 unatt+0.144
 losers+0.144
ash+0.142
Neg logit contributions
 suddenly-0.087
 opened-0.083
 pretended-0.079
 two-0.078
 a-0.075
Token Then
Token ID3244
Feature activation-5.91e+00

Pos logit contributions
beh+0.025
 unatt+0.025
ash+0.024
 forward+0.024
rav+0.023
Neg logit contributions
 suddenly-0.012
 opened-0.012
 pretended-0.011
 two-0.011
 Suddenly-0.011
Token he
Token ID339
Feature activation-1.11e+00

Pos logit contributions
 opened+0.119
 pretended+0.118
 clicked+0.111
 suddenly+0.109
 pressed+0.104
Neg logit contributions
 forward-0.231
 unatt-0.210
beh-0.206
baby-0.205
overs-0.205
Token saw
Token ID2497
Feature activation-6.00e+00

Pos logit contributions
 suddenly+0.018
 Suddenly+0.017
 opened+0.017
 pretended+0.016
 two+0.016
Neg logit contributions
 forward-0.045
 unatt-0.045
beh-0.044
 mir-0.044
ash-0.043
Token a
Token ID257
Feature activation-7.94e+00

Pos logit contributions
 pretended+0.121
 opened+0.120
 suddenly+0.114
 clicked+0.107
 Suddenly+0.105
Neg logit contributions
 unatt-0.233
 forward-0.226
 permission-0.216
overs-0.216
beh-0.214
Token huge
Token ID3236
Feature activation-2.32e+00

Pos logit contributions
 suddenly+0.176
 opened+0.165
 pretended+0.157
 two+0.157
 Suddenly+0.148
Neg logit contributions
beh-0.325
 unatt-0.309
ash-0.307
 forward-0.301
rav-0.295
Token neck
Token ID7393
Feature activation-2.80e+00

Pos logit contributions
 suddenly+0.053
 opened+0.050
 two+0.048
 pretended+0.047
 a+0.047
Neg logit contributions
beh-0.099
 unatt-0.090
ash-0.090
rav-0.088
 forward-0.087
Token-
Token ID12
Feature activation+1.33e+01

Pos logit contributions
 suddenly+0.069
 pretended+0.069
 opened+0.066
 Suddenly+0.064
 two+0.062
Neg logit contributions
 unatt-0.097
 forward-0.097
beh-0.096
aring-0.093
ash-0.093
Tokenhigh
Token ID8929
Feature activation-3.23e+00

Pos logit contributions
beh+0.351
off+0.316
 forward+0.309
ash+0.305
aring+0.297
Neg logit contributions
 suddenly-0.497
 pretended-0.483
 opened-0.468
 led-0.448
 two-0.439
Token patch
Token ID8529
Feature activation+1.20e+00

Pos logit contributions
 suddenly+0.080
 pretended+0.078
 opened+0.076
 Suddenly+0.073
 two+0.072
Neg logit contributions
 unatt-0.111
beh-0.107
 forward-0.107
ash-0.105
 mir-0.105
Token She
Token ID1375
Feature activation-2.04e+00

Pos logit contributions
beh+0.036
 unatt+0.036
ash+0.034
 forward+0.034
rav+0.033
Neg logit contributions
 suddenly-0.030
 opened-0.029
 pretended-0.028
 two-0.028
 Suddenly-0.028
Token gave
Token ID2921
Feature activation+4.15e-01

Pos logit contributions
 suddenly+0.042
 Suddenly+0.037
 opened+0.037
 pretended+0.037
 two+0.036
Neg logit contributions
beh-0.081
 unatt-0.077
 forward-0.076
ash-0.076
rav-0.076
Token it
Token ID340
Feature activation+3.60e+00

Pos logit contributions
beh+0.014
 unatt+0.014
ash+0.013
 forward+0.013
aring+0.013
Neg logit contributions
 suddenly-0.012
 opened-0.011
 two-0.011
 pretended-0.011
 a-0.011
Token to
Token ID284
Feature activation+2.14e+00

Pos logit contributions
beh+0.148
opl+0.144
 unatt+0.143
agging+0.142
ash+0.140
Neg logit contributions
 a-0.089
 two-0.081
 opened-0.079
 suddenly-0.073
 pretended-0.070
Token me
Token ID502
Feature activation+8.57e+00

Pos logit contributions
beh+0.076
aring+0.069
ash+0.068
rav+0.066
 unatt+0.066
Neg logit contributions
 a-0.069
 two-0.065
 suddenly-0.065
 opened-0.062
 pretended-0.058
Token when
Token ID618
Feature activation-9.91e+00

Pos logit contributions
beh+0.371
 unatt+0.356
rav+0.347
ash+0.344
agging+0.340
Neg logit contributions
 suddenly-0.171
 a-0.163
 opened-0.162
 two-0.161
 pretended-0.152
Token I
Token ID314
Feature activation+4.49e+00

Pos logit contributions
 suddenly+0.259
 two+0.239
 opened+0.235
 a+0.235
 pretended+0.212
Neg logit contributions
beh-0.391
ash-0.377
 unatt-0.373
aring-0.366
agging-0.360
Token married
Token ID6405
Feature activation+1.85e+00

Pos logit contributions
beh+0.183
 unatt+0.178
ash+0.173
 forward+0.170
rav+0.169
Neg logit contributions
 suddenly-0.084
 Suddenly-0.079
 two-0.074
 pretended-0.072
 opened-0.069
Token your
Token ID534
Feature activation+5.65e+00

Pos logit contributions
beh+0.080
aring+0.072
agging+0.072
ash+0.071
rav+0.070
Neg logit contributions
 suddenly-0.042
 a-0.041
 opened-0.040
 two-0.040
 pretended-0.039
Token dad
Token ID9955
Feature activation+2.95e+00

Pos logit contributions
beh+0.215
ash+0.204
 unatt+0.195
 forward+0.195
aring+0.192
Neg logit contributions
 suddenly-0.144
 two-0.142
 opened-0.141
 pretended-0.139
 a-0.136
Token.
Token ID13
Feature activation+9.97e-01

Pos logit contributions
beh+0.116
 unatt+0.112
 forward+0.109
ash+0.108
rav+0.108
Neg logit contributions
 opened-0.068
 suddenly-0.067
 pretended-0.066
 two-0.064
 a-0.062
Token park
Token ID3952
Feature activation-1.93e+00

Pos logit contributions
beh+0.003
 unatt+0.003
ash+0.002
 forward+0.002
rav+0.002
Neg logit contributions
 suddenly-0.002
 opened-0.002
 two-0.002
 pretended-0.002
 Suddenly-0.001
Token,
Token ID11
Feature activation-1.73e+00

Pos logit contributions
 pretended+0.041
 suddenly+0.039
 opened+0.037
 two+0.036
 clicked+0.036
Neg logit contributions
 forward-0.072
 unatt-0.071
rav-0.069
aring-0.068
overs-0.068
Token the
Token ID262
Feature activation+6.23e-02

Pos logit contributions
 pretended+0.043
 opened+0.040
 inserted+0.040
 dial+0.039
 imagined+0.039
Neg logit contributions
 forward-0.054
 unatt-0.054
 hurricane-0.050
 losers-0.049
overs-0.049
Token mouse
Token ID10211
Feature activation-5.55e+00

Pos logit contributions
 unatt+0.002
baby+0.002
 law+0.002
 losers+0.002
 ambulance+0.002
Neg logit contributions
 suddenly-0.002
 opened-0.002
 pretended-0.002
 clicked-0.002
 inserted-0.002
Token saw
Token ID2497
Feature activation-6.20e+00

Pos logit contributions
 suddenly+0.087
 two+0.083
 Suddenly+0.078
 opened+0.075
 Under+0.073
Neg logit contributions
 unatt-0.227
 forward-0.210
 mir-0.210
beh-0.210
off-0.209
Token a
Token ID257
Feature activation-8.06e+00

Pos logit contributions
 pretended+0.079
 suddenly+0.075
 opened+0.071
 Suddenly+0.059
 clicked+0.058
Neg logit contributions
 unatt-0.287
beh-0.276
 losers-0.273
 forward-0.272
 ambulance-0.271
Token big
Token ID1263
Feature activation-1.54e+00

Pos logit contributions
 suddenly+0.171
 opened+0.161
 pretended+0.155
 two+0.152
 Suddenly+0.145
Neg logit contributions
beh-0.328
 unatt-0.317
ash-0.312
 forward-0.310
rav-0.304
Token ball
Token ID2613
Feature activation-1.20e-01

Pos logit contributions
 opened+0.036
 suddenly+0.036
 two+0.035
 a+0.034
 pretended+0.034
Neg logit contributions
beh-0.066
ash-0.059
 unatt-0.058
rav-0.057
 forward-0.057
Token.
Token ID13
Feature activation+5.18e-01

Pos logit contributions
 suddenly+0.003
 opened+0.003
 two+0.003
 pretended+0.003
 a+0.002
Neg logit contributions
beh-0.005
rav-0.005
 unatt-0.005
ash-0.004
 forward-0.004
Token The
Token ID383
Feature activation-3.35e+00

Pos logit contributions
beh+0.021
 unatt+0.020
ash+0.020
 forward+0.019
rav+0.019
Neg logit contributions
 suddenly-0.012
 opened-0.011
 pretended-0.011
 two-0.010
 Suddenly-0.010
Token mouse
Token ID10211
Feature activation-5.63e+00

Pos logit contributions
 suddenly+0.104
 opened+0.100
 pretended+0.099
 Suddenly+0.094
 clicked+0.089
Neg logit contributions
 unatt-0.097
 losers-0.093
 forward-0.093
baby-0.092
beh-0.091
Token a
Token ID257
Feature activation-8.08e+00

Pos logit contributions
 clicked+0.156
 inserted+0.149
 blasted+0.147
 pretended+0.142
 suddenly+0.140
Neg logit contributions
 unatt-0.226
 losers-0.222
baby-0.216
 future-0.214
des-0.210
Token time
Token ID640
Feature activation-2.01e+00

Pos logit contributions
 suddenly+0.219
 opened+0.206
 pretended+0.201
 clicked+0.195
 two+0.192
Neg logit contributions
 forward-0.262
ash-0.261
 unatt-0.261
agging-0.255
beh-0.253
Token,
Token ID11
Feature activation-1.31e+00

Pos logit contributions
 pretended+0.047
 suddenly+0.046
 opened+0.043
 clicked+0.041
 dial+0.040
Neg logit contributions
rav-0.073
 forward-0.072
 unatt-0.071
aring-0.070
baby-0.069
Token there
Token ID612
Feature activation-7.84e+00

Pos logit contributions
growth+0.042
 dial+0.040
 pretended+0.039
 trek+0.038
 blasted+0.037
Neg logit contributions
 forward-0.041
 back-0.034
 unhappy-0.033
baby-0.033
 unatt-0.032
Token was
Token ID373
Feature activation-1.62e+00

Pos logit contributions
 pretended+0.168
 dial+0.163
 inserted+0.161
 blasted+0.145
 pressed+0.144
Neg logit contributions
baby-0.271
rav-0.254
 unatt-0.247
 future-0.246
ash-0.238
Token a
Token ID257
Feature activation-8.07e+00

Pos logit contributions
 dial+0.034
 clicked+0.034
 rang+0.033
 suddenly+0.031
 opened+0.031
Neg logit contributions
 forward-0.057
ags-0.057
overs-0.056
baby-0.055
 future-0.055
Token boy
Token ID2933
Feature activation-5.13e+00

Pos logit contributions
 suddenly+0.116
 opened+0.106
 pretended+0.101
 two+0.096
 Suddenly+0.091
Neg logit contributions
beh-0.381
 unatt-0.372
ash-0.365
 forward-0.365
rav-0.359
Token named
Token ID3706
Feature activation-4.37e+00

Pos logit contributions
 suddenly+0.115
 opened+0.109
 pretended+0.105
 two+0.104
 Suddenly+0.102
Neg logit contributions
beh-0.194
 unatt-0.190
baby-0.188
ash-0.184
aring-0.184
Token Tim
Token ID5045
Feature activation+5.67e-01

Pos logit contributions
 suddenly+0.134
 pretended+0.120
 opened+0.120
 clicked+0.113
 two+0.113
Neg logit contributions
ash-0.131
baby-0.130
beh-0.128
 unatt-0.128
 losers-0.127
Tokenmy
Token ID1820
Feature activation-2.70e+00

Pos logit contributions
baby+0.015
 unatt+0.014
ash+0.014
beh+0.014
off+0.014
Neg logit contributions
 suddenly-0.020
 Suddenly-0.018
 opened-0.018
 clicked-0.018
 pretended-0.017
Token.
Token ID13
Feature activation+1.28e+00

Pos logit contributions
 suddenly+0.086
 opened+0.081
 pretended+0.078
 Suddenly+0.077
 clicked+0.077
Neg logit contributions
baby-0.077
beh-0.077
 unatt-0.076
 forward-0.072
aring-0.072
Token with
Token ID351
Feature activation-2.80e+00

Pos logit contributions
 suddenly+0.042
 opened+0.039
 pretended+0.038
 two+0.037
 Suddenly+0.036
Neg logit contributions
beh-0.079
 unatt-0.076
ash-0.075
 forward-0.074
rav-0.074
Token her
Token ID607
Feature activation+2.77e+00

Pos logit contributions
 suddenly+0.084
 pretended+0.081
 opened+0.081
 Suddenly+0.078
 two+0.075
Neg logit contributions
beh-0.084
 forward-0.082
 unatt-0.082
ash-0.079
baby-0.076
Token mom
Token ID1995
Feature activation+3.75e+00

Pos logit contributions
beh+0.094
 unatt+0.093
 forward+0.091
ash+0.090
rav+0.088
Neg logit contributions
 suddenly-0.074
 opened-0.071
 pretended-0.070
 Suddenly-0.067
 two-0.066
Token and
Token ID290
Feature activation+7.54e-01

Pos logit contributions
beh+0.146
 unatt+0.142
ash+0.138
 forward+0.138
rav+0.137
Neg logit contributions
 suddenly-0.086
 opened-0.081
 pretended-0.079
 two-0.077
 Suddenly-0.074
Token brought
Token ID3181
Feature activation+8.53e-02

Pos logit contributions
 unatt+0.021
beh+0.021
 forward+0.021
rav+0.020
baby+0.019
Neg logit contributions
 suddenly-0.023
 Suddenly-0.022
 opened-0.022
 pretended-0.021
 two-0.021
Token a
Token ID257
Feature activation-8.25e+00

Pos logit contributions
 unatt+0.004
beh+0.004
aring+0.004
rav+0.004
 losers+0.004
Neg logit contributions
 two-0.002
 suddenly-0.002
 a-0.002
 opened-0.002
 pretended-0.001
Token sp
Token ID599
Feature activation-4.91e-01

Pos logit contributions
 suddenly+0.209
 opened+0.200
 pretended+0.194
 two+0.190
 Suddenly+0.183
Neg logit contributions
beh-0.301
 unatt-0.290
ash-0.283
 forward-0.282
rav-0.276
Tokenade
Token ID671
Feature activation-6.57e-01

Pos logit contributions
 opened+0.015
 suddenly+0.015
 two+0.015
 pretended+0.014
 a+0.014
Neg logit contributions
beh-0.014
 unatt-0.014
rav-0.013
 forward-0.013
baby-0.013
Token.
Token ID13
Feature activation+1.16e+00

Pos logit contributions
 a+0.013
 suddenly+0.013
 two+0.013
 opened+0.013
 pretended+0.012
Neg logit contributions
rav-0.028
beh-0.028
 losers-0.026
baby-0.026
 apologies-0.025
Token As
Token ID1081
Feature activation-6.81e+00

Pos logit contributions
 forward+0.038
overs+0.037
ash+0.037
beh+0.037
rav+0.036
Neg logit contributions
 suddenly-0.030
 pretended-0.029
 opened-0.028
 two-0.027
 clicked-0.025
Token they
Token ID484
Feature activation+1.29e+00

Pos logit contributions
 pretended+0.169
 opened+0.168
 suddenly+0.161
 Suddenly+0.159
 two+0.155
Neg logit contributions
 forward-0.228
beh-0.220
 unatt-0.218
rav-0.210
overs-0.207