TOP ACTIVATIONS
MAX = 7.534

said , " That is called a stand . We need
" Those cars are called traffic ," Mom my said
" That is called a cell ," his mum
said , " It is called jelly . Would you like
" That pepper is called a jumping pepper ," said
said , " These are called notes , and they are
said , " This is called striking . Watch what I
says , " They are called seasons . And they happen
, " This lake is called the Bright Blue Eye ,
" That 's called the clouds , John ,"
it . " This is called flour ," she told Tim
, this little thing is called a mole . He is
" It is called chalk ," said Dad .
I am called a squirrel . I have
replied , " That 's called a mustache . There are
bowl . " This is called caul iflower soup ," said
. " The game is called Match !" Everyone was quiet
and Annie said it was called ˜ Pretty
. She said it was called dust . He asked her
, the other child was called Bob . Amy

MIN ACTIVATIONS
MIN = -7.091

flew away , singing a goodbye to me . I waved
. Tom and Anna wave goodbye . They go back to
. Lily and Ben wave goodbye to the bird . They
sm elly flower as a goodbye gift . Sam thanked him
to Anna . He waves goodbye and walks away .
. Tim and Mia wave goodbye . They are happy .
in the car and waves goodbye . Tom and Mia wave
away , waving its tail goodbye . L
L ily and Ben wave goodbye . They learn a lesson
. Sara and Tom wave goodbye . They have a new
They kissed the snow man goodbye . They took
L ily and Ben wave goodbye to the z ebra .
. Tom and Mom wave goodbye . They are happy too
L ila and Ben wave goodbye to the lion . They
the car . They wave goodbye and drive away . They
the car . They wave goodbye to their old house and
den hugged Mrs . Bell goodbye . Jay den was proud
dog and gave it a goodbye hug . The
L ily and Tom wave goodbye . They put on their
ground and said a special goodbye . Jack and

INTERVAL 3.878 - 7.534
CONTAINS 0.173%

there was a little girl called Penny . Penny was three
whispered , " Are the leaves talking ?" His
. Lib by was three years old and loved to pick
saw two gates . One gate was small and blue ,
ie and she was 3 years old . One

INTERVAL 0.222 - 3.878
CONTAINS 41.099%

appreciate the beauty of the me adow . <|endoftext|> Once upon
." She took Ben 's hand and followed their trail back
the noise made them turn around . The
Billy was mesmer ized . He couldn 't believe
next to Sara . He looked at the book and said

INTERVAL -3.435 - 0.222
CONTAINS 58.263%

in the street . Sam thought it would be y ummy
. She sees Sara and Ben fighting . She sees the
because he was taking dance lessons . H oot ie 's
day , she went for a walk with her mom in
. We can float on the raft together ," Lily says

INTERVAL -7.091 - -3.435
CONTAINS 0.464%

unt ies the rope and fre es Ben . He lifts
He gives them each a kiss on the lip . Lily
." The mushroom softened . It saw that they
f auc et all over again . <|endoftext|> Once upon a
But then , something bad happened . One of the balloons
Token said
Token ID531
Feature activation+2.06e+00

Pos logit contributions
asis+0.055
rig+0.050
place+0.049
row+0.044
eh+0.042
Neg logit contributions
ked-0.059
joy-0.053
 Ow-0.052
anish-0.052
 superstar-0.049
Token,
Token ID11
Feature activation+1.43e+00

Pos logit contributions
asis+0.063
place+0.060
old+0.059
row+0.057
rig+0.057
Neg logit contributions
ked-0.103
arre-0.102
 Ow-0.100
adoes-0.099
anish-0.099
Token "
Token ID366
Feature activation-5.39e-01

Pos logit contributions
asis+0.062
rig+0.062
 called+0.059
place+0.057
isin+0.056
Neg logit contributions
anish-0.053
ked-0.052
 tant-0.052
 Ow-0.052
 anymore-0.052
TokenThat
Token ID2504
Feature activation+8.87e-01

Pos logit contributions
ked+0.015
anish+0.015
 Ow+0.014
joy+0.014
 anymore+0.013
Neg logit contributions
asis-0.032
rig-0.030
place-0.030
row-0.028
eh-0.028
Token is
Token ID318
Feature activation+2.13e+00

Pos logit contributions
asis+0.048
rig+0.048
place+0.046
eh+0.044
rim+0.043
Neg logit contributions
 Ow-0.027
ked-0.026
anish-0.026
 anymore-0.024
joy-0.023
Token called
Token ID1444
Feature activation+7.53e+00

Pos logit contributions
asis+0.151
rig+0.145
old+0.141
place+0.139
rim+0.137
Neg logit contributions
 Ow-0.036
 anymore-0.033
ked-0.029
adoes-0.029
anish-0.027
Token a
Token ID257
Feature activation+2.02e+00

Pos logit contributions
asis+0.404
rig+0.387
place+0.375
row+0.344
old+0.344
Neg logit contributions
ked-0.254
 Ow-0.247
anish-0.244
 anymore-0.228
joy-0.228
Token stand
Token ID1302
Feature activation+2.78e+00

Pos logit contributions
rig+0.090
asis+0.086
old+0.085
row+0.083
place+0.082
Neg logit contributions
 Ow-0.076
joy-0.075
anish-0.073
 superstar-0.073
ked-0.072
Token.
Token ID13
Feature activation+1.38e+00

Pos logit contributions
rig+0.139
asis+0.137
place+0.132
isin+0.122
old+0.121
Neg logit contributions
 anymore-0.095
ked-0.095
anish-0.090
joy-0.083
adoes-0.082
Token We
Token ID775
Feature activation+5.99e-02

Pos logit contributions
asis+0.086
rig+0.082
place+0.081
eh+0.077
row+0.076
Neg logit contributions
ked-0.035
anish-0.033
 Ow-0.033
joy-0.030
 anymore-0.030
Token need
Token ID761
Feature activation+1.51e+00

Pos logit contributions
asis+0.003
rig+0.003
place+0.003
row+0.003
eh+0.003
Neg logit contributions
ked-0.002
anish-0.002
 Ow-0.002
joy-0.002
 anymore-0.002
Token
Token ID198
Feature activation+1.16e+00

Pos logit contributions
asis+0.050
rig+0.049
place+0.047
row+0.043
old+0.043
Neg logit contributions
ked-0.042
anish-0.039
 Ow-0.038
joy-0.038
 anymore-0.038
Token"
Token ID1
Feature activation+2.09e-01

Pos logit contributions
asis+0.049
rig+0.047
place+0.046
row+0.041
old+0.041
Neg logit contributions
ked-0.053
anish-0.049
 Ow-0.049
 anymore-0.049
joy-0.049
TokenThose
Token ID9627
Feature activation+2.41e+00

Pos logit contributions
rig+0.011
place+0.011
asis+0.011
isin+0.010
eh+0.010
Neg logit contributions
 anymore-0.007
ked-0.007
 Ow-0.006
adoes-0.006
joy-0.006
Token cars
Token ID5006
Feature activation+1.95e+00

Pos logit contributions
asis+0.135
place+0.134
rig+0.128
old+0.120
row+0.118
Neg logit contributions
ked-0.073
anish-0.070
joy-0.069
 Ow-0.066
 anymore-0.062
Token are
Token ID389
Feature activation+9.29e-01

Pos logit contributions
asis+0.128
rig+0.127
place+0.121
eh+0.117
row+0.115
Neg logit contributions
ked-0.040
anish-0.037
 anymore-0.036
 Ow-0.034
joy-0.030
Token called
Token ID1444
Feature activation+7.46e+00

Pos logit contributions
asis+0.046
rig+0.043
place+0.041
old+0.039
eh+0.039
Neg logit contributions
ked-0.035
 anymore-0.034
 Ow-0.032
adoes-0.031
anish-0.031
Token traffic
Token ID4979
Feature activation+4.52e+00

Pos logit contributions
asis+0.371
rig+0.353
place+0.343
row+0.316
eh+0.314
Neg logit contributions
ked-0.280
anish-0.266
 Ow-0.260
 anymore-0.255
joy-0.254
Token,"
Token ID553
Feature activation-1.71e-01

Pos logit contributions
asis+0.217
rig+0.207
place+0.197
eh+0.188
row+0.184
Neg logit contributions
ked-0.174
 anymore-0.170
anish-0.166
 Ow-0.159
adoes-0.156
Token Mom
Token ID11254
Feature activation+1.36e+00

Pos logit contributions
ked+0.008
anish+0.008
 Ow+0.007
joy+0.007
 anymore+0.007
Neg logit contributions
asis-0.007
rig-0.007
place-0.006
old-0.006
row-0.006
Tokenmy
Token ID1820
Feature activation-5.07e-02

Pos logit contributions
asis+0.077
place+0.073
rig+0.070
ands+0.063
fire+0.063
Neg logit contributions
ked-0.046
anish-0.041
 anymore-0.039
joy-0.038
 Ow-0.038
Token said
Token ID531
Feature activation+1.07e+00

Pos logit contributions
ked+0.002
anish+0.002
joy+0.002
 anymore+0.002
 again+0.002
Neg logit contributions
asis-0.003
place-0.002
rig-0.002
ands-0.002
eh-0.002
Token
Token ID198
Feature activation+1.12e-03

Pos logit contributions
ked+0.011
anish+0.010
 Ow+0.010
joy+0.010
 anymore+0.010
Neg logit contributions
asis-0.016
rig-0.016
place-0.015
row-0.014
eh-0.014
Token
Token ID198
Feature activation+2.66e-01

Pos logit contributions
asis+0.000
place+0.000
rig+0.000
row+0.000
 stump+0.000
Neg logit contributions
 Ow-0.000
anish-0.000
ked-0.000
joy-0.000
Look-0.000
Token"
Token ID1
Feature activation-3.01e-01

Pos logit contributions
asis+0.013
rig+0.012
place+0.012
row+0.011
 stump+0.011
Neg logit contributions
anish-0.010
ked-0.010
 Ow-0.010
arre-0.009
joy-0.009
TokenThat
Token ID2504
Feature activation+6.14e-01

Pos logit contributions
ked+0.010
anish+0.010
 anymore+0.009
 Ow+0.009
joy+0.009
Neg logit contributions
asis-0.016
rig-0.016
place-0.015
row-0.014
eh-0.014
Token is
Token ID318
Feature activation+1.70e+00

Pos logit contributions
asis+0.034
rig+0.033
place+0.032
eh+0.029
old+0.029
Neg logit contributions
ked-0.019
anish-0.019
 Ow-0.019
 anymore-0.017
adoes-0.017
Token called
Token ID1444
Feature activation+7.19e+00

Pos logit contributions
asis+0.106
rig+0.099
place+0.096
old+0.095
row+0.094
Neg logit contributions
 Ow-0.042
 anymore-0.042
ked-0.039
anish-0.039
adoes-0.035
Token a
Token ID257
Feature activation+1.70e+00

Pos logit contributions
asis+0.368
rig+0.345
place+0.338
row+0.308
eh+0.306
Neg logit contributions
ked-0.264
 Ow-0.255
anish-0.254
 anymore-0.242
joy-0.237
Token cell
Token ID2685
Feature activation+1.98e+00

Pos logit contributions
rig+0.073
asis+0.072
place+0.067
old+0.066
aling+0.063
Neg logit contributions
anish-0.069
 Ow-0.069
ked-0.068
 superstar-0.067
joy-0.066
Token,"
Token ID553
Feature activation-9.03e-01

Pos logit contributions
asis+0.091
rig+0.090
place+0.086
eh+0.077
old+0.077
Neg logit contributions
ked-0.080
anish-0.076
 anymore-0.074
 Ow-0.073
joy-0.071
Token his
Token ID465
Feature activation-1.32e+00

Pos logit contributions
ked+0.037
anish+0.035
 Ow+0.035
joy+0.034
 anymore+0.033
Neg logit contributions
asis-0.043
rig-0.041
place-0.039
row-0.035
eh-0.035
Token mum
Token ID25682
Feature activation-1.03e-01

Pos logit contributions
joy+0.049
ked+0.047
 Ow+0.046
 eyes+0.046
anish+0.045
Neg logit contributions
asis-0.067
rig-0.062
place-0.062
aling-0.059
isin-0.057
Token said
Token ID531
Feature activation+1.09e+00

Pos logit contributions
asis+0.009
rig+0.009
place+0.008
row+0.008
eh+0.007
Neg logit contributions
ked-0.009
anish-0.008
 Ow-0.008
joy-0.008
 anymore-0.008
Token,
Token ID11
Feature activation+5.80e-01

Pos logit contributions
asis+0.047
rig+0.045
place+0.044
row+0.042
old+0.041
Neg logit contributions
ked-0.045
 Ow-0.044
anish-0.044
joy-0.042
adoes-0.042
Token "
Token ID366
Feature activation-1.22e+00

Pos logit contributions
asis+0.037
rig+0.035
place+0.035
row+0.032
eh+0.032
Neg logit contributions
ked-0.014
anish-0.013
joy-0.013
 Ow-0.013
 anymore-0.012
TokenIt
Token ID1026
Feature activation+1.61e+00

Pos logit contributions
ked+0.036
anish+0.034
 Ow+0.033
joy+0.032
 anymore+0.031
Neg logit contributions
asis-0.071
rig-0.068
place-0.067
row-0.062
eh-0.062
Token is
Token ID318
Feature activation+1.52e+00

Pos logit contributions
asis+0.089
rig+0.086
place+0.084
eh+0.078
row+0.077
Neg logit contributions
ked-0.049
anish-0.049
 Ow-0.048
 anymore-0.045
adoes-0.044
Token called
Token ID1444
Feature activation+7.16e+00

Pos logit contributions
asis+0.088
rig+0.084
place+0.081
old+0.079
row+0.077
Neg logit contributions
 Ow-0.043
 anymore-0.042
anish-0.041
ked-0.040
joy-0.039
Token jelly
Token ID27644
Feature activation+3.08e+00

Pos logit contributions
asis+0.366
rig+0.348
place+0.337
row+0.309
old+0.308
Neg logit contributions
ked-0.260
anish-0.251
 Ow-0.250
 anymore-0.235
joy-0.234
Token.
Token ID13
Feature activation+1.38e+00

Pos logit contributions
rig+0.144
asis+0.139
place+0.134
old+0.133
aling+0.124
Neg logit contributions
 anymore-0.113
ked-0.113
anish-0.113
 Ow-0.106
 guys-0.100
Token Would
Token ID10928
Feature activation-1.93e-01

Pos logit contributions
asis+0.086
rig+0.081
place+0.081
eh+0.077
row+0.075
Neg logit contributions
ked-0.035
 Ow-0.034
anish-0.034
 anymore-0.030
joy-0.030
Token you
Token ID345
Feature activation+1.77e+00

Pos logit contributions
anish+0.008
 anymore+0.008
 Ow+0.008
ked+0.007
joy+0.007
Neg logit contributions
asis-0.009
rig-0.009
row-0.008
place-0.008
eh-0.007
Token like
Token ID588
Feature activation+2.34e+00

Pos logit contributions
asis+0.105
rig+0.099
place+0.093
rim+0.090
eh+0.089
Neg logit contributions
ked-0.049
 anymore-0.048
 Ow-0.046
anish-0.046
joy-0.043
Token
Token ID198
Feature activation+3.28e-01

Pos logit contributions
asis+0.008
place+0.008
rig+0.007
row+0.007
eh+0.007
Neg logit contributions
 Ow-0.004
anish-0.004
ked-0.004
joy-0.004
arre-0.003
Token"
Token ID1
Feature activation-1.91e-01

Pos logit contributions
asis+0.018
rig+0.017
place+0.017
row+0.015
 stump+0.015
Neg logit contributions
anish-0.011
 Ow-0.010
arre-0.010
ked-0.010
joy-0.009
TokenThat
Token ID2504
Feature activation+5.65e-01

Pos logit contributions
ked+0.006
anish+0.006
 Ow+0.006
joy+0.006
 anymore+0.006
Neg logit contributions
asis-0.010
rig-0.010
place-0.010
row-0.009
eh-0.009
Token pepper
Token ID13385
Feature activation+1.37e+00

Pos logit contributions
asis+0.026
rig+0.025
place+0.024
row+0.022
eh+0.022
Neg logit contributions
ked-0.023
anish-0.022
 Ow-0.022
joy-0.022
 anymore-0.021
Token is
Token ID318
Feature activation+1.50e+00

Pos logit contributions
rig+0.072
asis+0.071
place+0.067
old+0.064
aling+0.063
Neg logit contributions
anish-0.044
 anymore-0.041
ked-0.040
 Ow-0.040
adoes-0.038
Token called
Token ID1444
Feature activation+7.11e+00

Pos logit contributions
asis+0.082
rig+0.075
place+0.072
old+0.072
row+0.068
Neg logit contributions
 anymore-0.050
 Ow-0.048
ked-0.048
anish-0.047
adoes-0.044
Token a
Token ID257
Feature activation+1.57e+00

Pos logit contributions
asis+0.339
rig+0.319
place+0.306
old+0.283
eh+0.280
Neg logit contributions
ked-0.289
 Ow-0.287
anish-0.278
 anymore-0.267
joy-0.254
Token jumping
Token ID14284
Feature activation+7.27e-01

Pos logit contributions
asis+0.063
rig+0.061
place+0.058
old+0.054
row+0.054
Neg logit contributions
anish-0.071
ked-0.070
 Ow-0.070
joy-0.068
 anymore-0.068
Token pepper
Token ID13385
Feature activation-1.33e-01

Pos logit contributions
asis+0.032
rig+0.031
place+0.030
old+0.027
row+0.027
Neg logit contributions
ked-0.031
anish-0.030
 Ow-0.029
 anymore-0.029
joy-0.029
Token,"
Token ID553
Feature activation-8.03e-01

Pos logit contributions
ked+0.005
anish+0.005
 anymore+0.005
 Ow+0.005
adoes+0.004
Neg logit contributions
rig-0.006
asis-0.006
place-0.006
old-0.006
isin-0.005
Token said
Token ID531
Feature activation+6.69e-01

Pos logit contributions
ked+0.035
anish+0.034
 Ow+0.034
joy+0.033
 anymore+0.033
Neg logit contributions
asis-0.035
rig-0.033
place-0.032
row-0.029
eh-0.029
Token said
Token ID531
Feature activation+1.98e+00

Pos logit contributions
ked+0.016
anish+0.015
 anymore+0.014
joy+0.014
 Ow+0.014
Neg logit contributions
asis-0.015
rig-0.014
place-0.014
eh-0.012
row-0.012
Token,
Token ID11
Feature activation+1.01e+00

Pos logit contributions
asis+0.073
place+0.072
rig+0.069
old+0.067
isin+0.066
Neg logit contributions
 Ow-0.089
ked-0.089
anish-0.087
adoes-0.083
joy-0.083
Token "
Token ID366
Feature activation-1.13e+00

Pos logit contributions
rig+0.050
asis+0.050
place+0.047
 called+0.045
old+0.045
Neg logit contributions
ked-0.035
anish-0.034
 Ow-0.033
 anymore-0.031
joy-0.031
TokenThese
Token ID4711
Feature activation+7.19e-01

Pos logit contributions
ked+0.045
 anymore+0.043
anish+0.041
adoes+0.041
joy+0.041
Neg logit contributions
rig-0.053
asis-0.052
place-0.051
isin-0.046
old-0.046
Token are
Token ID389
Feature activation+3.67e-01

Pos logit contributions
place+0.035
asis+0.035
rig+0.034
old+0.031
isin+0.031
Neg logit contributions
ked-0.027
joy-0.025
 Ow-0.025
anish-0.024
 anymore-0.023
Token called
Token ID1444
Feature activation+7.10e+00

Pos logit contributions
asis+0.019
rig+0.018
place+0.017
row+0.016
eh+0.016
Neg logit contributions
ked-0.013
anish-0.012
 anymore-0.012
 Ow-0.012
joy-0.012
Token notes
Token ID4710
Feature activation+1.60e+00

Pos logit contributions
asis+0.337
rig+0.331
place+0.323
row+0.293
old+0.291
Neg logit contributions
ked-0.269
anish-0.259
 Ow-0.253
joy-0.252
 anymore-0.245
Token,
Token ID11
Feature activation+6.44e-01

Pos logit contributions
asis+0.078
rig+0.075
place+0.073
row+0.067
old+0.066
Neg logit contributions
ked-0.061
anish-0.059
 Ow-0.057
joy-0.057
 anymore-0.055
Token and
Token ID290
Feature activation+2.83e-02

Pos logit contributions
rig+0.028
asis+0.027
place+0.027
isin+0.024
old+0.024
Neg logit contributions
ked-0.028
anish-0.026
joy-0.026
 Ow-0.026
 anymore-0.024
Token they
Token ID484
Feature activation-1.11e+00

Pos logit contributions
asis+0.001
rig+0.001
place+0.001
old+0.001
row+0.001
Neg logit contributions
ked-0.001
anish-0.001
 Ow-0.001
joy-0.001
 anymore-0.001
Token are
Token ID389
Feature activation-8.26e-01

Pos logit contributions
ked+0.035
anish+0.033
 Ow+0.032
joy+0.032
 anymore+0.031
Neg logit contributions
asis-0.062
rig-0.059
place-0.058
row-0.054
eh-0.053
Token said
Token ID531
Feature activation+1.46e+00

Pos logit contributions
asis+0.037
rig+0.035
place+0.034
row+0.030
eh+0.030
Neg logit contributions
ked-0.045
anish-0.042
joy-0.041
 Ow-0.041
 anymore-0.040
Token,
Token ID11
Feature activation+9.44e-01

Pos logit contributions
asis+0.049
place+0.047
old+0.046
rig+0.045
row+0.045
Neg logit contributions
 Ow-0.069
ked-0.068
anish-0.066
arre-0.065
joy-0.064
Token "
Token ID366
Feature activation-1.09e+00

Pos logit contributions
asis+0.052
rig+0.051
place+0.049
row+0.046
eh+0.046
Neg logit contributions
ked-0.028
anish-0.027
 Ow-0.026
 anymore-0.026
joy-0.025
TokenThis
Token ID1212
Feature activation+1.47e+00

Pos logit contributions
ked+0.037
anish+0.036
joy+0.035
 Ow+0.034
 superstar+0.032
Neg logit contributions
asis-0.059
rig-0.055
place-0.053
row-0.050
eh-0.050
Token is
Token ID318
Feature activation+1.40e+00

Pos logit contributions
asis+0.087
rig+0.086
place+0.082
eh+0.078
row+0.077
Neg logit contributions
anish-0.039
 Ow-0.036
ked-0.036
 anymore-0.035
joy-0.034
Token called
Token ID1444
Feature activation+7.06e+00

Pos logit contributions
asis+0.091
rig+0.081
place+0.079
rim+0.079
row+0.078
Neg logit contributions
 anymore-0.032
 Ow-0.031
anish-0.030
ked-0.030
joy-0.029
Token striking
Token ID8871
Feature activation+7.24e-01

Pos logit contributions
asis+0.359
rig+0.335
place+0.326
eh+0.300
row+0.299
Neg logit contributions
ked-0.262
anish-0.254
 Ow-0.250
 anymore-0.237
joy-0.236
Token.
Token ID13
Feature activation+1.38e+00

Pos logit contributions
asis+0.035
rig+0.032
place+0.031
row+0.029
eh+0.029
Neg logit contributions
ked-0.028
anish-0.028
 Ow-0.027
 anymore-0.027
joy-0.026
Token Watch
Token ID6305
Feature activation+3.49e-01

Pos logit contributions
asis+0.078
rig+0.073
place+0.073
eh+0.068
row+0.067
Neg logit contributions
ked-0.043
anish-0.042
 Ow-0.041
joy-0.039
 anymore-0.038
Token what
Token ID644
Feature activation-1.51e+00

Pos logit contributions
asis+0.015
rig+0.014
place+0.013
eh+0.012
row+0.012
Neg logit contributions
ked-0.015
anish-0.015
 Ow-0.015
 anymore-0.015
adoes-0.014
Token I
Token ID314
Feature activation-1.26e-01

Pos logit contributions
ked+0.065
anish+0.061
joy+0.060
 Ow+0.060
 anymore+0.058
Neg logit contributions
asis-0.067
rig-0.064
place-0.064
old-0.057
row-0.057
Token says
Token ID1139
Feature activation+1.95e+00

Pos logit contributions
asis+0.065
rig+0.063
place+0.059
old+0.053
row+0.053
Neg logit contributions
ked-0.084
anish-0.081
 Ow-0.079
joy-0.079
 anymore-0.077
Token,
Token ID11
Feature activation+5.40e-01

Pos logit contributions
asis+0.046
place+0.045
ion+0.044
 called+0.042
old+0.041
Neg logit contributions
 tant-0.109
ked-0.107
 Ow-0.107
ifying-0.107
arre-0.106
Token "
Token ID366
Feature activation-1.20e+00

Pos logit contributions
asis+0.022
 called+0.021
rig+0.020
eh+0.020
isin+0.019
Neg logit contributions
 tant-0.021
anish-0.021
 Ow-0.021
 anymore-0.021
ked-0.020
TokenThey
Token ID2990
Feature activation+2.07e+00

Pos logit contributions
ked+0.038
anish+0.037
 Ow+0.037
joy+0.034
 anymore+0.033
Neg logit contributions
asis-0.065
rig-0.062
place-0.060
row-0.058
old-0.056
Token are
Token ID389
Feature activation+2.73e-01

Pos logit contributions
asis+0.122
rig+0.121
place+0.114
eh+0.110
row+0.108
Neg logit contributions
ked-0.055
anish-0.053
 anymore-0.052
 Ow-0.051
joy-0.045
Token called
Token ID1444
Feature activation+7.02e+00

Pos logit contributions
asis+0.015
rig+0.014
place+0.013
row+0.013
old+0.013
Neg logit contributions
 anymore-0.009
ked-0.009
 Ow-0.008
joy-0.008
adoes-0.008
Token seasons
Token ID7028
Feature activation+5.71e+00

Pos logit contributions
asis+0.336
rig+0.321
place+0.311
row+0.286
eh+0.283
Neg logit contributions
ked-0.275
anish-0.264
 Ow-0.259
joy-0.252
 anymore-0.252
Token.
Token ID13
Feature activation+8.11e-01

Pos logit contributions
asis+0.323
rig+0.311
place+0.304
eh+0.294
old+0.290
Neg logit contributions
 anymore-0.166
ked-0.161
anish-0.153
 Ow-0.145
adoes-0.141
Token And
Token ID843
Feature activation-5.65e-02

Pos logit contributions
asis+0.052
rig+0.050
place+0.049
eh+0.047
row+0.047
Neg logit contributions
 Ow-0.018
ked-0.018
anish-0.017
 anymore-0.016
joy-0.016
Token they
Token ID484
Feature activation-5.76e-01

Pos logit contributions
ked+0.002
 anymore+0.002
 Ow+0.002
anish+0.002
adoes+0.002
Neg logit contributions
asis-0.003
rig-0.003
eh-0.003
place-0.003
old-0.003
Token happen
Token ID1645
Feature activation-1.73e+00

Pos logit contributions
ked+0.013
 anymore+0.013
anish+0.012
 Ow+0.012
arre+0.011
Neg logit contributions
rig-0.035
asis-0.034
eh-0.032
place-0.032
row-0.032
Token,
Token ID11
Feature activation+9.33e-01

Pos logit contributions
asis+0.062
place+0.058
rig+0.057
row+0.055
old+0.054
Neg logit contributions
ked-0.071
 Ow-0.071
arre-0.069
anish-0.068
 tant-0.068
Token "
Token ID366
Feature activation-1.06e+00

Pos logit contributions
asis+0.052
rig+0.051
place+0.048
row+0.046
eh+0.045
Neg logit contributions
ked-0.027
anish-0.027
 Ow-0.026
 anymore-0.026
joy-0.025
TokenThis
Token ID1212
Feature activation+1.56e+00

Pos logit contributions
ked+0.030
anish+0.028
 Ow+0.027
joy+0.026
 anymore+0.024
Neg logit contributions
asis-0.062
rig-0.060
place-0.059
row-0.055
eh-0.055
Token lake
Token ID13546
Feature activation+3.96e+00

Pos logit contributions
rig+0.084
asis+0.083
place+0.080
old+0.077
eh+0.076
Neg logit contributions
anish-0.047
ked-0.046
 Ow-0.046
 anymore-0.045
joy-0.043
Token is
Token ID318
Feature activation+1.62e+00

Pos logit contributions
rig+0.239
asis+0.238
eh+0.230
place+0.228
old+0.221
Neg logit contributions
ked-0.086
 anymore-0.086
anish-0.085
 Ow-0.076
adoes-0.074
Token called
Token ID1444
Feature activation+7.02e+00

Pos logit contributions
asis+0.090
rig+0.086
old+0.084
place+0.082
isin+0.079
Neg logit contributions
 anymore-0.049
ked-0.045
 Ow-0.045
joy-0.043
ifying-0.043
Token the
Token ID262
Feature activation+3.60e+00

Pos logit contributions
asis+0.372
rig+0.354
place+0.341
eh+0.325
old+0.323
Neg logit contributions
ked-0.246
 Ow-0.235
anish-0.228
 anymore-0.219
joy-0.215
Token Bright
Token ID17558
Feature activation+3.12e+00

Pos logit contributions
asis+0.153
rig+0.148
place+0.141
row+0.129
old+0.129
Neg logit contributions
ked-0.159
anish-0.153
 Ow-0.151
joy-0.148
 anymore-0.148
Token Blue
Token ID4518
Feature activation-4.36e-01

Pos logit contributions
asis+0.147
rig+0.143
place+0.138
eh+0.131
old+0.129
Neg logit contributions
ked-0.121
 anymore-0.114
anish-0.114
 Ow-0.114
joy-0.108
Token Eye
Token ID14144
Feature activation+2.81e+00

Pos logit contributions
ked+0.016
anish+0.016
 Ow+0.015
joy+0.015
 anymore+0.015
Neg logit contributions
asis-0.021
rig-0.021
place-0.020
row-0.018
eh-0.018
Token,
Token ID11
Feature activation-3.02e-01

Pos logit contributions
asis+0.145
rig+0.141
place+0.135
eh+0.128
isin+0.128
Neg logit contributions
ked-0.094
 anymore-0.093
anish-0.089
 Ow-0.084
joy-0.082
Token
Token ID198
Feature activation+9.62e-01

Pos logit contributions
ked+0.020
 Ow+0.019
anish+0.019
 anymore+0.018
joy+0.018
Neg logit contributions
asis-0.030
rig-0.028
place-0.028
row-0.026
eh-0.026
Token
Token ID198
Feature activation+1.09e+00

Pos logit contributions
asis+0.046
rig+0.044
place+0.043
row+0.039
eh+0.038
Neg logit contributions
ked-0.037
anish-0.037
 Ow-0.036
joy-0.035
 anymore-0.034
Token"
Token ID1
Feature activation+3.06e-01

Pos logit contributions
asis+0.048
rig+0.045
place+0.044
row+0.040
eh+0.039
Neg logit contributions
ked-0.047
anish-0.046
 Ow-0.045
joy-0.044
 anymore-0.043
TokenThat
Token ID2504
Feature activation+1.06e+00

Pos logit contributions
asis+0.017
rig+0.017
place+0.016
row+0.015
eh+0.015
Neg logit contributions
ked-0.010
anish-0.009
 Ow-0.009
joy-0.009
 anymore-0.009
Token's
Token ID338
Feature activation+1.90e+00

Pos logit contributions
asis+0.055
rig+0.053
place+0.052
row+0.048
eh+0.047
Neg logit contributions
ked-0.037
anish-0.035
 Ow-0.034
joy-0.034
 anymore-0.033
Token called
Token ID1444
Feature activation+7.01e+00

Pos logit contributions
asis+0.119
rig+0.111
place+0.110
old+0.107
row+0.105
Neg logit contributions
 Ow-0.047
 anymore-0.044
anish-0.043
ked-0.043
adoes-0.040
Token the
Token ID262
Feature activation+4.30e+00

Pos logit contributions
asis+0.335
rig+0.329
place+0.319
row+0.294
eh+0.288
Neg logit contributions
ked-0.266
anish-0.253
joy-0.249
 Ow-0.243
 anymore-0.241
Token clouds
Token ID15114
Feature activation+4.31e+00

Pos logit contributions
asis+0.205
rig+0.197
place+0.189
old+0.175
row+0.173
Neg logit contributions
ked-0.169
anish-0.165
 Ow-0.161
joy-0.157
 anymore-0.157
Token,
Token ID11
Feature activation+1.07e+00

Pos logit contributions
asis+0.201
rig+0.195
place+0.187
eh+0.174
row+0.169
Neg logit contributions
ked-0.169
 anymore-0.163
anish-0.161
 Ow-0.156
adoes-0.148
Token John
Token ID1757
Feature activation+2.00e-02

Pos logit contributions
asis+0.053
rig+0.051
place+0.050
old+0.045
isin+0.045
Neg logit contributions
ked-0.040
anish-0.038
joy-0.037
 Ow-0.035
 anymore-0.035
Token,"
Token ID553
Feature activation-5.74e-01

Pos logit contributions
asis+0.001
rig+0.001
place+0.001
eh+0.001
isin+0.001
Neg logit contributions
ked-0.001
 anymore-0.001
 Ow-0.001
anish-0.001
joy-0.001
Token it
Token ID340
Feature activation-1.00e+00

Pos logit contributions
ked+0.007
anish+0.006
joy+0.006
arre+0.006
 anymore+0.006
Neg logit contributions
asis-0.008
place-0.007
rig-0.007
row-0.007
aster-0.007
Token.
Token ID13
Feature activation-1.76e-01

Pos logit contributions
ked+0.031
 anymore+0.030
anish+0.027
 Ow+0.026
 again+0.026
Neg logit contributions
asis-0.059
rig-0.057
place-0.055
rim-0.052
old-0.052
Token "
Token ID366
Feature activation-2.35e+00

Pos logit contributions
ked+0.005
 Ow+0.004
anish+0.004
 anymore+0.004
joy+0.004
Neg logit contributions
asis-0.011
rig-0.010
place-0.010
row-0.010
isin-0.009
TokenThis
Token ID1212
Feature activation+1.03e+00

Pos logit contributions
ked+0.088
 anymore+0.082
anish+0.081
joy+0.080
 Ow+0.079
Neg logit contributions
asis-0.118
rig-0.112
place-0.112
eh-0.104
row-0.101
Token is
Token ID318
Feature activation+1.09e+00

Pos logit contributions
asis+0.051
place+0.046
rig+0.046
eh+0.043
row+0.042
Neg logit contributions
ked-0.044
joy-0.038
anish-0.038
 Ow-0.036
 anymore-0.036
Token called
Token ID1444
Feature activation+7.01e+00

Pos logit contributions
asis+0.065
rig+0.061
old+0.059
place+0.059
row+0.057
Neg logit contributions
 Ow-0.032
 anymore-0.031
anish-0.028
ked-0.028
adoes-0.026
Token flour
Token ID10601
Feature activation+4.04e+00

Pos logit contributions
asis+0.372
rig+0.354
place+0.345
old+0.317
row+0.316
Neg logit contributions
ked-0.242
anish-0.232
 Ow-0.231
 anymore-0.218
joy-0.216
Token,"
Token ID553
Feature activation+1.54e-01

Pos logit contributions
rig+0.208
asis+0.207
place+0.199
old+0.185
eh+0.183
Neg logit contributions
ked-0.139
 anymore-0.135
anish-0.133
 Ow-0.132
adoes-0.120
Token she
Token ID673
Feature activation+8.10e-01

Pos logit contributions
asis+0.008
rig+0.008
place+0.008
row+0.007
aling+0.007
Neg logit contributions
ked-0.005
 Ow-0.005
anish-0.005
adoes-0.005
Wow-0.005
Token told
Token ID1297
Feature activation+3.38e-01

Pos logit contributions
asis+0.040
place+0.037
rig+0.035
row+0.031
rim+0.030
Neg logit contributions
ked-0.034
 Ow-0.031
anish-0.031
 superstar-0.029
arre-0.028
Token Tim
Token ID5045
Feature activation+2.69e+00

Pos logit contributions
asis+0.019
rig+0.018
place+0.018
row+0.017
eh+0.017
Neg logit contributions
ked-0.010
anish-0.010
joy-0.009
 Ow-0.009
 anymore-0.009
Token,
Token ID11
Feature activation+6.98e-01

Pos logit contributions
asis+0.102
rig+0.100
place+0.097
eh+0.089
row+0.087
Neg logit contributions
ked-0.062
anish-0.058
 anymore-0.057
 Ow-0.057
joy-0.056
Token this
Token ID428
Feature activation+6.42e-01

Pos logit contributions
asis+0.031
rig+0.029
place+0.029
row+0.026
old+0.025
Neg logit contributions
ked-0.030
anish-0.029
 Ow-0.028
joy-0.028
 anymore-0.028
Token little
Token ID1310
Feature activation+1.16e+00

Pos logit contributions
asis+0.033
rig+0.032
place+0.031
old+0.028
row+0.028
Neg logit contributions
ked-0.022
anish-0.022
 Ow-0.022
joy-0.021
 anymore-0.021
Token thing
Token ID1517
Feature activation-1.36e+00

Pos logit contributions
asis+0.051
rig+0.049
place+0.047
row+0.042
eh+0.042
Neg logit contributions
ked-0.051
anish-0.049
 Ow-0.048
joy-0.047
 anymore-0.047
Token is
Token ID318
Feature activation+1.17e+00

Pos logit contributions
ked+0.041
anish+0.039
 Ow+0.038
 anymore+0.037
joy+0.036
Neg logit contributions
asis-0.077
rig-0.074
place-0.072
row-0.067
eh-0.067
Token called
Token ID1444
Feature activation+6.98e+00

Pos logit contributions
asis+0.070
rig+0.067
place+0.064
old+0.062
isin+0.061
Neg logit contributions
 anymore-0.032
ked-0.031
 Ow-0.031
anish-0.030
adoes-0.029
Token a
Token ID257
Feature activation+1.51e+00

Pos logit contributions
asis+0.369
rig+0.351
place+0.340
old+0.314
row+0.312
Neg logit contributions
ked-0.242
anish-0.233
 Ow-0.232
 anymore-0.220
joy-0.217
Token mole
Token ID9411
Feature activation+1.12e+00

Pos logit contributions
asis+0.062
rig+0.060
place+0.058
row+0.052
old+0.052
Neg logit contributions
ked-0.067
anish-0.066
 Ow-0.065
joy-0.064
 anymore-0.063
Token.
Token ID13
Feature activation+9.96e-01

Pos logit contributions
asis+0.055
rig+0.054
place+0.052
isin+0.047
old+0.047
Neg logit contributions
ked-0.043
 anymore-0.041
anish-0.040
 Ow-0.040
joy-0.038
Token He
Token ID679
Feature activation+8.50e-01

Pos logit contributions
asis+0.065
rig+0.062
place+0.061
eh+0.058
row+0.057
Neg logit contributions
ked-0.023
 Ow-0.022
anish-0.022
joy-0.019
 anymore-0.019
Token is
Token ID318
Feature activation+9.56e-01

Pos logit contributions
asis+0.048
rig+0.047
place+0.045
eh+0.042
row+0.042
Neg logit contributions
ked-0.026
 Ow-0.024
anish-0.023
 anymore-0.022
joy-0.021
Token
Token ID198
Feature activation+2.94e-01

Pos logit contributions
ked+0.028
anish+0.027
 Ow+0.026
joy+0.026
 anymore+0.025
Neg logit contributions
asis-0.036
rig-0.035
place-0.033
row-0.031
old-0.030
Token
Token ID198
Feature activation+3.82e-01

Pos logit contributions
asis+0.017
rig+0.016
place+0.016
row+0.015
eh+0.014
Neg logit contributions
 Ow-0.009
anish-0.008
ked-0.008
joy-0.008
 anymore-0.008
Token"
Token ID1
Feature activation-1.38e-01

Pos logit contributions
asis+0.020
rig+0.019
place+0.019
row+0.017
isin+0.016
Neg logit contributions
anish-0.014
ked-0.013
 Ow-0.012
joy-0.012
Look-0.012
TokenIt
Token ID1026
Feature activation+1.34e+00

Pos logit contributions
ked+0.005
joy+0.004
anish+0.004
 anymore+0.004
 Ow+0.004
Neg logit contributions
asis-0.007
rig-0.007
place-0.007
row-0.006
eh-0.006
Token is
Token ID318
Feature activation+1.40e+00

Pos logit contributions
asis+0.067
rig+0.065
place+0.063
row+0.058
eh+0.057
Neg logit contributions
ked-0.049
anish-0.047
joy-0.046
 Ow-0.046
 anymore-0.044
Token called
Token ID1444
Feature activation+6.98e+00

Pos logit contributions
asis+0.074
rig+0.071
place+0.069
old+0.064
row+0.064
Neg logit contributions
ked-0.047
anish-0.046
 Ow-0.046
 anymore-0.045
joy-0.044
Token chalk
Token ID30860
Feature activation+2.69e+00

Pos logit contributions
asis+0.359
rig+0.345
place+0.336
row+0.309
eh+0.306
Neg logit contributions
ked-0.249
anish-0.238
 Ow-0.232
joy-0.227
 anymore-0.225
Token,"
Token ID553
Feature activation-8.52e-01

Pos logit contributions
asis+0.119
rig+0.113
place+0.110
row+0.100
eh+0.099
Neg logit contributions
ked-0.115
anish-0.110
 Ow-0.108
joy-0.107
 anymore-0.105
Token said
Token ID531
Feature activation+8.81e-01

Pos logit contributions
ked+0.033
anish+0.031
 Ow+0.031
 anymore+0.030
joy+0.030
Neg logit contributions
asis-0.040
rig-0.039
place-0.038
old-0.035
eh-0.035
Token Dad
Token ID17415
Feature activation+4.92e-01

Pos logit contributions
asis+0.038
rig+0.037
place+0.036
old+0.035
 called+0.035
Neg logit contributions
anish-0.034
ked-0.033
 Ow-0.033
arre-0.032
ifying-0.031
Token.
Token ID13
Feature activation+4.75e-01

Pos logit contributions
asis+0.028
place+0.026
rig+0.026
eh+0.024
ands+0.023
Neg logit contributions
ked-0.018
 anymore-0.016
joy-0.015
 again-0.014
anish-0.014
Token
Token ID26391
Feature activation+1.53e+00

Pos logit contributions
erry+0.071
rig+0.070
place+0.069
asis+0.068
row+0.067
Neg logit contributions
ked-0.056
joy-0.053
anish-0.051
ved-0.048
 anymore-0.048
Token
Token ID129
Feature activation+2.53e-01

Pos logit contributions
asis+0.074
rig+0.070
place+0.068
row+0.062
eh+0.062
Neg logit contributions
ked-0.059
anish-0.057
 Ow-0.056
 anymore-0.054
joy-0.054
Token
Token ID241
Feature activation+2.93e+00

Pos logit contributions
place+0.012
asis+0.012
row+0.011
erry+0.011
atmeal+0.011
Neg logit contributions
ked-0.010
 anymore-0.008
 Ow-0.008
joy-0.008
adoes-0.008
TokenI
Token ID40
Feature activation+1.59e+00

Pos logit contributions
asis+0.144
rig+0.140
place+0.135
old+0.124
eh+0.122
Neg logit contributions
ked-0.111
anish-0.106
 anymore-0.101
 Ow-0.101
joy-0.098
Token am
Token ID716
Feature activation+1.96e+00

Pos logit contributions
asis+0.080
place+0.075
rig+0.075
row+0.070
isin+0.069
Neg logit contributions
ked-0.056
 Ow-0.054
anish-0.053
joy-0.050
 anymore-0.050
Token called
Token ID1444
Feature activation+6.97e+00

Pos logit contributions
asis+0.119
rig+0.113
place+0.113
row+0.106
isin+0.098
Neg logit contributions
ked-0.055
joy-0.054
 anymore-0.052
 Ow-0.052
anish-0.045
Token a
Token ID257
Feature activation+1.78e+00

Pos logit contributions
asis+0.353
rig+0.336
place+0.326
row+0.300
eh+0.299
Neg logit contributions
ked-0.257
anish-0.246
 Ow-0.246
joy-0.238
 anymore-0.236
Token squirrel
Token ID33039
Feature activation+3.68e-01

Pos logit contributions
asis+0.089
rig+0.087
place+0.083
row+0.079
old+0.078
Neg logit contributions
ked-0.062
anish-0.060
 Ow-0.060
joy-0.059
 anymore-0.058
Token.
Token ID13
Feature activation+4.94e-01

Pos logit contributions
asis+0.018
rig+0.018
place+0.017
isin+0.016
row+0.015
Neg logit contributions
ked-0.014
 anymore-0.013
anish-0.013
 Ow-0.012
joy-0.012
Token I
Token ID314
Feature activation-1.23e-01

Pos logit contributions
asis+0.027
rig+0.025
place+0.025
row+0.023
eh+0.023
Neg logit contributions
ked-0.017
 Ow-0.016
anish-0.016
joy-0.015
 anymore-0.015
Token have
Token ID423
Feature activation+9.80e-02

Pos logit contributions
ked+0.005
anish+0.005
 Ow+0.005
 anymore+0.004
joy+0.004
Neg logit contributions
asis-0.006
rig-0.006
place-0.005
row-0.005
eh-0.005
Token replied
Token ID8712
Feature activation+6.72e-01

Pos logit contributions
ked+0.078
anish+0.074
 Ow+0.073
joy+0.072
 anymore+0.072
Neg logit contributions
asis-0.070
rig-0.067
place-0.065
row-0.058
eh-0.057
Token,
Token ID11
Feature activation+1.21e+00

Pos logit contributions
asis+0.026
rig+0.025
place+0.025
row+0.023
old+0.023
Neg logit contributions
 Ow-0.030
ked-0.029
anish-0.029
joy-0.028
adoes-0.027
Token "
Token ID366
Feature activation-8.89e-01

Pos logit contributions
asis+0.062
rig+0.060
place+0.057
eh+0.055
 called+0.055
Neg logit contributions
anish-0.040
ked-0.039
 Ow-0.038
 anymore-0.037
 tant-0.036
TokenThat
Token ID2504
Feature activation+7.18e-01

Pos logit contributions
ked+0.030
anish+0.029
joy+0.028
 Ow+0.028
 anymore+0.028
Neg logit contributions
asis-0.047
rig-0.046
place-0.045
row-0.041
eh-0.041
Token's
Token ID338
Feature activation+1.80e+00

Pos logit contributions
asis+0.031
place+0.027
rig+0.027
eh+0.025
old+0.025
Neg logit contributions
ked-0.034
joy-0.031
anish-0.031
 anymore-0.029
 Ow-0.029
Token called
Token ID1444
Feature activation+6.96e+00

Pos logit contributions
asis+0.110
rig+0.105
place+0.103
row+0.098
old+0.097
Neg logit contributions
 Ow-0.048
ked-0.046
 anymore-0.044
anish-0.043
adoes-0.042
Token a
Token ID257
Feature activation+1.98e+00

Pos logit contributions
asis+0.343
rig+0.329
place+0.320
row+0.293
eh+0.290
Neg logit contributions
ked-0.263
anish-0.251
 Ow-0.246
joy-0.241
 anymore-0.239
Token mustache
Token ID49303
Feature activation-1.29e+00

Pos logit contributions
asis+0.096
rig+0.090
place+0.088
eh+0.081
row+0.079
Neg logit contributions
ked-0.080
anish-0.075
 Ow-0.073
 anymore-0.072
joy-0.071
Token.
Token ID13
Feature activation+1.16e+00

Pos logit contributions
ked+0.050
anish+0.048
 anymore+0.047
 Ow+0.046
joy+0.044
Neg logit contributions
asis-0.061
rig-0.061
place-0.058
eh-0.053
row-0.052
Token There
Token ID1318
Feature activation+1.08e+00

Pos logit contributions
asis+0.073
rig+0.070
place+0.069
eh+0.064
row+0.064
Neg logit contributions
ked-0.029
anish-0.027
 Ow-0.027
joy-0.025
 anymore-0.024
Token are
Token ID389
Feature activation-1.18e+00

Pos logit contributions
asis+0.062
rig+0.061
place+0.058
eh+0.055
row+0.054
Neg logit contributions
ked-0.031
anish-0.030
 Ow-0.029
 anymore-0.029
adoes-0.027
Token bowl
Token ID9396
Feature activation-1.19e+00

Pos logit contributions
joy+0.093
anish+0.091
ked+0.089
 anymore+0.088
 tant+0.088
Neg logit contributions
rig-0.108
asis-0.108
place-0.099
old-0.096
row-0.096
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
ked+0.033
 anymore+0.030
anish+0.030
joy+0.029
 Ow+0.027
Neg logit contributions
asis-0.070
rig-0.070
place-0.067
isin-0.063
old-0.061
Token "
Token ID366
Feature activation-2.41e+00

Pos logit contributions
ked+0.003
 Ow+0.003
anish+0.003
joy+0.003
 anymore+0.003
Neg logit contributions
asis-0.006
place-0.006
rig-0.006
row-0.005
rim-0.005
TokenThis
Token ID1212
Feature activation+9.08e-01

Pos logit contributions
ked+0.096
anish+0.091
 Ow+0.089
 anymore+0.089
joy+0.088
Neg logit contributions
asis-0.114
rig-0.109
place-0.107
eh-0.097
row-0.097
Token is
Token ID318
Feature activation+1.03e+00

Pos logit contributions
asis+0.045
rig+0.044
place+0.042
row+0.039
old+0.038
Neg logit contributions
ked-0.034
anish-0.033
 Ow-0.032
joy-0.031
 anymore-0.031
Token called
Token ID1444
Feature activation+6.94e+00

Pos logit contributions
asis+0.063
old+0.058
rig+0.057
place+0.056
row+0.054
Neg logit contributions
 anymore-0.028
 Ow-0.027
anish-0.025
ked-0.024
 no-0.023
Token caul
Token ID46087
Feature activation+1.39e+00

Pos logit contributions
asis+0.342
rig+0.328
place+0.319
row+0.292
eh+0.289
Neg logit contributions
ked-0.262
anish-0.251
 Ow-0.245
joy-0.240
 anymore-0.238
Tokeniflower
Token ID42642
Feature activation+3.03e+00

Pos logit contributions
rig+0.043
asis+0.038
old+0.036
place+0.036
roads+0.031
Neg logit contributions
anish-0.076
 Ow-0.072
ked-0.072
 anymore-0.070
rots-0.069
Token soup
Token ID17141
Feature activation+1.48e+00

Pos logit contributions
rig+0.156
asis+0.151
place+0.143
isin+0.136
aling+0.135
Neg logit contributions
 anymore-0.100
anish-0.100
ked-0.096
 Ow-0.094
 again-0.086
Token,"
Token ID553
Feature activation+5.18e-02

Pos logit contributions
rig+0.073
asis+0.072
place+0.069
old+0.066
aling+0.065
Neg logit contributions
 anymore-0.051
ked-0.049
anish-0.049
 Ow-0.047
adoes-0.043
Token said
Token ID531
Feature activation+1.13e+00

Pos logit contributions
asis+0.003
rig+0.003
place+0.003
row+0.002
rim+0.002
Neg logit contributions
ked-0.002
 Ow-0.002
anish-0.002
 anymore-0.002
joy-0.002
Token.
Token ID13
Feature activation+2.22e-01

Pos logit contributions
asis+0.034
rig+0.033
place+0.033
row+0.030
old+0.030
Neg logit contributions
ked-0.030
 Ow-0.029
anish-0.028
joy-0.028
 anymore-0.027
Token "
Token ID366
Feature activation-2.05e+00

Pos logit contributions
asis+0.010
rig+0.010
place+0.010
old+0.009
eh+0.009
Neg logit contributions
ked-0.009
anish-0.008
 Ow-0.008
 anymore-0.008
joy-0.008
TokenThe
Token ID464
Feature activation+1.58e+00

Pos logit contributions
ked+0.076
 anymore+0.072
 Ow+0.069
anish+0.069
joy+0.067
Neg logit contributions
asis-0.101
rig-0.099
place-0.098
eh-0.091
old-0.090
Token game
Token ID983
Feature activation-3.70e-01

Pos logit contributions
asis+0.068
place+0.066
rig+0.066
isin+0.057
eh+0.057
Neg logit contributions
ked-0.072
 Ow-0.066
joy-0.063
anish-0.062
 anymore-0.061
Token is
Token ID318
Feature activation+1.19e+00

Pos logit contributions
ked+0.012
anish+0.011
 Ow+0.011
joy+0.011
 anymore+0.011
Neg logit contributions
asis-0.020
rig-0.019
place-0.019
row-0.017
eh-0.017
Token called
Token ID1444
Feature activation+6.93e+00

Pos logit contributions
asis+0.060
rig+0.056
place+0.055
row+0.051
old+0.050
Neg logit contributions
ked-0.044
 anymore-0.043
anish-0.042
 Ow-0.041
joy-0.041
Token Match
Token ID13225
Feature activation+2.20e+00

Pos logit contributions
rig+0.317
asis+0.309
place+0.305
row+0.273
old+0.268
Neg logit contributions
ked-0.270
joy-0.259
anish-0.255
 Ow-0.251
 anymore-0.243
Token!"
Token ID2474
Feature activation+1.17e+00

Pos logit contributions
asis+0.094
rig+0.092
place+0.089
row+0.082
old+0.082
Neg logit contributions
ked-0.094
 Ow-0.091
anish-0.090
joy-0.087
 anymore-0.085
Token Everyone
Token ID11075
Feature activation+6.56e-03

Pos logit contributions
asis+0.052
rig+0.050
place+0.048
old+0.044
row+0.044
Neg logit contributions
ked-0.049
anish-0.047
 Ow-0.046
joy-0.046
 anymore-0.045
Token was
Token ID373
Feature activation+3.68e-01

Pos logit contributions
asis+0.000
rig+0.000
place+0.000
old+0.000
row+0.000
Neg logit contributions
ked-0.000
 Ow-0.000
anish-0.000
joy-0.000
 anymore-0.000
Token quiet
Token ID5897
Feature activation+1.98e+00

Pos logit contributions
asis+0.016
rig+0.015
place+0.015
old+0.013
eh+0.013
Neg logit contributions
ked-0.016
anish-0.016
 Ow-0.016
joy-0.015
 anymore-0.015
Token and
Token ID290
Feature activation+4.28e-01

Pos logit contributions
asis+0.035
rig+0.034
place+0.033
old+0.031
eh+0.030
Neg logit contributions
 anymore-0.022
ked-0.021
anish-0.020
 Ow-0.019
joy-0.019
Token Annie
Token ID25860
Feature activation+7.18e-02

Pos logit contributions
asis+0.021
rig+0.020
place+0.019
row+0.018
eh+0.017
Neg logit contributions
ked-0.017
anish-0.016
 Ow-0.016
joy-0.015
 anymore-0.015
Token said
Token ID531
Feature activation+2.24e+00

Pos logit contributions
asis+0.003
rig+0.003
place+0.003
row+0.002
eh+0.002
Neg logit contributions
ked-0.003
anish-0.003
 Ow-0.003
joy-0.003
 anymore-0.003
Token it
Token ID340
Feature activation+2.25e+00

Pos logit contributions
place+0.080
asis+0.079
 called+0.075
old+0.074
isin+0.074
Neg logit contributions
 Ow-0.101
arre-0.098
ked-0.098
anish-0.097
adoes-0.096
Token was
Token ID373
Feature activation+1.94e+00

Pos logit contributions
asis+0.114
rig+0.111
place+0.108
row+0.100
eh+0.097
Neg logit contributions
ked-0.080
anish-0.077
joy-0.076
 Ow-0.076
 anymore-0.072
Token called
Token ID1444
Feature activation+6.92e+00

Pos logit contributions
asis+0.108
rig+0.104
place+0.101
row+0.093
old+0.092
Neg logit contributions
ked-0.062
anish-0.058
 Ow-0.058
 anymore-0.058
joy-0.057
Token
Token ID6184
Feature activation+1.65e+00

Pos logit contributions
asis+0.316
rig+0.315
place+0.304
row+0.280
eh+0.280
Neg logit contributions
ked-0.262
anish-0.256
joy-0.243
 Ow-0.240
 anymore-0.237
Token
Token ID95
Feature activation+1.77e+00

Pos logit contributions
asis+0.076
row+0.072
rig+0.069
eh+0.068
b+0.068
Neg logit contributions
ked-0.063
 superstar-0.063
 anymore-0.063
anish-0.062
joy-0.061
Token
Token ID26391
Feature activation+1.56e+00

Pos logit contributions
asis+0.084
place+0.078
row+0.077
erry+0.077
rig+0.074
Neg logit contributions
anish-0.068
 superstar-0.064
 anymore-0.063
ked-0.062
joy-0.061
Token˜
Token ID41185
Feature activation+5.36e-01

Pos logit contributions
asis+0.075
rig+0.069
place+0.065
old+0.061
eh+0.061
Neg logit contributions
ked-0.064
 tant-0.059
anish-0.059
 Ow-0.058
 anymore-0.054
TokenPretty
Token ID35700
Feature activation+1.66e+00

Pos logit contributions
asis+0.023
rig+0.022
place+0.021
row+0.020
old+0.019
Neg logit contributions
ked-0.023
anish-0.022
 Ow-0.022
joy-0.021
 anymore-0.021
Token.
Token ID13
Feature activation+4.33e-01

Pos logit contributions
asis+0.028
rig+0.027
place+0.026
eh+0.025
isin+0.024
Neg logit contributions
ked-0.017
 anymore-0.017
anish-0.017
 Ow-0.016
joy-0.016
Token She
Token ID1375
Feature activation+1.60e+00

Pos logit contributions
asis+0.022
rig+0.021
place+0.021
row+0.019
eh+0.019
Neg logit contributions
ked-0.015
anish-0.015
 Ow-0.014
joy-0.014
 anymore-0.014
Token said
Token ID531
Feature activation+1.87e+00

Pos logit contributions
asis+0.073
rig+0.067
place+0.066
row+0.058
isin+0.057
Neg logit contributions
ked-0.070
anish-0.065
 Ow-0.064
joy-0.063
 anymore-0.060
Token it
Token ID340
Feature activation+2.11e+00

Pos logit contributions
old+0.061
place+0.060
asis+0.060
 called+0.058
isin+0.055
Neg logit contributions
anish-0.087
 Ow-0.087
arre-0.087
ked-0.086
ifying-0.084
Token was
Token ID373
Feature activation+1.84e+00

Pos logit contributions
asis+0.105
rig+0.102
place+0.100
row+0.092
old+0.090
Neg logit contributions
ked-0.077
anish-0.074
joy-0.074
 Ow-0.072
 anymore-0.070
Token called
Token ID1444
Feature activation+6.91e+00

Pos logit contributions
asis+0.114
rig+0.108
place+0.105
old+0.099
row+0.098
Neg logit contributions
ked-0.049
 Ow-0.046
 anymore-0.046
joy-0.044
anish-0.044
Token dust
Token ID8977
Feature activation+4.18e+00

Pos logit contributions
asis+0.361
rig+0.348
place+0.339
row+0.312
eh+0.309
Neg logit contributions
ked-0.240
anish-0.229
 Ow-0.223
joy-0.219
 anymore-0.217
Token.
Token ID13
Feature activation+6.94e-01

Pos logit contributions
asis+0.190
rig+0.181
place+0.177
row+0.166
eh+0.158
Neg logit contributions
ked-0.169
anish-0.165
 Ow-0.162
joy-0.162
 anymore-0.154
Token He
Token ID679
Feature activation+5.56e-01

Pos logit contributions
rig+0.031
asis+0.031
place+0.030
old+0.029
aster+0.028
Neg logit contributions
ked-0.026
anish-0.025
 prope-0.023
 superstar-0.023
 anymore-0.023
Token asked
Token ID1965
Feature activation+3.16e+00

Pos logit contributions
asis+0.025
rig+0.024
place+0.023
row+0.021
eh+0.020
Neg logit contributions
ked-0.024
anish-0.022
 Ow-0.022
joy-0.021
 anymore-0.021
Token her
Token ID607
Feature activation+2.63e+00

Pos logit contributions
asis+0.164
rig+0.157
place+0.154
row+0.141
eh+0.140
Neg logit contributions
ked-0.113
anish-0.108
 Ow-0.105
joy-0.103
 anymore-0.102
Token,
Token ID11
Feature activation+6.29e-01

Pos logit contributions
asis+0.137
rig+0.132
place+0.129
row+0.119
eh+0.118
Neg logit contributions
ked-0.086
anish-0.080
 Ow-0.078
joy-0.078
 anymore-0.077
Token the
Token ID262
Feature activation+1.63e+00

Pos logit contributions
asis+0.030
rig+0.029
place+0.029
eh+0.027
old+0.027
Neg logit contributions
anish-0.023
ked-0.023
 Ow-0.021
 tant-0.021
 anymore-0.021
Token other
Token ID584
Feature activation+1.01e+00

Pos logit contributions
asis+0.069
rig+0.066
place+0.064
eh+0.057
old+0.056
Neg logit contributions
ked-0.073
anish-0.070
 Ow-0.067
 anymore-0.067
adoes-0.065
Token child
Token ID1200
Feature activation+1.12e+00

Pos logit contributions
asis+0.049
place+0.048
rig+0.048
old+0.044
row+0.042
Neg logit contributions
ked-0.038
anish-0.036
 Ow-0.035
 prope-0.033
adoes-0.033
Token was
Token ID373
Feature activation+9.12e-01

Pos logit contributions
asis+0.060
rig+0.058
place+0.056
row+0.052
eh+0.051
Neg logit contributions
ked-0.038
 anymore-0.036
anish-0.036
joy-0.035
 Ow-0.034
Token called
Token ID1444
Feature activation+6.81e+00

Pos logit contributions
asis+0.044
rig+0.042
place+0.041
row+0.037
eh+0.037
Neg logit contributions
ked-0.036
anish-0.034
 Ow-0.033
joy-0.033
 anymore-0.033
Token Bob
Token ID5811
Feature activation+2.78e+00

Pos logit contributions
asis+0.365
rig+0.352
place+0.343
row+0.317
eh+0.314
Neg logit contributions
ked-0.227
anish-0.216
 Ow-0.210
joy-0.205
 anymore-0.203
Token.
Token ID13
Feature activation+4.98e-01

Pos logit contributions
asis+0.121
rig+0.116
place+0.112
row+0.102
eh+0.101
Neg logit contributions
ked-0.120
anish-0.117
 Ow-0.114
joy-0.111
 anymore-0.110
Token
Token ID220
Feature activation-9.15e-01

Pos logit contributions
asis+0.024
rig+0.024
place+0.022
old+0.021
eh+0.021
Neg logit contributions
ked-0.019
anish-0.019
 Ow-0.017
joy-0.017
 anymore-0.017
Token
Token ID198
Feature activation+6.41e-01

Pos logit contributions
ked+0.035
anish+0.033
 Ow+0.032
joy+0.032
 anymore+0.031
Neg logit contributions
asis-0.045
rig-0.043
place-0.042
row-0.038
eh-0.038
TokenAmy
Token ID40797
Feature activation+1.35e+00

Pos logit contributions
asis+0.030
rig+0.029
place+0.028
old+0.026
row+0.026
Neg logit contributions
ked-0.026
anish-0.024
 Ow-0.024
joy-0.023
 anymore-0.023
Token flew
Token ID13112
Feature activation-9.68e-01

Pos logit contributions
ked+0.023
anish+0.022
 Ow+0.021
joy+0.021
 anymore+0.021
Neg logit contributions
asis-0.029
rig-0.028
place-0.027
row-0.025
eh-0.025
Token away
Token ID1497
Feature activation-2.28e+00

Pos logit contributions
anish+0.040
 Ow+0.038
ked+0.038
arre+0.035
adoes+0.035
Neg logit contributions
asis-0.043
rig-0.042
place-0.040
row-0.040
eh-0.037
Token,
Token ID11
Feature activation-1.01e+00

Pos logit contributions
ked+0.084
anish+0.080
 Ow+0.078
joy+0.076
 anymore+0.075
Neg logit contributions
asis-0.115
rig-0.111
place-0.108
row-0.099
eh-0.098
Token singing
Token ID13777
Feature activation-1.63e+00

Pos logit contributions
ked+0.045
anish+0.044
 Ow+0.044
 anymore+0.041
joy+0.040
Neg logit contributions
asis-0.043
rig-0.041
place-0.039
eh-0.035
old-0.035
Token a
Token ID257
Feature activation-2.32e+00

Pos logit contributions
 Ow+0.073
ked+0.069
anish+0.067
arre+0.066
 tant+0.065
Neg logit contributions
asis-0.064
rig-0.061
place-0.061
 called-0.058
row-0.058
Token goodbye
Token ID24829
Feature activation-7.09e+00

Pos logit contributions
ked+0.098
anish+0.094
 Ow+0.092
joy+0.090
 anymore+0.089
Neg logit contributions
asis-0.105
rig-0.101
place-0.097
row-0.088
eh-0.087
Token to
Token ID284
Feature activation-1.60e+00

Pos logit contributions
anish+0.254
ked+0.249
 Ow+0.248
joy+0.225
 tant+0.225
Neg logit contributions
asis-0.358
rig-0.343
place-0.332
row-0.313
eh-0.301
Token me
Token ID502
Feature activation+2.29e-01

Pos logit contributions
ked+0.064
anish+0.062
 Ow+0.060
joy+0.059
 anymore+0.058
Neg logit contributions
asis-0.076
rig-0.072
place-0.070
row-0.064
eh-0.063
Token.
Token ID13
Feature activation-6.10e-01

Pos logit contributions
asis+0.011
place+0.010
rig+0.010
eh+0.009
isin+0.009
Neg logit contributions
 anymore-0.009
ked-0.009
joy-0.008
anish-0.008
 Ow-0.008
Token I
Token ID314
Feature activation-9.37e-01

Pos logit contributions
ked+0.019
 Ow+0.019
anish+0.019
joy+0.019
 anymore+0.017
Neg logit contributions
asis-0.034
place-0.032
rig-0.032
row-0.030
eh-0.029
Token waved
Token ID26834
Feature activation-1.78e+00

Pos logit contributions
ked+0.034
anish+0.032
 Ow+0.032
joy+0.031
 anymore+0.031
Neg logit contributions
asis-0.047
rig-0.045
place-0.044
row-0.041
eh-0.040
Token.
Token ID13
Feature activation-8.11e-01

Pos logit contributions
ked+0.102
anish+0.098
 Ow+0.097
joy+0.094
 anymore+0.090
Neg logit contributions
asis-0.113
rig-0.108
place-0.105
row-0.097
eh-0.095
Token Tom
Token ID4186
Feature activation-1.45e+00

Pos logit contributions
ked+0.036
anish+0.034
arre+0.031
adoes+0.030
 prope+0.030
Neg logit contributions
rig-0.034
asis-0.034
place-0.032
old-0.031
aster-0.029
Token and
Token ID290
Feature activation-1.17e+00

Pos logit contributions
ked+0.039
anish+0.036
 Ow+0.036
joy+0.035
 anymore+0.035
Neg logit contributions
asis-0.087
rig-0.084
place-0.083
row-0.077
eh-0.076
Token Anna
Token ID11735
Feature activation-1.40e+00

Pos logit contributions
ked+0.035
anish+0.033
 Ow+0.032
joy+0.032
 anymore+0.031
Neg logit contributions
asis-0.067
rig-0.065
place-0.063
row-0.059
old-0.059
Token wave
Token ID6769
Feature activation-1.54e+00

Pos logit contributions
ked+0.049
anish+0.047
 Ow+0.045
joy+0.045
 anymore+0.044
Neg logit contributions
asis-0.073
rig-0.070
place-0.068
row-0.063
old-0.062
Token goodbye
Token ID24829
Feature activation-6.95e+00

Pos logit contributions
anish+0.064
 Ow+0.062
arre+0.059
adoes+0.057
ifying+0.056
Neg logit contributions
old-0.063
rig-0.061
place-0.061
 called-0.059
asis-0.058
Token.
Token ID13
Feature activation-6.04e-01

Pos logit contributions
anish+0.328
 Ow+0.318
ked+0.312
arre+0.303
joy+0.301
Neg logit contributions
asis-0.267
rig-0.260
place-0.250
row-0.233
old-0.220
Token They
Token ID1119
Feature activation+1.53e-01

Pos logit contributions
anish+0.021
ked+0.021
 tant+0.019
arre+0.018
joy+0.018
Neg logit contributions
rig-0.030
asis-0.030
place-0.028
old-0.027
 called-0.026
Token go
Token ID467
Feature activation+3.92e-01

Pos logit contributions
asis+0.008
rig+0.007
place+0.007
row+0.007
eh+0.007
Neg logit contributions
ked-0.006
 Ow-0.005
 anymore-0.005
anish-0.005
joy-0.005
Token back
Token ID736
Feature activation-1.62e+00

Pos logit contributions
asis+0.022
rig+0.022
place+0.021
eh+0.019
row+0.019
Neg logit contributions
ked-0.012
anish-0.011
 anymore-0.011
joy-0.011
 Ow-0.011
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
ked+0.048
anish+0.045
 Ow+0.043
joy+0.043
 anymore+0.042
Neg logit contributions
asis-0.094
rig-0.091
place-0.089
row-0.082
eh-0.082
Token.
Token ID13
Feature activation-5.80e-01

Pos logit contributions
anish+0.166
 Ow+0.163
ked+0.157
arre+0.157
joy+0.153
Neg logit contributions
asis-0.095
rig-0.090
place-0.085
 called-0.080
fire-0.079
Token Lily
Token ID20037
Feature activation-2.11e-01

Pos logit contributions
ked+0.024
anish+0.023
joy+0.021
adoes+0.021
 tant+0.021
Neg logit contributions
rig-0.025
asis-0.024
place-0.024
old-0.022
 called-0.022
Token and
Token ID290
Feature activation-7.37e-01

Pos logit contributions
ked+0.007
anish+0.007
 Ow+0.007
joy+0.007
 anymore+0.007
Neg logit contributions
asis-0.011
rig-0.011
place-0.010
old-0.009
row-0.009
Token Ben
Token ID3932
Feature activation-1.84e+00

Pos logit contributions
anish+0.025
ked+0.024
 Ow+0.022
joy+0.022
 anymore+0.022
Neg logit contributions
asis-0.038
rig-0.036
place-0.036
aster-0.033
old-0.033
Token wave
Token ID6769
Feature activation-1.41e+00

Pos logit contributions
anish+0.071
joy+0.070
ked+0.070
 Ow+0.068
adoes+0.067
Neg logit contributions
asis-0.086
rig-0.083
place-0.081
old-0.071
row-0.070
Token goodbye
Token ID24829
Feature activation-6.90e+00

Pos logit contributions
anish+0.069
arre+0.064
 Ow+0.062
ifying+0.061
adoes+0.059
Neg logit contributions
old-0.048
 called-0.044
 old-0.043
rig-0.043
aling-0.042
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
anish+0.236
 Ow+0.225
ked+0.225
joy+0.214
 anymore+0.206
Neg logit contributions
asis-0.356
rig-0.348
place-0.335
row-0.319
old-0.307
Token the
Token ID262
Feature activation-3.77e-01

Pos logit contributions
anish+0.072
ked+0.071
arre+0.066
 Ow+0.064
joy+0.064
Neg logit contributions
asis-0.061
place-0.056
rig-0.055
aster-0.053
old-0.051
Token bird
Token ID6512
Feature activation-2.76e+00

Pos logit contributions
ked+0.019
ifying+0.017
anish+0.017
ved+0.017
arre+0.016
Neg logit contributions
asis-0.017
place-0.014
 old-0.013
igator-0.013
 stump-0.013
Token.
Token ID13
Feature activation-7.28e-01

Pos logit contributions
ked+0.083
 anymore+0.076
anish+0.076
 Ow+0.074
joy+0.072
Neg logit contributions
asis-0.158
rig-0.153
place-0.150
row-0.138
eh-0.137
Token They
Token ID1119
Feature activation+1.52e-01

Pos logit contributions
anish+0.023
ked+0.023
 tant+0.021
 anymore+0.021
joy+0.021
Neg logit contributions
rig-0.038
asis-0.037
place-0.036
old-0.034
 called-0.033
Token sm
Token ID895
Feature activation-5.86e-01

Pos logit contributions
asis+0.009
rig+0.009
place+0.009
row+0.008
isin+0.008
Neg logit contributions
ked-0.007
 Ow-0.006
anish-0.006
joy-0.006
 tant-0.006
Tokenelly
Token ID6148
Feature activation+9.70e-01

Pos logit contributions
 anymore+0.019
anish+0.019
joy+0.019
ked+0.018
 Ow+0.018
Neg logit contributions
asis-0.032
rig-0.030
place-0.028
isin-0.027
eh-0.027
Token flower
Token ID15061
Feature activation+3.22e-01

Pos logit contributions
asis+0.045
rig+0.043
place+0.041
row+0.038
old+0.037
Neg logit contributions
ked-0.039
anish-0.038
 Ow-0.037
joy-0.037
 anymore-0.037
Token as
Token ID355
Feature activation+5.91e-01

Pos logit contributions
asis+0.016
rig+0.015
place+0.014
old+0.013
isin+0.013
Neg logit contributions
ked-0.012
anish-0.012
 anymore-0.012
 Ow-0.011
joy-0.011
Token a
Token ID257
Feature activation-1.95e+00

Pos logit contributions
asis+0.031
rig+0.030
place+0.029
eh+0.027
row+0.027
Neg logit contributions
ked-0.020
anish-0.020
 Ow-0.019
joy-0.018
 anymore-0.018
Token goodbye
Token ID24829
Feature activation-6.82e+00

Pos logit contributions
ked+0.079
anish+0.076
joy+0.075
 Ow+0.074
 anymore+0.073
Neg logit contributions
asis-0.091
rig-0.086
place-0.083
row-0.077
eh-0.076
Token gift
Token ID6979
Feature activation-3.48e+00

Pos logit contributions
ked+0.298
anish+0.294
 Ow+0.287
joy+0.278
 anymore+0.273
Neg logit contributions
asis-0.292
rig-0.277
place-0.269
row-0.245
eh-0.239
Token.
Token ID13
Feature activation-5.07e-01

Pos logit contributions
ked+0.145
anish+0.138
 anymore+0.134
 Ow+0.134
joy+0.133
Neg logit contributions
asis-0.160
rig-0.153
place-0.148
eh-0.134
row-0.133
Token Sam
Token ID3409
Feature activation-3.85e-01

Pos logit contributions
ked+0.017
anish+0.016
 Ow+0.016
joy+0.016
 anymore+0.016
Neg logit contributions
asis-0.028
place-0.026
rig-0.026
row-0.024
eh-0.024
Token thanked
Token ID26280
Feature activation-1.31e+00

Pos logit contributions
ked+0.013
anish+0.012
joy+0.012
 Ow+0.012
 anymore+0.012
Neg logit contributions
asis-0.020
rig-0.020
place-0.019
row-0.018
eh-0.017
Token him
Token ID683
Feature activation+3.10e-01

Pos logit contributions
ked+0.051
anish+0.049
 Ow+0.048
joy+0.047
 anymore+0.046
Neg logit contributions
asis-0.063
rig-0.060
place-0.059
row-0.053
old-0.053
Token to
Token ID284
Feature activation-7.62e-01

Pos logit contributions
ked+0.028
anish+0.026
 Ow+0.025
joy+0.025
 anymore+0.025
Neg logit contributions
asis-0.054
rig-0.053
place-0.051
row-0.048
eh-0.047
Token Anna
Token ID11735
Feature activation-6.55e-01

Pos logit contributions
ked+0.029
anish+0.028
joy+0.026
arre+0.026
 Ow+0.025
Neg logit contributions
asis-0.037
rig-0.035
place-0.035
aster-0.033
old-0.032
Token.
Token ID13
Feature activation-4.71e-01

Pos logit contributions
ked+0.017
 anymore+0.015
anish+0.015
joy+0.015
 Ow+0.015
Neg logit contributions
asis-0.040
rig-0.039
place-0.039
eh-0.035
row-0.035
Token He
Token ID679
Feature activation-6.11e-01

Pos logit contributions
ked+0.017
anish+0.016
 Ow+0.015
joy+0.015
 anymore+0.015
Neg logit contributions
asis-0.024
rig-0.024
place-0.023
row-0.021
eh-0.021
Token waves
Token ID9813
Feature activation+5.19e-01

Pos logit contributions
ked+0.026
anish+0.025
 Ow+0.024
joy+0.024
 anymore+0.023
Neg logit contributions
asis-0.028
rig-0.026
place-0.026
row-0.023
eh-0.023
Token goodbye
Token ID24829
Feature activation-6.74e+00

Pos logit contributions
asis+0.020
old+0.020
rig+0.020
place+0.019
row+0.019
Neg logit contributions
anish-0.021
arre-0.021
 Ow-0.021
adoes-0.020
joy-0.019
Token and
Token ID290
Feature activation-4.58e-01

Pos logit contributions
ked+0.216
anish+0.215
 Ow+0.208
joy+0.199
 anymore+0.195
Neg logit contributions
asis-0.364
rig-0.351
place-0.341
row-0.322
eh-0.315
Token walks
Token ID11114
Feature activation-8.56e-01

Pos logit contributions
ked+0.020
anish+0.019
 Ow+0.019
joy+0.019
 anymore+0.019
Neg logit contributions
asis-0.020
rig-0.019
place-0.018
row-0.016
eh-0.016
Token away
Token ID1497
Feature activation-2.78e+00

Pos logit contributions
anish+0.036
 Ow+0.036
arre+0.034
ked+0.034
adoes+0.032
Neg logit contributions
asis-0.037
place-0.035
rig-0.033
old-0.033
row-0.033
Token.
Token ID13
Feature activation-4.07e-01

Pos logit contributions
ked+0.117
anish+0.113
 Ow+0.111
joy+0.109
 anymore+0.107
Neg logit contributions
asis-0.124
rig-0.119
place-0.115
row-0.105
eh-0.103
Token
Token ID198
Feature activation-7.33e-02

Pos logit contributions
ked+0.015
anish+0.014
 Ow+0.013
 anymore+0.013
joy+0.013
Neg logit contributions
asis-0.020
rig-0.020
place-0.019
old-0.018
eh-0.018
Token.
Token ID13
Feature activation-5.17e-01

Pos logit contributions
ked+0.011
anish+0.011
 Ow+0.010
joy+0.010
 anymore+0.010
Neg logit contributions
asis-0.012
rig-0.011
place-0.011
row-0.010
old-0.010
Token Tim
Token ID5045
Feature activation-2.10e-01

Pos logit contributions
ked+0.020
anish+0.020
 Ow+0.019
joy+0.018
 anymore+0.018
Neg logit contributions
asis-0.025
rig-0.024
place-0.023
old-0.021
eh-0.021
Token and
Token ID290
Feature activation-7.50e-01

Pos logit contributions
ked+0.006
anish+0.005
 Ow+0.005
joy+0.005
 anymore+0.005
Neg logit contributions
asis-0.012
rig-0.012
place-0.012
row-0.011
eh-0.011
Token Mia
Token ID32189
Feature activation+1.04e+00

Pos logit contributions
ked+0.034
anish+0.033
 Ow+0.032
joy+0.032
 anymore+0.031
Neg logit contributions
asis-0.032
rig-0.030
place-0.030
row-0.026
eh-0.026
Token wave
Token ID6769
Feature activation-1.33e+00

Pos logit contributions
asis+0.056
rig+0.053
place+0.052
row+0.048
old+0.048
Neg logit contributions
ked-0.034
anish-0.033
 Ow-0.032
joy-0.032
 anymore-0.031
Token goodbye
Token ID24829
Feature activation-6.74e+00

Pos logit contributions
anish+0.062
 Ow+0.059
arre+0.058
ifying+0.055
adoes+0.054
Neg logit contributions
old-0.047
 called-0.045
rig-0.044
place-0.044
asis-0.042
Token.
Token ID13
Feature activation-5.81e-01

Pos logit contributions
anish+0.294
 Ow+0.285
ked+0.285
joy+0.272
arre+0.266
Neg logit contributions
asis-0.286
rig-0.276
place-0.266
row-0.248
old-0.236
Token They
Token ID1119
Feature activation+2.85e-01

Pos logit contributions
ked+0.018
anish+0.018
 anymore+0.016
joy+0.016
 tant+0.016
Neg logit contributions
asis-0.031
rig-0.031
place-0.030
old-0.028
 called-0.027
Token are
Token ID389
Feature activation-1.32e+00

Pos logit contributions
asis+0.015
rig+0.014
place+0.014
row+0.013
eh+0.013
Neg logit contributions
ked-0.010
 Ow-0.009
 anymore-0.009
anish-0.009
joy-0.009
Token happy
Token ID3772
Feature activation-5.13e-01

Pos logit contributions
anish+0.068
ked+0.066
 Ow+0.065
joy+0.062
 tant+0.061
Neg logit contributions
asis-0.048
rig-0.044
place-0.043
eh-0.040
 called-0.039
Token.
Token ID13
Feature activation-2.24e-02

Pos logit contributions
ked+0.025
anish+0.025
 Ow+0.024
 tant+0.024
arre+0.023
Neg logit contributions
asis-0.019
place-0.018
rig-0.017
old-0.016
 called-0.016
Token in
Token ID287
Feature activation-2.41e-02

Pos logit contributions
anish+0.065
ked+0.063
 Ow+0.062
joy+0.059
 anymore+0.057
Neg logit contributions
asis-0.119
rig-0.114
place-0.114
row-0.107
eh-0.105
Token the
Token ID262
Feature activation-4.45e-01

Pos logit contributions
anish+0.001
ked+0.001
arre+0.001
 Ow+0.001
adoes+0.001
Neg logit contributions
asis-0.001
place-0.001
rig-0.001
aster-0.001
 called-0.001
Token car
Token ID1097
Feature activation-1.54e+00

Pos logit contributions
ked+0.017
anish+0.016
 Ow+0.016
joy+0.015
 anymore+0.015
Neg logit contributions
asis-0.022
rig-0.021
place-0.021
row-0.019
eh-0.019
Token and
Token ID290
Feature activation-1.18e+00

Pos logit contributions
ked+0.039
 anymore+0.036
anish+0.035
joy+0.032
 Ow+0.030
Neg logit contributions
asis-0.095
rig-0.092
place-0.089
isin-0.086
rim-0.085
Token waves
Token ID9813
Feature activation+4.58e-01

Pos logit contributions
ked+0.050
anish+0.050
 Ow+0.048
joy+0.047
 anymore+0.047
Neg logit contributions
asis-0.052
rig-0.049
place-0.047
eh-0.043
row-0.043
Token goodbye
Token ID24829
Feature activation-6.69e+00

Pos logit contributions
asis+0.018
rig+0.017
place+0.017
row+0.017
old+0.017
Neg logit contributions
anish-0.020
 Ow-0.019
arre-0.019
adoes-0.018
joy-0.018
Token.
Token ID13
Feature activation-6.04e-01

Pos logit contributions
anish+0.302
ked+0.299
 Ow+0.293
joy+0.283
arre+0.276
Neg logit contributions
asis-0.275
rig-0.261
place-0.253
row-0.233
eh-0.224
Token Tom
Token ID4186
Feature activation-1.25e+00

Pos logit contributions
ked+0.024
anish+0.023
 Ow+0.022
joy+0.022
 anymore+0.022
Neg logit contributions
asis-0.029
rig-0.028
place-0.027
old-0.024
eh-0.024
Token and
Token ID290
Feature activation-8.31e-01

Pos logit contributions
ked+0.039
anish+0.037
 Ow+0.036
joy+0.035
 anymore+0.035
Neg logit contributions
asis-0.070
rig-0.068
place-0.066
row-0.061
old-0.061
Token Mia
Token ID32189
Feature activation+9.03e-01

Pos logit contributions
ked+0.033
anish+0.032
 Ow+0.031
joy+0.031
 anymore+0.030
Neg logit contributions
asis-0.040
rig-0.038
place-0.037
row-0.034
eh-0.033
Token wave
Token ID6769
Feature activation-1.25e+00

Pos logit contributions
asis+0.041
rig+0.038
place+0.037
row+0.034
old+0.034
Neg logit contributions
ked-0.038
anish-0.038
 Ow-0.036
joy-0.036
 anymore-0.035
Token away
Token ID1497
Feature activation-1.88e+00

Pos logit contributions
rig+0.029
asis+0.029
place+0.028
row+0.026
fire+0.026
Neg logit contributions
 Ow-0.029
anish-0.029
ked-0.027
adoes-0.026
 prope-0.026
Token,
Token ID11
Feature activation-9.69e-01

Pos logit contributions
anish+0.081
ked+0.081
 Ow+0.080
joy+0.074
adoes+0.073
Neg logit contributions
asis-0.081
rig-0.078
place-0.075
row-0.068
eh-0.067
Token waving
Token ID25849
Feature activation-1.03e+00

Pos logit contributions
anish+0.046
ked+0.045
 Ow+0.045
adoes+0.040
 tant+0.039
Neg logit contributions
asis-0.038
rig-0.036
 called-0.033
place-0.033
 secure-0.032
Token its
Token ID663
Feature activation-1.32e+00

Pos logit contributions
arre+0.045
anish+0.044
 Ow+0.044
yles+0.038
 fault+0.038
Neg logit contributions
 called-0.037
 old-0.036
asis-0.034
row-0.034
place-0.033
Token tail
Token ID7894
Feature activation-8.95e-01

Pos logit contributions
ked+0.059
anish+0.058
joy+0.056
 Ow+0.056
 anymore+0.056
Neg logit contributions
asis-0.055
place-0.052
rig-0.052
row-0.048
b-0.045
Token goodbye
Token ID24829
Feature activation-6.67e+00

Pos logit contributions
 Ow+0.035
anish+0.035
ked+0.032
joy+0.031
 tant+0.030
Neg logit contributions
asis-0.041
rig-0.039
place-0.038
row-0.037
eh-0.036
Token.
Token ID13
Feature activation-5.67e-01

Pos logit contributions
anish+0.293
 Ow+0.285
ked+0.273
arre+0.264
Mine+0.261
Neg logit contributions
asis-0.279
rig-0.269
place-0.257
row-0.250
fire-0.236
Token
Token ID220
Feature activation-2.01e+00

Pos logit contributions
ked+0.022
anish+0.021
 Ow+0.020
joy+0.020
 anymore+0.020
Neg logit contributions
asis-0.028
rig-0.027
place-0.026
row-0.024
old-0.024
Token
Token ID198
Feature activation-2.32e-01

Pos logit contributions
ked+0.069
anish+0.066
 Ow+0.066
joy+0.063
 anymore+0.063
Neg logit contributions
asis-0.106
rig-0.100
place-0.100
row-0.091
eh-0.090
Token
Token ID198
Feature activation+6.20e-02

Pos logit contributions
ked+0.007
 Ow+0.007
anish+0.007
joy+0.007
 anymore+0.006
Neg logit contributions
asis-0.013
place-0.012
rig-0.012
row-0.011
eh-0.011
TokenL
Token ID43
Feature activation-2.69e-01

Pos logit contributions
asis+0.003
rig+0.003
place+0.003
row+0.003
eh+0.002
Neg logit contributions
ked-0.002
anish-0.002
 Ow-0.002
joy-0.002
 anymore-0.002
TokenL
Token ID43
Feature activation-3.47e-01

Pos logit contributions
asis+0.010
rig+0.010
place+0.009
row+0.009
at+0.009
Neg logit contributions
anish-0.006
ked-0.005
joy-0.005
 Ow-0.005
Wow-0.005
Tokenily
Token ID813
Feature activation+1.39e+00

Pos logit contributions
ked+0.018
anish+0.017
 Ow+0.017
joy+0.017
 anymore+0.017
Neg logit contributions
asis-0.013
rig-0.012
place-0.012
row-0.010
eh-0.010
Token and
Token ID290
Feature activation-6.59e-01

Pos logit contributions
asis+0.076
rig+0.074
place+0.071
old+0.067
row+0.066
Neg logit contributions
ked-0.045
anish-0.043
 Ow-0.042
 anymore-0.041
joy-0.040
Token Ben
Token ID3932
Feature activation-1.35e+00

Pos logit contributions
ked+0.021
anish+0.021
 Ow+0.019
joy+0.019
 anymore+0.019
Neg logit contributions
asis-0.036
rig-0.034
place-0.034
old-0.031
eh-0.031
Token wave
Token ID6769
Feature activation-1.07e+00

Pos logit contributions
ked+0.055
anish+0.054
 Ow+0.053
joy+0.052
 anymore+0.051
Neg logit contributions
asis-0.061
rig-0.059
place-0.058
old-0.052
row-0.051
Token goodbye
Token ID24829
Feature activation-6.67e+00

Pos logit contributions
 Ow+0.044
anish+0.044
ifying+0.039
arre+0.039
adoes+0.039
Neg logit contributions
old-0.045
rig-0.043
 called-0.041
place-0.041
row-0.038
Token.
Token ID13
Feature activation-6.25e-01

Pos logit contributions
anish+0.267
 Ow+0.260
ked+0.248
joy+0.239
 superstar+0.236
Neg logit contributions
asis-0.303
rig-0.301
place-0.289
row-0.274
fire-0.261
Token They
Token ID1119
Feature activation+1.69e-01

Pos logit contributions
anish+0.020
ked+0.020
 tant+0.018
 Ow+0.018
 anymore+0.018
Neg logit contributions
rig-0.033
asis-0.031
place-0.030
old-0.029
 called-0.029
Token learn
Token ID2193
Feature activation+1.99e-01

Pos logit contributions
asis+0.008
rig+0.007
place+0.007
row+0.007
eh+0.007
Neg logit contributions
ked-0.007
anish-0.006
 Ow-0.006
 anymore-0.006
joy-0.006
Token a
Token ID257
Feature activation-7.45e-01

Pos logit contributions
rig+0.010
asis+0.010
place+0.010
old+0.010
row+0.009
Neg logit contributions
ked-0.007
anish-0.006
 Ow-0.006
joy-0.006
 anymore-0.006
Token lesson
Token ID11483
Feature activation-3.21e+00

Pos logit contributions
ked+0.031
anish+0.030
 Ow+0.029
joy+0.029
 anymore+0.028
Neg logit contributions
asis-0.034
rig-0.033
place-0.032
row-0.029
old-0.028
Token.
Token ID13
Feature activation-4.03e-01

Pos logit contributions
anish+0.161
 Ow+0.161
ked+0.158
arre+0.156
Mine+0.150
Neg logit contributions
asis-0.077
rig-0.075
place-0.070
fire-0.066
 called-0.064
Token Sara
Token ID24799
Feature activation+1.20e+00

Pos logit contributions
ked+0.017
anish+0.016
 anymore+0.015
joy+0.015
adoes+0.015
Neg logit contributions
asis-0.018
rig-0.017
place-0.016
old-0.015
isin-0.015
Token and
Token ID290
Feature activation-5.51e-01

Pos logit contributions
asis+0.062
rig+0.061
place+0.057
old+0.054
row+0.052
Neg logit contributions
ked-0.041
anish-0.040
 Ow-0.039
joy-0.038
 anymore-0.037
Token Tom
Token ID4186
Feature activation-1.79e+00

Pos logit contributions
ked+0.014
anish+0.014
 Ow+0.013
joy+0.013
 anymore+0.012
Neg logit contributions
asis-0.033
rig-0.032
place-0.031
old-0.029
eh-0.029
Token wave
Token ID6769
Feature activation-1.21e+00

Pos logit contributions
anish+0.077
joy+0.075
ked+0.074
 Ow+0.073
adoes+0.072
Neg logit contributions
asis-0.078
rig-0.074
place-0.071
old-0.064
 called-0.063
Token goodbye
Token ID24829
Feature activation-6.65e+00

Pos logit contributions
anish+0.057
 Ow+0.054
arre+0.052
joy+0.050
ifying+0.049
Neg logit contributions
old-0.042
rig-0.040
 called-0.040
 offer-0.037
place-0.037
Token.
Token ID13
Feature activation-5.77e-01

Pos logit contributions
anish+0.267
 Ow+0.256
ked+0.247
joy+0.242
arre+0.239
Neg logit contributions
asis-0.303
rig-0.300
place-0.283
row-0.271
fire-0.257
Token They
Token ID1119
Feature activation+3.12e-01

Pos logit contributions
anish+0.020
ked+0.020
 tant+0.018
arre+0.018
 anymore+0.018
Neg logit contributions
asis-0.029
rig-0.029
place-0.027
 called-0.025
old-0.025
Token have
Token ID423
Feature activation-6.01e-01

Pos logit contributions
asis+0.014
rig+0.013
place+0.013
row+0.011
eh+0.011
Neg logit contributions
ked-0.013
anish-0.013
 Ow-0.013
joy-0.013
 anymore-0.012
Token a
Token ID257
Feature activation-1.19e+00

Pos logit contributions
anish+0.027
ked+0.026
 Ow+0.025
 tant+0.025
adoes+0.024
Neg logit contributions
asis-0.025
place-0.024
rig-0.023
eh-0.022
old-0.021
Token new
Token ID649
Feature activation-1.64e+00

Pos logit contributions
ked+0.062
anish+0.058
adoes+0.057
 Ow+0.056
 anymore+0.053
Neg logit contributions
asis-0.046
rig-0.044
place-0.044
 called-0.036
eh-0.036
Token They
Token ID1119
Feature activation+2.95e-02

Pos logit contributions
ked+0.029
anish+0.028
 tant+0.027
ved+0.026
 prope+0.026
Neg logit contributions
rig-0.035
 called-0.030
place-0.029
asis-0.029
old-0.029
Token kissed
Token ID27946
Feature activation-3.17e+00

Pos logit contributions
 called+0.001
place+0.001
asis+0.001
rig+0.001
old+0.001
Neg logit contributions
anish-0.001
joy-0.001
 Ow-0.001
adoes-0.001
 anymore-0.001
Token the
Token ID262
Feature activation+1.08e+00

Pos logit contributions
joy+0.148
arre+0.145
 superstar+0.144
anish+0.143
yles+0.133
Neg logit contributions
 called-0.118
ion-0.101
aster-0.097
row-0.088
place-0.088
Token snow
Token ID6729
Feature activation+1.39e+00

Pos logit contributions
asis+0.049
place+0.046
rig+0.044
eh+0.041
 stump+0.040
Neg logit contributions
ked-0.045
anish-0.042
 Ow-0.042
 anymore-0.041
joy-0.040
Tokenman
Token ID805
Feature activation-2.61e+00

Pos logit contributions
asis+0.056
row+0.047
rig+0.046
fire+0.046
place+0.044
Neg logit contributions
joy-0.069
 Ow-0.067
anish-0.064
arre-0.063
ked-0.062
Token goodbye
Token ID24829
Feature activation-6.64e+00

Pos logit contributions
 Ow+0.099
anish+0.098
ked+0.091
joy+0.091
adoes+0.087
Neg logit contributions
asis-0.123
rig-0.121
place-0.117
row-0.112
old-0.110
Token.
Token ID13
Feature activation-6.16e-01

Pos logit contributions
anish+0.265
 Ow+0.261
ked+0.243
Mine+0.238
joy+0.238
Neg logit contributions
asis-0.299
rig-0.296
row-0.279
place-0.278
 called-0.263
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
ked+0.020
anish+0.020
 anymore+0.019
 tant+0.018
 Ow+0.018
Neg logit contributions
rig-0.032
asis-0.031
place-0.029
 called-0.028
old-0.028
Token
Token ID198
Feature activation-2.29e-02

Pos logit contributions
 Ow+0.007
Look+0.005
ked+0.005
anish+0.005
joy+0.005
Neg logit contributions
asis-0.022
place-0.021
rig-0.020
row-0.019
at-0.019
TokenThey
Token ID2990
Feature activation+2.05e-01

Pos logit contributions
Look+0.001
anish+0.001
ked+0.001
Wow+0.001
 Ow+0.000
Neg logit contributions
asis-0.001
place-0.001
rig-0.001
at-0.001
atmeal-0.001
Token took
Token ID1718
Feature activation-9.99e-01

Pos logit contributions
asis+0.009
rig+0.009
place+0.009
row+0.008
old+0.008
Neg logit contributions
anish-0.008
ked-0.008
 Ow-0.008
joy-0.008
 anymore-0.008
TokenL
Token ID43
Feature activation-2.15e-01

Pos logit contributions
asis+0.020
rig+0.019
place+0.018
at+0.017
eh+0.016
Neg logit contributions
ked-0.013
anish-0.013
joy-0.013
 Ow-0.012
 anymore-0.012
Tokenily
Token ID813
Feature activation+1.57e+00

Pos logit contributions
ked+0.010
anish+0.009
 Ow+0.009
 anymore+0.009
joy+0.009
Neg logit contributions
asis-0.009
rig-0.009
place-0.008
row-0.007
eh-0.007
Token and
Token ID290
Feature activation-4.25e-01

Pos logit contributions
rig+0.079
asis+0.078
place+0.073
old+0.070
eh+0.067
Neg logit contributions
ked-0.056
anish-0.054
 Ow-0.052
 anymore-0.051
joy-0.049
Token Ben
Token ID3932
Feature activation-1.13e+00

Pos logit contributions
anish+0.014
ked+0.014
 Ow+0.013
 anymore+0.013
joy+0.013
Neg logit contributions
asis-0.022
rig-0.021
place-0.021
old-0.020
eh-0.019
Token wave
Token ID6769
Feature activation-9.47e-01

Pos logit contributions
ked+0.046
anish+0.046
 Ow+0.044
joy+0.044
 anymore+0.043
Neg logit contributions
asis-0.051
rig-0.049
place-0.048
old-0.043
row-0.042
Token goodbye
Token ID24829
Feature activation-6.63e+00

Pos logit contributions
anish+0.045
 Ow+0.042
arre+0.039
ifying+0.039
adoes+0.037
Neg logit contributions
old-0.036
rig-0.034
 called-0.033
place-0.032
 old-0.032
Token to
Token ID284
Feature activation-1.36e+00

Pos logit contributions
anish+0.223
ked+0.223
 Ow+0.215
joy+0.208
 anymore+0.201
Neg logit contributions
asis-0.345
rig-0.336
place-0.325
row-0.305
old-0.297
Token the
Token ID262
Feature activation-2.21e-01

Pos logit contributions
ked+0.050
anish+0.048
 Ow+0.046
joy+0.045
 anymore+0.044
Neg logit contributions
asis-0.069
rig-0.066
place-0.065
old-0.059
row-0.059
Token z
Token ID1976
Feature activation-1.62e+00

Pos logit contributions
ked+0.008
joy+0.007
 Ow+0.007
anish+0.007
 anymore+0.007
Neg logit contributions
asis-0.011
rig-0.011
place-0.011
row-0.010
old-0.010
Tokenebra
Token ID37052
Feature activation-6.51e-01

Pos logit contributions
ked+0.068
anish+0.065
joy+0.062
 Ow+0.062
 anymore+0.061
Neg logit contributions
asis-0.073
rig-0.073
place-0.069
old-0.062
row-0.062
Token.
Token ID13
Feature activation-6.68e-01

Pos logit contributions
ked+0.024
anish+0.023
 anymore+0.022
 Ow+0.022
joy+0.022
Neg logit contributions
asis-0.033
rig-0.031
place-0.031
row-0.028
eh-0.028
Token.
Token ID13
Feature activation-5.29e-01

Pos logit contributions
ked+0.130
anish+0.125
 Ow+0.124
joy+0.121
 anymore+0.117
Neg logit contributions
asis-0.139
rig-0.133
place-0.129
row-0.118
old-0.116
Token Tom
Token ID4186
Feature activation-1.16e+00

Pos logit contributions
ked+0.021
anish+0.020
 tant+0.019
 anymore+0.018
joy+0.018
Neg logit contributions
rig-0.025
asis-0.024
place-0.022
old-0.022
aster-0.021
Token and
Token ID290
Feature activation-8.92e-01

Pos logit contributions
ked+0.034
anish+0.033
 Ow+0.032
joy+0.031
 anymore+0.030
Neg logit contributions
asis-0.067
rig-0.064
place-0.063
row-0.058
eh-0.058
Token Mom
Token ID11254
Feature activation-4.53e-01

Pos logit contributions
ked+0.034
anish+0.033
 Ow+0.031
joy+0.031
 anymore+0.031
Neg logit contributions
asis-0.043
rig-0.042
place-0.040
old-0.038
eh-0.038
Token wave
Token ID6769
Feature activation-1.06e+00

Pos logit contributions
ked+0.017
anish+0.016
 Ow+0.016
 anymore+0.016
joy+0.015
Neg logit contributions
asis-0.022
rig-0.021
place-0.021
row-0.019
eh-0.019
Token goodbye
Token ID24829
Feature activation-6.63e+00

Pos logit contributions
anish+0.047
 Ow+0.045
arre+0.043
adoes+0.041
ifying+0.040
Neg logit contributions
old-0.041
rig-0.039
 called-0.038
place-0.037
 old-0.035
Token.
Token ID13
Feature activation-5.60e-01

Pos logit contributions
anish+0.231
ked+0.226
 Ow+0.222
joy+0.212
 anymore+0.204
Neg logit contributions
asis-0.340
rig-0.331
place-0.319
row-0.300
eh-0.291
Token They
Token ID1119
Feature activation+2.54e-01

Pos logit contributions
ked+0.020
anish+0.019
 tant+0.018
 anymore+0.017
joy+0.017
Neg logit contributions
asis-0.029
rig-0.028
place-0.026
old-0.025
 called-0.024
Token are
Token ID389
Feature activation-1.30e+00

Pos logit contributions
asis+0.012
rig+0.012
place+0.012
row+0.011
eh+0.011
Neg logit contributions
ked-0.010
anish-0.009
 Ow-0.009
 anymore-0.009
joy-0.009
Token happy
Token ID3772
Feature activation-5.49e-01

Pos logit contributions
anish+0.067
ked+0.066
 Ow+0.064
 tant+0.061
joy+0.061
Neg logit contributions
asis-0.048
rig-0.043
place-0.042
eh-0.039
old-0.038
Token too
Token ID1165
Feature activation+1.62e+00

Pos logit contributions
ked+0.024
anish+0.024
 Ow+0.024
 tant+0.023
ifying+0.022
Neg logit contributions
asis-0.023
place-0.022
rig-0.021
 called-0.020
old-0.020
TokenL
Token ID43
Feature activation-2.14e-01

Pos logit contributions
asis+0.014
rig+0.013
place+0.013
adow+0.012
igator+0.012
Neg logit contributions
anish-0.005
ked-0.005
Look-0.005
 Ow-0.005
Wow-0.005
Tokenila
Token ID10102
Feature activation+3.12e+00

Pos logit contributions
ked+0.009
anish+0.009
 Ow+0.009
 anymore+0.009
joy+0.009
Neg logit contributions
asis-0.009
rig-0.009
place-0.008
fire-0.008
 stump-0.008
Token and
Token ID290
Feature activation-4.05e-01

Pos logit contributions
asis+0.180
rig+0.174
place+0.170
row+0.158
eh+0.157
Neg logit contributions
ked-0.091
anish-0.086
 Ow-0.084
joy-0.082
 anymore-0.081
Token Ben
Token ID3932
Feature activation-1.22e+00

Pos logit contributions
ked+0.012
anish+0.012
 Ow+0.011
joy+0.011
 anymore+0.011
Neg logit contributions
asis-0.023
rig-0.022
place-0.021
old-0.020
row-0.020
Token wave
Token ID6769
Feature activation-9.92e-01

Pos logit contributions
ked+0.042
anish+0.040
 Ow+0.039
joy+0.038
 anymore+0.038
Neg logit contributions
asis-0.064
rig-0.062
place-0.060
row-0.056
eh-0.055
Token goodbye
Token ID24829
Feature activation-6.60e+00

Pos logit contributions
anish+0.044
 Ow+0.042
arre+0.039
ifying+0.038
adoes+0.037
Neg logit contributions
old-0.039
rig-0.036
 called-0.035
place-0.034
 old-0.033
Token to
Token ID284
Feature activation-1.33e+00

Pos logit contributions
anish+0.251
 Ow+0.242
ked+0.242
joy+0.230
arre+0.221
Neg logit contributions
asis-0.316
rig-0.308
place-0.296
row-0.280
old-0.269
Token the
Token ID262
Feature activation-2.03e-01

Pos logit contributions
ked+0.046
anish+0.043
 Ow+0.043
joy+0.042
 anymore+0.042
Neg logit contributions
asis-0.070
rig-0.068
place-0.066
row-0.061
eh-0.061
Token lion
Token ID18744
Feature activation-2.73e+00

Pos logit contributions
ked+0.008
anish+0.008
 Ow+0.008
 anymore+0.007
joy+0.007
Neg logit contributions
asis-0.010
place-0.009
rig-0.009
eh-0.008
row-0.008
Token.
Token ID13
Feature activation-6.03e-01

Pos logit contributions
ked+0.105
anish+0.102
 Ow+0.100
joy+0.097
 anymore+0.095
Neg logit contributions
asis-0.132
rig-0.126
place-0.122
row-0.112
eh-0.111
Token They
Token ID1119
Feature activation+2.48e-01

Pos logit contributions
ked+0.014
anish+0.013
 Ow+0.012
joy+0.012
 anymore+0.012
Neg logit contributions
asis-0.039
rig-0.038
place-0.037
row-0.034
old-0.034
Token the
Token ID262
Feature activation+6.08e-01

Pos logit contributions
ked+0.010
anish+0.009
 Ow+0.009
joy+0.009
 anymore+0.009
Neg logit contributions
asis-0.012
rig-0.012
place-0.011
old-0.010
row-0.010
Token car
Token ID1097
Feature activation-9.49e-01

Pos logit contributions
asis+0.024
rig+0.023
place+0.023
eh+0.020
row+0.020
Neg logit contributions
ked-0.029
anish-0.028
 Ow-0.027
joy-0.027
 anymore-0.026
Token.
Token ID13
Feature activation-6.11e-01

Pos logit contributions
ked+0.034
 anymore+0.034
anish+0.032
joy+0.030
 Ow+0.029
Neg logit contributions
asis-0.048
rig-0.047
place-0.044
isin-0.042
eh-0.042
Token They
Token ID1119
Feature activation+1.87e-01

Pos logit contributions
ked+0.021
anish+0.019
joy+0.018
 anymore+0.018
 Ow+0.017
Neg logit contributions
rig-0.032
asis-0.032
place-0.030
old-0.029
eh-0.027
Token wave
Token ID6769
Feature activation-8.00e-01

Pos logit contributions
asis+0.010
rig+0.009
place+0.009
row+0.008
eh+0.008
Neg logit contributions
ked-0.007
anish-0.006
 Ow-0.006
 anymore-0.006
joy-0.006
Token goodbye
Token ID24829
Feature activation-6.59e+00

Pos logit contributions
anish+0.034
 Ow+0.031
arre+0.030
ked+0.029
joy+0.028
Neg logit contributions
old-0.033
rig-0.032
place-0.031
 called-0.030
asis-0.029
Token and
Token ID290
Feature activation-5.05e-01

Pos logit contributions
anish+0.214
ked+0.211
 Ow+0.206
joy+0.196
 anymore+0.191
Neg logit contributions
asis-0.352
rig-0.343
place-0.332
row-0.312
eh-0.305
Token drive
Token ID3708
Feature activation-1.67e+00

Pos logit contributions
ked+0.024
anish+0.023
 Ow+0.023
joy+0.022
 anymore+0.022
Neg logit contributions
asis-0.020
rig-0.019
place-0.019
row-0.017
eh-0.016
Token away
Token ID1497
Feature activation-2.56e+00

Pos logit contributions
anish+0.073
ked+0.072
 Ow+0.071
arre+0.071
 superstar+0.069
Neg logit contributions
place-0.069
old-0.066
asis-0.063
ion-0.061
rig-0.061
Token.
Token ID13
Feature activation-5.45e-01

Pos logit contributions
ked+0.126
 Ow+0.123
anish+0.123
joy+0.116
arre+0.114
Neg logit contributions
asis-0.094
rig-0.091
place-0.090
row-0.077
fire-0.077
Token They
Token ID1119
Feature activation+1.67e-01

Pos logit contributions
ked+0.022
anish+0.021
 anymore+0.019
 tant+0.019
joy+0.019
Neg logit contributions
rig-0.025
asis-0.025
place-0.024
old-0.022
 called-0.021
Token the
Token ID262
Feature activation+7.31e-01

Pos logit contributions
ked+0.005
anish+0.005
 Ow+0.004
joy+0.004
 anymore+0.004
Neg logit contributions
asis-0.007
rig-0.006
place-0.006
row-0.006
eh-0.006
Token car
Token ID1097
Feature activation-8.05e-01

Pos logit contributions
asis+0.029
rig+0.028
place+0.026
row+0.024
eh+0.023
Neg logit contributions
ked-0.035
anish-0.034
 Ow-0.033
joy-0.033
 anymore-0.033
Token.
Token ID13
Feature activation-5.49e-01

Pos logit contributions
 anymore+0.026
ked+0.025
 again+0.023
anish+0.022
joy+0.022
Neg logit contributions
asis-0.044
rig-0.044
isin-0.041
place-0.041
rim-0.041
Token They
Token ID1119
Feature activation+2.56e-01

Pos logit contributions
ked+0.018
anish+0.018
 Ow+0.017
joy+0.016
 anymore+0.016
Neg logit contributions
asis-0.029
rig-0.029
place-0.028
old-0.025
eh-0.025
Token wave
Token ID6769
Feature activation-7.48e-01

Pos logit contributions
asis+0.011
rig+0.011
place+0.010
row+0.010
eh+0.010
Neg logit contributions
ked-0.011
anish-0.010
 Ow-0.010
 anymore-0.010
joy-0.010
Token goodbye
Token ID24829
Feature activation-6.57e+00

Pos logit contributions
anish+0.033
arre+0.030
 Ow+0.030
 superstar+0.027
 anymore+0.027
Neg logit contributions
old-0.030
rig-0.029
place-0.028
 called-0.028
ion-0.027
Token to
Token ID284
Feature activation-1.32e+00

Pos logit contributions
anish+0.226
 Ow+0.216
ked+0.215
joy+0.202
arre+0.197
Neg logit contributions
asis-0.340
rig-0.329
place-0.322
row-0.304
old-0.294
Token their
Token ID511
Feature activation-2.31e+00

Pos logit contributions
ked+0.048
anish+0.046
 Ow+0.044
joy+0.043
 anymore+0.042
Neg logit contributions
asis-0.068
rig-0.065
place-0.064
row-0.058
eh-0.058
Token old
Token ID1468
Feature activation+5.40e-01

Pos logit contributions
ked+0.094
anish+0.092
 Ow+0.087
joy+0.082
 anymore+0.081
Neg logit contributions
asis-0.110
rig-0.104
place-0.104
old-0.090
row-0.090
Token house
Token ID2156
Feature activation+1.11e+00

Pos logit contributions
asis+0.024
place+0.022
rig+0.022
eh+0.020
row+0.020
Neg logit contributions
ked-0.023
anish-0.022
 Ow-0.022
ifying-0.021
 anymore-0.020
Token and
Token ID290
Feature activation-8.74e-01

Pos logit contributions
asis+0.050
rig+0.049
place+0.047
row+0.043
old+0.043
Neg logit contributions
ked-0.045
anish-0.044
 Ow-0.044
joy-0.042
 anymore-0.040
Tokenden
Token ID6559
Feature activation-5.59e-01

Pos logit contributions
ked+0.004
 Ow+0.004
anish+0.004
 anymore+0.003
joy+0.003
Neg logit contributions
asis-0.004
rig-0.004
place-0.003
row-0.003
old-0.003
Token hugged
Token ID41130
Feature activation-1.70e+00

Pos logit contributions
ked+0.020
anish+0.019
 Ow+0.018
joy+0.018
 anymore+0.018
Neg logit contributions
asis-0.029
rig-0.028
place-0.027
row-0.025
eh-0.025
Token Mrs
Token ID9074
Feature activation-1.26e+00

Pos logit contributions
anish+0.078
ked+0.078
arre+0.075
 Ow+0.072
ifying+0.070
Neg logit contributions
asis-0.063
rig-0.062
place-0.061
old-0.058
 called-0.057
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
ked+0.059
anish+0.059
 Ow+0.057
arre+0.056
 tant+0.056
Neg logit contributions
asis-0.048
rig-0.047
place-0.045
row-0.041
old-0.041
Token Bell
Token ID7459
Feature activation-1.31e+00

Pos logit contributions
ked+0.005
anish+0.005
 Ow+0.005
 anymore+0.005
 tant+0.005
Neg logit contributions
asis-0.007
rig-0.006
place-0.006
row-0.006
 stump-0.006
Token goodbye
Token ID24829
Feature activation-6.56e+00

Pos logit contributions
anish+0.049
 Ow+0.049
ked+0.048
joy+0.045
adoes+0.045
Neg logit contributions
asis-0.063
rig-0.061
place-0.059
row-0.055
old-0.055
Token.
Token ID13
Feature activation-6.03e-01

Pos logit contributions
anish+0.236
ked+0.233
 Ow+0.232
joy+0.213
 anymore+0.211
Neg logit contributions
asis-0.327
rig-0.316
place-0.305
row-0.286
old-0.279
Token Jay
Token ID9180
Feature activation-6.76e-01

Pos logit contributions
ked+0.021
anish+0.020
 Ow+0.020
joy+0.020
 anymore+0.019
Neg logit contributions
asis-0.031
rig-0.030
place-0.030
row-0.027
eh-0.027
Tokenden
Token ID6559
Feature activation-9.89e-01

Pos logit contributions
 Ow+0.027
ked+0.026
anish+0.026
 anymore+0.025
joy+0.025
Neg logit contributions
asis-0.032
rig-0.031
place-0.029
row-0.028
old-0.028
Token was
Token ID373
Feature activation-5.76e-01

Pos logit contributions
ked+0.034
anish+0.032
 Ow+0.031
joy+0.031
 anymore+0.031
Neg logit contributions
asis-0.052
rig-0.050
place-0.048
row-0.045
eh-0.044
Token proud
Token ID6613
Feature activation+3.27e-01

Pos logit contributions
ked+0.024
anish+0.023
joy+0.023
 Ow+0.023
 anymore+0.022
Neg logit contributions
asis-0.026
rig-0.025
place-0.024
row-0.022
eh-0.022
Token dog
Token ID3290
Feature activation-2.12e+00

Pos logit contributions
asis+0.025
rig+0.025
place+0.023
old+0.022
eh+0.021
Neg logit contributions
ked-0.016
joy-0.016
anish-0.015
 anymore-0.015
 Ow-0.015
Token and
Token ID290
Feature activation-7.88e-01

Pos logit contributions
ked+0.069
 anymore+0.064
anish+0.062
 Ow+0.060
joy+0.060
Neg logit contributions
asis-0.117
rig-0.113
place-0.110
isin-0.101
eh-0.101
Token gave
Token ID2921
Feature activation-5.74e-01

Pos logit contributions
anish+0.034
ked+0.033
 Ow+0.033
 anymore+0.032
joy+0.032
Neg logit contributions
asis-0.034
rig-0.033
place-0.032
eh-0.029
row-0.029
Token it
Token ID340
Feature activation+1.35e+00

Pos logit contributions
anish+0.020
ked+0.019
arre+0.018
joy+0.018
 Ow+0.018
Neg logit contributions
asis-0.028
place-0.028
rig-0.027
old-0.027
row-0.025
Token a
Token ID257
Feature activation-3.09e-01

Pos logit contributions
asis+0.085
rig+0.082
place+0.078
isin+0.075
rim+0.073
Neg logit contributions
ked-0.035
 Ow-0.031
joy-0.030
 anymore-0.030
anish-0.030
Token goodbye
Token ID24829
Feature activation-6.54e+00

Pos logit contributions
ked+0.012
anish+0.011
 Ow+0.011
joy+0.011
 anymore+0.011
Neg logit contributions
asis-0.015
rig-0.014
place-0.014
row-0.013
old-0.012
Token hug
Token ID16225
Feature activation-2.39e+00

Pos logit contributions
ked+0.285
anish+0.280
 Ow+0.274
joy+0.264
 anymore+0.259
Neg logit contributions
asis-0.283
rig-0.268
place-0.260
row-0.238
eh-0.231
Token.
Token ID13
Feature activation-3.88e-01

Pos logit contributions
ked+0.116
 Ow+0.115
anish+0.114
joy+0.110
arre+0.106
Neg logit contributions
asis-0.088
rig-0.081
place-0.081
row-0.076
old-0.071
Token
Token ID198
Feature activation-1.30e-01

Pos logit contributions
ked+0.012
 Ow+0.012
joy+0.012
anish+0.012
 anymore+0.011
Neg logit contributions
asis-0.022
place-0.021
rig-0.021
row-0.019
eh-0.019
Token
Token ID198
Feature activation+1.10e-01

Pos logit contributions
 Ow+0.004
ked+0.003
anish+0.003
joy+0.003
Look+0.003
Neg logit contributions
asis-0.008
place-0.008
rig-0.007
row-0.007
 stump-0.007
TokenThe
Token ID464
Feature activation+6.18e-01

Pos logit contributions
asis+0.005
rig+0.005
place+0.005
row+0.005
old+0.004
Neg logit contributions
ked-0.004
anish-0.004
 Ow-0.004
joy-0.004
 anymore-0.004
TokenL
Token ID43
Feature activation-2.37e-01

Pos logit contributions
asis+0.015
rig+0.014
place+0.014
row+0.013
eh+0.013
Neg logit contributions
ked-0.009
anish-0.008
 Ow-0.008
joy-0.008
 anymore-0.008
Tokenily
Token ID813
Feature activation+1.43e+00

Pos logit contributions
ked+0.011
anish+0.011
 Ow+0.011
joy+0.011
 anymore+0.011
Neg logit contributions
asis-0.009
rig-0.009
place-0.009
row-0.008
eh-0.008
Token and
Token ID290
Feature activation-5.02e-01

Pos logit contributions
asis+0.082
rig+0.079
place+0.077
row+0.072
eh+0.071
Neg logit contributions
ked-0.043
anish-0.040
 Ow-0.039
joy-0.038
 anymore-0.038
Token Tom
Token ID4186
Feature activation-1.21e+00

Pos logit contributions
anish+0.016
ked+0.015
joy+0.015
 Ow+0.014
 superstar+0.014
Neg logit contributions
asis-0.026
rig-0.025
place-0.025
old-0.024
aster-0.024
Token wave
Token ID6769
Feature activation-8.52e-01

Pos logit contributions
ked+0.056
anish+0.053
 Ow+0.052
joy+0.052
 anymore+0.051
Neg logit contributions
asis-0.050
rig-0.048
place-0.046
row-0.041
eh-0.041
Token goodbye
Token ID24829
Feature activation-6.53e+00

Pos logit contributions
anish+0.038
 Ow+0.037
ifying+0.035
arre+0.034
 prope+0.033
Neg logit contributions
old-0.033
rig-0.031
place-0.031
 called-0.030
 old-0.028
Token.
Token ID13
Feature activation-4.53e-01

Pos logit contributions
anish+0.274
ked+0.269
 Ow+0.266
joy+0.256
 superstar+0.247
Neg logit contributions
asis-0.284
rig-0.277
place-0.267
row-0.249
old-0.238
Token They
Token ID1119
Feature activation+2.97e-01

Pos logit contributions
anish+0.015
ked+0.014
 Ow+0.013
 tant+0.013
joy+0.013
Neg logit contributions
rig-0.024
asis-0.023
place-0.022
 called-0.021
old-0.021
Token put
Token ID1234
Feature activation+7.94e-01

Pos logit contributions
asis+0.014
rig+0.013
place+0.013
row+0.012
eh+0.012
Neg logit contributions
ked-0.012
 Ow-0.011
 anymore-0.011
anish-0.011
joy-0.011
Token on
Token ID319
Feature activation-1.19e+00

Pos logit contributions
asis+0.036
place+0.035
rig+0.034
ion+0.032
row+0.032
Neg logit contributions
anish-0.031
ked-0.029
 Ow-0.029
arre-0.028
joy-0.028
Token their
Token ID511
Feature activation-1.64e+00

Pos logit contributions
anish+0.043
ked+0.040
 superstar+0.037
joy+0.036
arre+0.036
Neg logit contributions
place-0.059
asis-0.058
rig-0.058
old-0.054
aster-0.053
Token ground
Token ID2323
Feature activation+2.64e+00

Pos logit contributions
ked+0.024
 Ow+0.024
anish+0.024
 anymore+0.024
joy+0.023
Neg logit contributions
rig-0.019
asis-0.019
place-0.017
old-0.016
row-0.016
Token and
Token ID290
Feature activation-1.11e+00

Pos logit contributions
asis+0.140
rig+0.135
place+0.132
row+0.122
eh+0.121
Neg logit contributions
ked-0.089
anish-0.085
 Ow-0.083
joy-0.081
 anymore-0.079
Token said
Token ID531
Feature activation+1.27e+00

Pos logit contributions
 Ow+0.044
anish+0.043
ked+0.043
joy+0.043
 anymore+0.039
Neg logit contributions
asis-0.049
place-0.046
rig-0.046
 called-0.046
fire-0.043
Token a
Token ID257
Feature activation-1.93e-01

Pos logit contributions
old+0.040
asis+0.039
place+0.038
 called+0.037
row+0.037
Neg logit contributions
 Ow-0.058
ked-0.058
ifying-0.057
arre-0.056
joy-0.055
Token special
Token ID2041
Feature activation-6.82e-01

Pos logit contributions
ked+0.008
anish+0.008
 Ow+0.007
 anymore+0.007
joy+0.007
Neg logit contributions
asis-0.009
rig-0.009
place-0.008
row-0.007
eh-0.007
Token goodbye
Token ID24829
Feature activation-6.52e+00

Pos logit contributions
ked+0.027
anish+0.026
 Ow+0.025
joy+0.025
 anymore+0.025
Neg logit contributions
asis-0.032
rig-0.031
place-0.030
row-0.027
eh-0.027
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
ked+0.266
anish+0.264
 Ow+0.259
joy+0.246
 anymore+0.241
Neg logit contributions
asis-0.296
rig-0.283
place-0.273
row-0.254
eh-0.245
Token
Token ID198
Feature activation+8.60e-02

Pos logit contributions
ked+0.008
anish+0.008
 prope+0.007
 anymore+0.007
 Ow+0.007
Neg logit contributions
rig-0.009
asis-0.009
place-0.008
old-0.008
eh-0.008
Token
Token ID198
Feature activation+3.09e-01

Pos logit contributions
asis+0.005
place+0.005
rig+0.005
row+0.004
eh+0.004
Neg logit contributions
 Ow-0.002
anish-0.002
ked-0.002
 anymore-0.002
joy-0.002
TokenJack
Token ID14295
Feature activation-6.42e-01

Pos logit contributions
asis+0.014
rig+0.013
place+0.013
eh+0.012
old+0.012
Neg logit contributions
ked-0.013
anish-0.013
 Ow-0.012
joy-0.012
 anymore-0.012
Token and
Token ID290
Feature activation-6.43e-01

Pos logit contributions
ked+0.021
anish+0.020
 Ow+0.019
joy+0.018
 anymore+0.018
Neg logit contributions
asis-0.035
rig-0.034
place-0.033
eh-0.030
isin-0.030
Token there
Token ID612
Feature activation-4.78e-01

Pos logit contributions
ked+0.054
anish+0.050
 Ow+0.045
adoes+0.045
joy+0.044
Neg logit contributions
asis-0.099
rig-0.097
place-0.093
old-0.091
row-0.089
Token was
Token ID373
Feature activation+4.40e-01

Pos logit contributions
ked+0.018
anish+0.017
 Ow+0.016
joy+0.016
adoes+0.016
Neg logit contributions
asis-0.024
rig-0.022
place-0.022
old-0.020
row-0.020
Token a
Token ID257
Feature activation-1.69e-01

Pos logit contributions
asis+0.021
place+0.020
rig+0.020
eh+0.019
old+0.019
Neg logit contributions
ked-0.017
anish-0.016
joy-0.015
adoes-0.015
 anymore-0.015
Token little
Token ID1310
Feature activation+5.62e-01

Pos logit contributions
ked+0.006
anish+0.005
 Ow+0.005
joy+0.005
 anymore+0.005
Neg logit contributions
asis-0.009
rig-0.009
place-0.009
row-0.008
eh-0.008
Token girl
Token ID2576
Feature activation+7.30e-01

Pos logit contributions
asis+0.033
rig+0.032
place+0.031
row+0.029
eh+0.029
Neg logit contributions
ked-0.015
anish-0.014
 Ow-0.014
joy-0.014
 anymore-0.014
Token called
Token ID1444
Feature activation+5.43e+00

Pos logit contributions
asis+0.038
rig+0.036
place+0.033
isin+0.032
row+0.030
Neg logit contributions
 anymore-0.027
ked-0.026
joy-0.025
anish-0.024
 Ow-0.023
Token Penny
Token ID25965
Feature activation+1.35e+00

Pos logit contributions
asis+0.301
rig+0.286
place+0.278
row+0.256
isin+0.251
Neg logit contributions
ked-0.178
anish-0.173
 Ow-0.172
 anymore-0.167
joy-0.165
Token.
Token ID13
Feature activation+5.71e-01

Pos logit contributions
asis+0.086
rig+0.079
place+0.077
isin+0.076
rim+0.073
Neg logit contributions
ked-0.037
 anymore-0.036
joy-0.032
 again-0.030
 Ow-0.029
Token Penny
Token ID25965
Feature activation-1.52e-01

Pos logit contributions
rig+0.022
place+0.022
asis+0.022
row+0.019
 called+0.019
Neg logit contributions
ked-0.026
anish-0.024
 prope-0.023
 Ow-0.023
adoes-0.023
Token was
Token ID373
Feature activation+6.70e-01

Pos logit contributions
ked+0.004
 Ow+0.003
 anymore+0.003
anish+0.003
joy+0.003
Neg logit contributions
asis-0.009
rig-0.009
place-0.009
row-0.008
isin-0.008
Token three
Token ID1115
Feature activation+1.49e+00

Pos logit contributions
asis+0.034
rig+0.033
place+0.032
row+0.030
eh+0.029
Neg logit contributions
ked-0.024
anish-0.023
 Ow-0.023
joy-0.023
 anymore-0.022
Token whispered
Token ID25029
Feature activation+8.87e-01

Pos logit contributions
ked+0.039
anish+0.039
 Ow+0.038
 anymore+0.037
joy+0.036
Neg logit contributions
asis-0.040
rig-0.039
place-0.037
row-0.034
eh-0.034
Token,
Token ID11
Feature activation+4.57e-01

Pos logit contributions
asis+0.034
row+0.033
place+0.033
rig+0.032
b+0.030
Neg logit contributions
 Ow-0.038
anish-0.038
arre-0.037
Goal-0.036
Mine-0.035
Token "
Token ID366
Feature activation-1.46e+00

Pos logit contributions
asis+0.026
rig+0.025
place+0.024
row+0.022
eh+0.022
Neg logit contributions
anish-0.013
ked-0.013
 Ow-0.013
 anymore-0.012
joy-0.012
TokenAre
Token ID8491
Feature activation-2.55e-01

Pos logit contributions
ked+0.049
 anymore+0.047
anish+0.047
joy+0.046
 Ow+0.045
Neg logit contributions
asis-0.077
rig-0.075
place-0.072
row-0.066
eh-0.065
Token the
Token ID262
Feature activation+3.22e+00

Pos logit contributions
ked+0.015
anish+0.014
joy+0.014
 tant+0.014
 Ow+0.014
Neg logit contributions
asis-0.007
rig-0.007
place-0.007
isin-0.006
row-0.005
Token leaves
Token ID5667
Feature activation+5.56e+00

Pos logit contributions
asis+0.138
rig+0.132
place+0.128
row+0.116
old+0.114
Neg logit contributions
ked-0.142
anish-0.137
 Ow-0.135
joy-0.133
 anymore-0.133
Token talking
Token ID3375
Feature activation-1.16e+00

Pos logit contributions
asis+0.263
rig+0.262
place+0.250
old+0.241
eh+0.229
Neg logit contributions
ked-0.205
 anymore-0.203
anish-0.198
 Ow-0.193
adoes-0.185
Token?"
Token ID1701
Feature activation+7.49e-01

Pos logit contributions
ked+0.047
joy+0.045
anish+0.044
 Ow+0.043
 tant+0.040
Neg logit contributions
asis-0.054
rig-0.052
place-0.051
row-0.047
eh-0.045
Token
Token ID198
Feature activation+5.82e-01

Pos logit contributions
asis+0.041
rig+0.039
place+0.039
row+0.036
eh+0.035
Neg logit contributions
ked-0.024
joy-0.024
anish-0.023
 Ow-0.023
 anymore-0.022
Token
Token ID198
Feature activation+6.63e-01

Pos logit contributions
asis+0.034
rig+0.032
place+0.032
row+0.029
eh+0.028
Neg logit contributions
 Ow-0.017
anish-0.016
ked-0.016
joy-0.016
 anymore-0.015
TokenHis
Token ID6653
Feature activation-1.42e+00

Pos logit contributions
asis+0.033
rig+0.032
place+0.031
row+0.028
isin+0.027
Neg logit contributions
anish-0.024
ked-0.024
 Ow-0.023
joy-0.023
Look-0.021
Token.
Token ID13
Feature activation+5.43e-01

Pos logit contributions
asis+0.029
rig+0.028
place+0.027
row+0.024
eh+0.024
Neg logit contributions
ked-0.029
anish-0.028
 Ow-0.028
joy-0.027
 anymore-0.027
Token Lib
Token ID7980
Feature activation-1.51e-01

Pos logit contributions
asis+0.020
place+0.018
rig+0.018
old+0.017
 stump+0.015
Neg logit contributions
ked-0.026
anish-0.026
arre-0.025
 tant-0.025
adoes-0.024
Tokenby
Token ID1525
Feature activation-1.01e+00

Pos logit contributions
ked+0.005
anish+0.005
 Ow+0.005
joy+0.005
adoes+0.005
Neg logit contributions
asis-0.008
rig-0.008
place-0.008
old-0.007
row-0.007
Token was
Token ID373
Feature activation+4.75e-01

Pos logit contributions
anish+0.024
ked+0.024
 Ow+0.023
joy+0.022
 anymore+0.022
Neg logit contributions
rig-0.061
asis-0.060
place-0.058
isin-0.054
row-0.054
Token three
Token ID1115
Feature activation+1.27e+00

Pos logit contributions
asis+0.025
rig+0.024
place+0.023
row+0.022
old+0.021
Neg logit contributions
ked-0.017
 Ow-0.016
joy-0.016
anish-0.016
 anymore-0.015
Token years
Token ID812
Feature activation+4.66e+00

Pos logit contributions
asis+0.039
rig+0.036
place+0.032
row+0.030
eh+0.028
Neg logit contributions
 anymore-0.069
ked-0.069
joy-0.068
anish-0.066
 tant-0.065
Token old
Token ID1468
Feature activation+3.75e+00

Pos logit contributions
asis+0.225
rig+0.206
eling+0.196
place+0.188
fire+0.182
Neg logit contributions
joy-0.187
 at-0.180
 eyes-0.175
 anymore-0.174
 heart-0.156
Token and
Token ID290
Feature activation+8.98e-01

Pos logit contributions
asis+0.167
place+0.161
rig+0.157
old+0.143
row+0.142
Neg logit contributions
anish-0.155
ked-0.155
 Ow-0.148
joy-0.139
arre-0.138
Token loved
Token ID6151
Feature activation-5.40e-02

Pos logit contributions
asis+0.061
rig+0.060
place+0.056
row+0.055
rim+0.054
Neg logit contributions
ked-0.017
Wow-0.016
Look-0.015
joy-0.015
 superstar-0.014
Token to
Token ID284
Feature activation+6.02e-01

Pos logit contributions
ked+0.002
anish+0.002
 Ow+0.002
joy+0.002
 anymore+0.001
Neg logit contributions
asis-0.003
rig-0.003
place-0.003
row-0.003
eh-0.003
Token pick
Token ID2298
Feature activation+2.68e+00

Pos logit contributions
rig+0.031
asis+0.031
place+0.028
row+0.028
isin+0.027
Neg logit contributions
 Ow-0.020
anish-0.020
ked-0.019
 anymore-0.019
 guys-0.019
Token saw
Token ID2497
Feature activation-1.33e-01

Pos logit contributions
ked+0.010
anish+0.010
 Ow+0.009
joy+0.009
 anymore+0.009
Neg logit contributions
asis-0.015
rig-0.015
place-0.015
eh-0.013
row-0.013
Token two
Token ID734
Feature activation-7.02e-01

Pos logit contributions
ked+0.005
anish+0.005
 Ow+0.005
joy+0.004
 anymore+0.004
Neg logit contributions
asis-0.006
place-0.006
rig-0.006
old-0.006
eh-0.006
Token gates
Token ID17435
Feature activation+3.29e+00

Pos logit contributions
ked+0.028
anish+0.028
 Ow+0.027
joy+0.026
 anymore+0.025
Neg logit contributions
asis-0.033
place-0.031
rig-0.031
eh-0.028
row-0.028
Token.
Token ID13
Feature activation-3.90e-02

Pos logit contributions
asis+0.154
rig+0.147
place+0.143
row+0.130
eh+0.129
Neg logit contributions
ked-0.133
anish-0.128
 Ow-0.125
joy-0.123
 anymore-0.122
Token One
Token ID1881
Feature activation+9.34e-01

Pos logit contributions
ked+0.001
anish+0.001
 Ow+0.001
joy+0.001
 anymore+0.001
Neg logit contributions
asis-0.002
rig-0.002
place-0.002
old-0.002
eh-0.002
Token gate
Token ID8946
Feature activation+4.17e+00

Pos logit contributions
asis+0.044
rig+0.041
isin+0.040
place+0.039
ands+0.038
Neg logit contributions
 anymore-0.036
ked-0.034
anish-0.034
 Ow-0.033
joy-0.033
Token was
Token ID373
Feature activation+7.70e-01

Pos logit contributions
asis+0.179
place+0.169
rig+0.165
row+0.156
old+0.155
Neg logit contributions
 Ow-0.179
ked-0.178
anish-0.173
joy-0.172
 tant-0.164
Token small
Token ID1402
Feature activation+2.92e+00

Pos logit contributions
asis+0.034
rig+0.033
place+0.032
row+0.029
eh+0.029
Neg logit contributions
ked-0.032
anish-0.031
 Ow-0.031
joy-0.030
 anymore-0.030
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
place+0.127
asis+0.125
rig+0.120
 called+0.112
old+0.110
Neg logit contributions
 Ow-0.122
ked-0.120
anish-0.119
joy-0.108
Goal-0.106
Token blue
Token ID4171
Feature activation+1.07e+00

Pos logit contributions
asis+0.043
place+0.042
rig+0.041
 called+0.038
 stump+0.037
Neg logit contributions
ked-0.044
anish-0.044
 Ow-0.043
joy-0.041
 anymore-0.040
Token,
Token ID11
Feature activation-1.59e-01

Pos logit contributions
asis+0.042
place+0.040
rig+0.037
row+0.036
 called+0.035
Neg logit contributions
ked-0.049
 Ow-0.048
joy-0.048
anish-0.047
 tant-0.047
Tokenie
Token ID494
Feature activation+2.62e+00

Pos logit contributions
asis+0.058
rig+0.054
place+0.052
row+0.045
eh+0.044
Neg logit contributions
ked-0.124
anish-0.121
 Ow-0.119
joy-0.118
 anymore-0.116
Token and
Token ID290
Feature activation+9.63e-01

Pos logit contributions
asis+0.150
rig+0.140
place+0.136
isin+0.126
row+0.125
Neg logit contributions
 anymore-0.082
ked-0.082
joy-0.073
anish-0.071
 Ow-0.070
Token she
Token ID673
Feature activation-4.47e-01

Pos logit contributions
asis+0.046
rig+0.045
place+0.043
row+0.039
eh+0.038
Neg logit contributions
ked-0.039
anish-0.037
 Ow-0.037
joy-0.036
 anymore-0.036
Token was
Token ID373
Feature activation+1.84e-01

Pos logit contributions
ked+0.011
anish+0.010
 anymore+0.010
 superstar+0.010
 Ow+0.009
Neg logit contributions
asis-0.027
rig-0.027
place-0.026
row-0.025
isin-0.024
Token 3
Token ID513
Feature activation+7.99e-01

Pos logit contributions
asis+0.008
rig+0.008
place+0.007
row+0.007
old+0.006
Neg logit contributions
ked-0.008
anish-0.008
 Ow-0.008
joy-0.008
 anymore-0.008
Token years
Token ID812
Feature activation+4.94e+00

Pos logit contributions
asis+0.021
rig+0.019
place+0.018
row+0.015
eh+0.014
Neg logit contributions
ked-0.048
 anymore-0.047
anish-0.047
joy-0.047
 Ow-0.046
Token old
Token ID1468
Feature activation+3.84e+00

Pos logit contributions
asis+0.241
rig+0.205
at+0.198
eling+0.194
roads+0.194
Neg logit contributions
 anymore-0.200
joy-0.200
 eyes-0.193
 asleep-0.188
 at-0.186
Token.
Token ID13
Feature activation+4.25e-01

Pos logit contributions
asis+0.130
place+0.128
rig+0.124
 called+0.112
old+0.109
Neg logit contributions
anish-0.194
ked-0.192
 Ow-0.186
arre-0.177
adoes-0.176
Token
Token ID198
Feature activation+5.60e-01

Pos logit contributions
asis+0.022
rig+0.021
place+0.021
row+0.019
eh+0.019
Neg logit contributions
ked-0.015
anish-0.014
 Ow-0.014
joy-0.014
 anymore-0.014
Token
Token ID198
Feature activation+7.99e-01

Pos logit contributions
asis+0.026
rig+0.025
place+0.025
old+0.023
row+0.022
Neg logit contributions
ked-0.023
anish-0.021
 Ow-0.021
joy-0.020
 anymore-0.020
TokenOne
Token ID3198
Feature activation+8.27e-01

Pos logit contributions
asis+0.038
rig+0.036
place+0.034
row+0.032
eh+0.031
Neg logit contributions
ked-0.031
anish-0.031
 Ow-0.030
joy-0.030
 anymore-0.030
Token appreciate
Token ID9144
Feature activation-5.77e-01

Pos logit contributions
ked+0.028
 anymore+0.028
joy+0.028
 Ow+0.028
anish+0.027
Neg logit contributions
rig-0.031
asis-0.030
place-0.028
row-0.027
old-0.027
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
ked+0.022
anish+0.021
 Ow+0.021
joy+0.020
 anymore+0.020
Neg logit contributions
asis-0.028
rig-0.027
place-0.027
row-0.024
eh-0.024
Token beauty
Token ID8737
Feature activation+1.83e-01

Pos logit contributions
asis+0.057
rig+0.054
place+0.052
row+0.049
eh+0.048
Neg logit contributions
ked-0.059
anish-0.057
joy-0.057
 Ow-0.057
 anymore-0.056
Token of
Token ID286
Feature activation-1.31e+00

Pos logit contributions
asis+0.008
rig+0.008
place+0.007
eh+0.007
row+0.007
Neg logit contributions
ked-0.008
 anymore-0.008
anish-0.007
joy-0.007
 Ow-0.007
Token the
Token ID262
Feature activation+6.89e-01

Pos logit contributions
ked+0.046
anish+0.044
 Ow+0.043
joy+0.043
 anymore+0.043
Neg logit contributions
asis-0.067
rig-0.066
place-0.063
row-0.059
eh-0.058
Token me
Token ID502
Feature activation+1.23e+00

Pos logit contributions
asis+0.031
rig+0.030
place+0.028
row+0.027
old+0.027
Neg logit contributions
ked-0.027
joy-0.027
 Ow-0.027
 anymore-0.026
anish-0.026
Tokenadow
Token ID4584
Feature activation+3.36e+00

Pos logit contributions
place+0.028
rig+0.028
asis+0.028
 pharmacy+0.025
isin+0.024
Neg logit contributions
 anymore-0.072
joy-0.069
ked-0.065
 again-0.065
ved-0.062
Token.
Token ID13
Feature activation-2.34e-01

Pos logit contributions
asis+0.160
rig+0.154
place+0.150
row+0.136
eh+0.135
Neg logit contributions
ked-0.132
anish-0.126
 Ow-0.123
joy-0.122
 anymore-0.121
Token<|endoftext|>
Token ID50256
Feature activation-5.16e-01

Pos logit contributions
 Ow+0.008
ked+0.008
anish+0.007
joy+0.007
 anymore+0.007
Neg logit contributions
asis-0.013
rig-0.012
place-0.012
row-0.011
isin-0.011
TokenOnce
Token ID7454
Feature activation-1.65e+00

Pos logit contributions
ked+0.025
anish+0.023
adoes+0.023
 tant+0.022
 prope+0.022
Neg logit contributions
asis-0.021
rig-0.019
place-0.019
row-0.017
eh-0.017
Token upon
Token ID2402
Feature activation-4.25e-01

Pos logit contributions
ked+0.050
anish+0.046
 Ow+0.042
adoes+0.041
joy+0.041
Neg logit contributions
asis-0.094
rig-0.092
place-0.089
old-0.085
row-0.084
Token."
Token ID526
Feature activation-2.94e-02

Pos logit contributions
ked+0.072
anish+0.070
 Ow+0.068
 anymore+0.067
joy+0.067
Neg logit contributions
asis-0.077
rig-0.075
place-0.072
eh-0.065
row-0.065
Token She
Token ID1375
Feature activation+1.10e+00

Pos logit contributions
ked+0.001
anish+0.001
 Ow+0.001
 anymore+0.001
adoes+0.001
Neg logit contributions
asis-0.001
rig-0.001
place-0.001
old-0.001
row-0.001
Token took
Token ID1718
Feature activation-9.78e-01

Pos logit contributions
asis+0.053
rig+0.050
place+0.049
row+0.044
old+0.044
Neg logit contributions
ked-0.044
anish-0.041
 Ow-0.040
joy-0.040
 anymore-0.039
Token Ben
Token ID3932
Feature activation+5.12e-01

Pos logit contributions
anish+0.038
ked+0.038
joy+0.037
 prope+0.036
 superstar+0.035
Neg logit contributions
place-0.041
asis-0.041
aster-0.040
old-0.040
rig-0.040
Token's
Token ID338
Feature activation+1.10e-02

Pos logit contributions
asis+0.029
rig+0.027
place+0.027
eh+0.025
row+0.024
Neg logit contributions
ked-0.016
anish-0.015
 Ow-0.015
 anymore-0.015
joy-0.015
Token hand
Token ID1021
Feature activation+1.15e+00

Pos logit contributions
asis+0.001
rig+0.001
place+0.001
row+0.000
eh+0.000
Neg logit contributions
ked-0.000
anish-0.000
 Ow-0.000
joy-0.000
 anymore-0.000
Token and
Token ID290
Feature activation-8.89e-02

Pos logit contributions
asis+0.061
rig+0.059
place+0.058
row+0.055
old+0.054
Neg logit contributions
anish-0.037
ked-0.037
 Ow-0.035
joy-0.035
 anymore-0.034
Token followed
Token ID3940
Feature activation-2.38e-01

Pos logit contributions
ked+0.004
anish+0.003
 Ow+0.003
joy+0.003
 anymore+0.003
Neg logit contributions
asis-0.004
rig-0.004
place-0.004
row-0.004
old-0.004
Token their
Token ID511
Feature activation-6.40e-01

Pos logit contributions
ked+0.008
anish+0.007
 Ow+0.007
joy+0.007
 anymore+0.007
Neg logit contributions
asis-0.013
rig-0.012
place-0.012
row-0.011
old-0.011
Token trail
Token ID8025
Feature activation+2.67e+00

Pos logit contributions
ked+0.019
anish+0.018
 Ow+0.018
joy+0.017
 anymore+0.017
Neg logit contributions
asis-0.037
rig-0.036
place-0.035
row-0.032
eh-0.032
Token back
Token ID736
Feature activation-1.72e+00

Pos logit contributions
asis+0.138
rig+0.129
place+0.124
isin+0.115
eh+0.115
Neg logit contributions
ked-0.098
 anymore-0.096
anish-0.091
joy-0.087
adoes-0.084
Token the
Token ID262
Feature activation+3.91e-01

Pos logit contributions
asis+0.025
rig+0.024
place+0.023
row+0.021
eh+0.021
Neg logit contributions
ked-0.020
anish-0.019
 Ow-0.018
joy-0.018
 anymore-0.018
Token noise
Token ID7838
Feature activation+4.34e-01

Pos logit contributions
asis+0.019
rig+0.018
place+0.018
row+0.016
eh+0.016
Neg logit contributions
ked-0.015
anish-0.014
 Ow-0.014
joy-0.014
 anymore-0.014
Token made
Token ID925
Feature activation+5.66e-01

Pos logit contributions
asis+0.023
rig+0.022
place+0.021
row+0.020
eh+0.019
Neg logit contributions
ked-0.015
anish-0.015
 Ow-0.014
joy-0.014
 anymore-0.013
Token them
Token ID606
Feature activation+3.72e-01

Pos logit contributions
asis+0.031
rig+0.030
place+0.029
row+0.027
eh+0.027
Neg logit contributions
ked-0.018
anish-0.017
 Ow-0.017
joy-0.016
 anymore-0.016
Token turn
Token ID1210
Feature activation+1.82e+00

Pos logit contributions
asis+0.014
rig+0.014
place+0.014
row+0.012
old+0.012
Neg logit contributions
anish-0.018
ked-0.017
joy-0.017
 Ow-0.017
 superstar-0.016
Token around
Token ID1088
Feature activation+2.65e-01

Pos logit contributions
rig+0.079
place+0.075
asis+0.073
row+0.071
 called+0.071
Neg logit contributions
anish-0.079
 Ow-0.073
joy-0.069
ked-0.067
 superstar-0.065
Token.
Token ID13
Feature activation-1.52e-02

Pos logit contributions
asis+0.010
place+0.010
rig+0.010
row+0.009
 called+0.009
Neg logit contributions
ked-0.012
anish-0.012
 Ow-0.012
adoes-0.011
arre-0.011
Token
Token ID220
Feature activation-1.53e+00

Pos logit contributions
ked+0.001
 Ow+0.001
anish+0.000
joy+0.000
 anymore+0.000
Neg logit contributions
asis-0.001
rig-0.001
place-0.001
eh-0.001
isin-0.001
Token
Token ID198
Feature activation+1.47e-01

Pos logit contributions
 Ow+0.046
ked+0.045
anish+0.044
 anymore+0.043
joy+0.041
Neg logit contributions
asis-0.087
place-0.081
rig-0.081
row-0.075
eh-0.075
Token
Token ID198
Feature activation+3.79e-01

Pos logit contributions
asis+0.009
rig+0.008
place+0.008
eh+0.008
row+0.008
Neg logit contributions
 Ow-0.004
anish-0.004
ked-0.004
joy-0.003
 anymore-0.003
TokenThe
Token ID464
Feature activation+1.30e+00

Pos logit contributions
asis+0.019
rig+0.018
place+0.018
old+0.017
eh+0.016
Neg logit contributions
ked-0.014
anish-0.013
 Ow-0.013
joy-0.012
Look-0.012
Token
Token ID198
Feature activation-1.71e-01

Pos logit contributions
ked+0.021
anish+0.020
 Ow+0.019
joy+0.019
 anymore+0.019
Neg logit contributions
asis-0.028
rig-0.027
place-0.026
row-0.024
eh-0.024
Token
Token ID198
Feature activation+1.02e-01

Pos logit contributions
 Ow+0.004
anish+0.004
ked+0.004
joy+0.004
 anymore+0.004
Neg logit contributions
asis-0.010
place-0.010
rig-0.010
row-0.009
eh-0.009
TokenBilly
Token ID49640
Feature activation-9.48e-01

Pos logit contributions
asis+0.005
rig+0.005
place+0.004
row+0.004
eh+0.004
Neg logit contributions
ked-0.004
anish-0.004
 Ow-0.004
joy-0.004
 anymore-0.004
Token was
Token ID373
Feature activation-5.00e-01

Pos logit contributions
ked+0.031
anish+0.028
 Ow+0.027
joy+0.027
 anymore+0.026
Neg logit contributions
asis-0.052
rig-0.050
place-0.049
eh-0.046
row-0.045
Token mesmer
Token ID46814
Feature activation-1.25e+00

Pos logit contributions
ked+0.021
joy+0.020
 anymore+0.020
anish+0.019
 Ow+0.019
Neg logit contributions
asis-0.023
rig-0.022
place-0.022
row-0.020
eh-0.019
Tokenized
Token ID1143
Feature activation+3.56e-01

Pos logit contributions
anish+0.063
ked+0.061
 Ow+0.060
joy+0.056
 anymore+0.056
Neg logit contributions
asis-0.046
rig-0.044
place-0.044
old-0.037
row-0.036
Token.
Token ID13
Feature activation-9.20e-02

Pos logit contributions
rig+0.014
place+0.014
asis+0.014
old+0.012
row+0.012
Neg logit contributions
anish-0.016
ked-0.016
 Ow-0.016
 prope-0.015
 superstar-0.015
Token He
Token ID679
Feature activation-1.46e-01

Pos logit contributions
ked+0.004
anish+0.003
 Ow+0.003
joy+0.003
 anymore+0.003
Neg logit contributions
asis-0.004
rig-0.004
place-0.004
row-0.004
eh-0.004
Token couldn
Token ID3521
Feature activation-1.76e+00

Pos logit contributions
ked+0.005
anish+0.004
joy+0.004
 Ow+0.004
 anymore+0.004
Neg logit contributions
asis-0.008
rig-0.008
place-0.008
eh-0.007
row-0.007
Token't
Token ID470
Feature activation-1.33e+00

Pos logit contributions
ked+0.055
anish+0.052
 Ow+0.051
joy+0.050
 anymore+0.049
Neg logit contributions
asis-0.098
rig-0.095
place-0.092
row-0.086
eh-0.085
Token believe
Token ID1975
Feature activation-9.62e-02

Pos logit contributions
ked+0.074
 anymore+0.072
anish+0.071
 Ow+0.068
 superstar+0.067
Neg logit contributions
asis-0.042
rig-0.040
place-0.035
eh-0.035
row-0.033
Token next
Token ID1306
Feature activation-2.17e+00

Pos logit contributions
ked+0.068
 Ow+0.067
anish+0.067
adoes+0.062
joy+0.062
Neg logit contributions
asis-0.071
rig-0.067
place-0.066
row-0.060
eh-0.060
Token to
Token ID284
Feature activation-2.06e-02

Pos logit contributions
ked+0.060
anish+0.058
joy+0.055
 Ow+0.055
 anymore+0.055
Neg logit contributions
asis-0.128
rig-0.123
place-0.120
eh-0.112
row-0.112
Token Sara
Token ID24799
Feature activation+1.71e+00

Pos logit contributions
ked+0.001
anish+0.001
adoes+0.001
 Ow+0.001
arre+0.001
Neg logit contributions
asis-0.001
rig-0.001
place-0.001
aster-0.001
eh-0.001
Token.
Token ID13
Feature activation-4.00e-01

Pos logit contributions
asis+0.106
rig+0.103
place+0.103
isin+0.093
rim+0.093
Neg logit contributions
ked-0.044
 anymore-0.043
joy-0.037
 again-0.037
anish-0.036
Token He
Token ID679
Feature activation-3.01e-01

Pos logit contributions
ked+0.015
anish+0.014
 Ow+0.014
joy+0.013
 anymore+0.013
Neg logit contributions
asis-0.020
rig-0.020
place-0.019
row-0.018
eh-0.017
Token looked
Token ID3114
Feature activation+3.93e-01

Pos logit contributions
ked+0.013
anish+0.012
 Ow+0.012
joy+0.012
 anymore+0.012
Neg logit contributions
asis-0.014
rig-0.013
place-0.013
row-0.011
eh-0.011
Token at
Token ID379
Feature activation-1.25e+00

Pos logit contributions
asis+0.024
rig+0.024
place+0.023
eh+0.022
old+0.022
Neg logit contributions
anish-0.010
ked-0.010
 Ow-0.009
joy-0.008
adoes-0.008
Token the
Token ID262
Feature activation+1.62e+00

Pos logit contributions
ked+0.048
anish+0.047
joy+0.044
 Ow+0.044
 anymore+0.043
Neg logit contributions
asis-0.061
rig-0.058
place-0.057
row-0.052
old-0.052
Token book
Token ID1492
Feature activation-1.47e+00

Pos logit contributions
asis+0.080
place+0.072
rig+0.070
eh+0.067
 stump+0.064
Neg logit contributions
ked-0.067
anish-0.062
 Ow-0.059
arre-0.058
joy-0.058
Token and
Token ID290
Feature activation-8.63e-01

Pos logit contributions
ked+0.047
anish+0.045
 Ow+0.044
joy+0.043
 anymore+0.042
Neg logit contributions
asis-0.081
rig-0.078
place-0.076
row-0.070
eh-0.070
Token said
Token ID531
Feature activation+1.20e+00

Pos logit contributions
anish+0.041
ked+0.040
 Ow+0.039
 anymore+0.038
joy+0.038
Neg logit contributions
asis-0.033
rig-0.032
place-0.031
eh-0.028
old-0.027
Token in
Token ID287
Feature activation-3.98e-01

Pos logit contributions
ked+0.027
 anymore+0.026
anish+0.025
 Ow+0.022
joy+0.022
Neg logit contributions
rig-0.066
asis-0.065
place-0.061
old-0.059
eh-0.058
Token the
Token ID262
Feature activation-4.24e-01

Pos logit contributions
ked+0.015
anish+0.014
 Ow+0.014
joy+0.013
 anymore+0.013
Neg logit contributions
asis-0.020
rig-0.019
place-0.019
row-0.017
eh-0.017
Token street
Token ID4675
Feature activation+3.17e+00

Pos logit contributions
 Ow+0.019
anish+0.019
ked+0.019
 anymore+0.018
joy+0.018
Neg logit contributions
rig-0.017
asis-0.016
place-0.015
row-0.014
old-0.014
Token.
Token ID13
Feature activation+3.28e-01

Pos logit contributions
asis+0.172
rig+0.168
place+0.159
eh+0.151
isin+0.149
Neg logit contributions
 anymore-0.103
ked-0.100
anish-0.096
joy-0.095
 Ow-0.088
Token Sam
Token ID3409
Feature activation+4.13e-01

Pos logit contributions
asis+0.021
place+0.020
rig+0.019
isin+0.019
rim+0.018
Neg logit contributions
 Ow-0.009
ked-0.008
anish-0.008
joy-0.008
 anymore-0.007
Token thought
Token ID1807
Feature activation-4.00e-01

Pos logit contributions
asis+0.025
rig+0.025
place+0.024
row+0.022
isin+0.022
Neg logit contributions
ked-0.011
 Ow-0.009
anish-0.009
 anymore-0.009
joy-0.009
Token it
Token ID340
Feature activation+1.28e+00

Pos logit contributions
ked+0.011
anish+0.010
 Ow+0.010
joy+0.010
 anymore+0.010
Neg logit contributions
asis-0.024
rig-0.023
place-0.023
row-0.021
eh-0.021
Token would
Token ID561
Feature activation-1.69e+00

Pos logit contributions
asis+0.066
rig+0.063
place+0.062
row+0.057
eh+0.055
Neg logit contributions
ked-0.046
anish-0.044
joy-0.043
 Ow-0.043
 anymore-0.041
Token be
Token ID307
Feature activation+1.46e+00

Pos logit contributions
 anymore+0.065
anish+0.063
 Ow+0.061
ked+0.060
joy+0.055
Neg logit contributions
rig-0.082
asis-0.081
old-0.074
eh-0.073
place-0.073
Token y
Token ID331
Feature activation-2.47e-01

Pos logit contributions
asis+0.064
rig+0.061
place+0.058
row+0.053
old+0.053
Neg logit contributions
ked-0.064
 anymore-0.061
 Ow-0.060
anish-0.060
joy-0.060
Tokenummy
Token ID13513
Feature activation+2.86e+00

Pos logit contributions
 anymore+0.010
 Ow+0.010
anish+0.010
ked+0.010
joy+0.009
Neg logit contributions
asis-0.012
rig-0.011
place-0.010
isin-0.010
eh-0.010
Token.
Token ID13
Feature activation-2.52e-01

Pos logit contributions
asis+0.099
rig+0.096
place+0.094
row+0.083
old+0.083
Neg logit contributions
ked-0.130
 Ow-0.126
anish-0.124
 superstar-0.116
 prope-0.115
Token She
Token ID1375
Feature activation+8.97e-01

Pos logit contributions
ked+0.008
anish+0.008
 Ow+0.008
joy+0.007
 anymore+0.007
Neg logit contributions
asis-0.014
rig-0.014
place-0.013
row-0.012
eh-0.012
Token sees
Token ID7224
Feature activation+5.01e-02

Pos logit contributions
asis+0.057
rig+0.054
place+0.053
row+0.051
eh+0.050
Neg logit contributions
ked-0.021
joy-0.020
anish-0.019
 Ow-0.019
 anymore-0.019
Token Sara
Token ID24799
Feature activation+1.89e+00

Pos logit contributions
place+0.002
asis+0.002
rig+0.002
old+0.002
ion+0.002
Neg logit contributions
anish-0.002
ked-0.002
joy-0.002
 superstar-0.002
ved-0.002
Token and
Token ID290
Feature activation-1.43e-01

Pos logit contributions
asis+0.100
rig+0.097
place+0.094
row+0.089
old+0.089
Neg logit contributions
ked-0.061
anish-0.060
 Ow-0.058
joy-0.058
 anymore-0.054
Token Ben
Token ID3932
Feature activation-1.51e+00

Pos logit contributions
ked+0.004
anish+0.004
 Ow+0.004
joy+0.004
 anymore+0.004
Neg logit contributions
asis-0.008
rig-0.008
place-0.008
old-0.007
row-0.007
Token fighting
Token ID4330
Feature activation-2.40e+00

Pos logit contributions
ked+0.054
anish+0.052
 Ow+0.050
joy+0.050
 superstar+0.047
Neg logit contributions
asis-0.076
rig-0.073
place-0.072
row-0.067
old-0.067
Token.
Token ID13
Feature activation-3.34e-01

Pos logit contributions
ked+0.122
joy+0.118
 Ow+0.115
anish+0.114
 superstar+0.112
Neg logit contributions
rig-0.082
asis-0.078
place-0.078
old-0.070
row-0.070
Token She
Token ID1375
Feature activation+9.54e-01

Pos logit contributions
ked+0.012
anish+0.011
 Ow+0.011
 anymore+0.011
joy+0.011
Neg logit contributions
asis-0.017
rig-0.017
place-0.016
old-0.015
row-0.015
Token sees
Token ID7224
Feature activation+8.12e-02

Pos logit contributions
asis+0.055
rig+0.052
place+0.051
row+0.048
eh+0.047
Neg logit contributions
ked-0.029
anish-0.027
 Ow-0.027
joy-0.026
 anymore-0.026
Token the
Token ID262
Feature activation+9.40e-01

Pos logit contributions
asis+0.004
rig+0.004
place+0.004
old+0.004
row+0.003
Neg logit contributions
ked-0.003
anish-0.003
joy-0.003
 Ow-0.003
 anymore-0.003
Token because
Token ID780
Feature activation+1.71e+00

Pos logit contributions
place+0.026
rig+0.026
asis+0.026
row+0.023
old+0.023
Neg logit contributions
ked-0.032
anish-0.031
 Ow-0.031
joy-0.029
 prope-0.029
Token he
Token ID339
Feature activation-2.23e+00

Pos logit contributions
asis+0.062
rig+0.058
place+0.058
row+0.050
old+0.050
Neg logit contributions
ked-0.087
anish-0.085
 Ow-0.083
joy-0.081
 anymore-0.079
Token was
Token ID373
Feature activation-5.84e-01

Pos logit contributions
ked+0.069
anish+0.062
 Ow+0.062
 anymore+0.060
joy+0.060
Neg logit contributions
asis-0.127
rig-0.121
place-0.119
row-0.110
eh-0.109
Token taking
Token ID2263
Feature activation+5.78e-01

Pos logit contributions
anish+0.026
ked+0.026
 Ow+0.025
joy+0.024
 anymore+0.023
Neg logit contributions
asis-0.024
rig-0.023
place-0.023
eh-0.021
old-0.020
Token dance
Token ID9280
Feature activation+4.20e-01

Pos logit contributions
asis+0.026
place+0.026
rig+0.026
row+0.023
old+0.023
Neg logit contributions
ked-0.023
anish-0.022
 Ow-0.021
joy-0.021
 anymore-0.020
Token lessons
Token ID11658
Feature activation-1.93e+00

Pos logit contributions
asis+0.019
rig+0.019
place+0.018
row+0.017
eh+0.016
Neg logit contributions
ked-0.017
 Ow-0.017
anish-0.017
joy-0.016
adoes-0.015
Token.
Token ID13
Feature activation-2.30e-01

Pos logit contributions
ked+0.072
 anymore+0.069
anish+0.069
joy+0.067
 Ow+0.065
Neg logit contributions
asis-0.096
rig-0.090
place-0.088
eh-0.081
row-0.081
Token H
Token ID367
Feature activation-7.87e-01

Pos logit contributions
ked+0.008
 Ow+0.008
anish+0.008
joy+0.008
 anymore+0.008
Neg logit contributions
asis-0.012
rig-0.011
place-0.011
eh-0.010
row-0.010
Tokenoot
Token ID1025
Feature activation+3.93e-01

Pos logit contributions
ked+0.042
anish+0.039
 Ow+0.039
 anymore+0.038
joy+0.038
Neg logit contributions
asis-0.028
rig-0.025
place-0.025
eh-0.022
aster-0.022
Tokenie
Token ID494
Feature activation+4.54e-02

Pos logit contributions
asis+0.012
rig+0.011
place+0.011
row+0.010
eh+0.009
Neg logit contributions
ked-0.022
anish-0.022
 Ow-0.021
joy-0.021
 anymore-0.021
Token's
Token ID338
Feature activation-8.24e-01

Pos logit contributions
asis+0.002
rig+0.002
place+0.002
row+0.002
eh+0.002
Neg logit contributions
ked-0.002
anish-0.002
 Ow-0.002
joy-0.002
 anymore-0.002
Token day
Token ID1110
Feature activation+3.60e-01

Pos logit contributions
asis+0.050
rig+0.048
place+0.046
ands+0.044
isin+0.042
Neg logit contributions
 Ow-0.045
 anymore-0.045
anish-0.041
joy-0.041
ked-0.041
Token,
Token ID11
Feature activation+5.54e-02

Pos logit contributions
asis+0.012
place+0.011
eh+0.011
row+0.011
old+0.011
Neg logit contributions
ked-0.018
anish-0.017
adoes-0.017
joy-0.017
 prope-0.016
Token she
Token ID673
Feature activation+2.09e-01

Pos logit contributions
 called+0.001
aster+0.001
eh+0.001
place+0.001
asis+0.001
Neg logit contributions
arre-0.003
anish-0.003
ked-0.003
 prope-0.003
joy-0.003
Token went
Token ID1816
Feature activation+1.28e+00

Pos logit contributions
asis+0.010
rig+0.009
place+0.009
eh+0.009
old+0.009
Neg logit contributions
ked-0.008
anish-0.008
joy-0.008
 Ow-0.008
 anymore-0.008
Token for
Token ID329
Feature activation+8.01e-01

Pos logit contributions
asis+0.084
rig+0.083
place+0.078
isin+0.077
rim+0.074
Neg logit contributions
ked-0.027
joy-0.025
 anymore-0.024
 on-0.021
 Ow-0.021
Token a
Token ID257
Feature activation-1.56e-01

Pos logit contributions
asis+0.045
rig+0.043
place+0.042
row+0.039
eh+0.039
Neg logit contributions
ked-0.025
anish-0.023
 Ow-0.023
joy-0.022
 anymore-0.022
Token walk
Token ID2513
Feature activation-3.35e-01

Pos logit contributions
ked+0.007
anish+0.007
 Ow+0.007
joy+0.007
 anymore+0.007
Neg logit contributions
asis-0.006
rig-0.006
place-0.006
row-0.005
eh-0.005
Token with
Token ID351
Feature activation-7.03e-02

Pos logit contributions
ked+0.009
anish+0.009
 anymore+0.008
joy+0.008
 Ow+0.008
Neg logit contributions
asis-0.020
rig-0.019
place-0.019
row-0.017
isin-0.017
Token her
Token ID607
Feature activation+6.80e-01

Pos logit contributions
ked+0.002
 Ow+0.002
anish+0.002
joy+0.002
 anymore+0.002
Neg logit contributions
asis-0.004
rig-0.004
place-0.004
row-0.004
eh-0.003
Token mom
Token ID1995
Feature activation-5.33e-01

Pos logit contributions
asis+0.033
place+0.033
rig+0.032
 called+0.029
eh+0.029
Neg logit contributions
anish-0.025
ked-0.025
 Ow-0.023
arre-0.022
joy-0.022
Token in
Token ID287
Feature activation+1.09e-01

Pos logit contributions
ked+0.016
 anymore+0.016
joy+0.015
 Ow+0.014
anish+0.014
Neg logit contributions
asis-0.030
rig-0.029
place-0.027
isin-0.026
eh-0.025
Token.
Token ID13
Feature activation+7.89e-02

Pos logit contributions
asis+0.045
rig+0.043
place+0.043
row+0.038
eh+0.038
Neg logit contributions
ked-0.046
anish-0.044
 Ow-0.043
joy-0.043
 anymore-0.041
Token We
Token ID775
Feature activation-5.72e-01

Pos logit contributions
asis+0.004
rig+0.004
place+0.004
row+0.004
eh+0.004
Neg logit contributions
ked-0.003
anish-0.003
 Ow-0.003
joy-0.002
 anymore-0.002
Token can
Token ID460
Feature activation-1.11e+00

Pos logit contributions
ked+0.016
anish+0.015
 Ow+0.015
joy+0.014
 anymore+0.014
Neg logit contributions
asis-0.034
rig-0.033
place-0.032
row-0.030
eh-0.030
Token float
Token ID12178
Feature activation+1.90e-01

Pos logit contributions
ked+0.049
anish+0.047
 Ow+0.046
 anymore+0.046
joy+0.044
Neg logit contributions
asis-0.047
rig-0.046
place-0.044
row-0.040
eh-0.040
Token on
Token ID319
Feature activation-2.17e+00

Pos logit contributions
asis+0.009
place+0.009
rig+0.009
row+0.009
b+0.008
Neg logit contributions
ked-0.007
joy-0.007
anish-0.007
 Ow-0.006
arre-0.006
Token the
Token ID262
Feature activation-5.36e-01

Pos logit contributions
ked+0.099
anish+0.097
joy+0.090
arre+0.088
ved+0.087
Neg logit contributions
asis-0.088
place-0.084
rig-0.084
eh-0.074
aster-0.073
Token raft
Token ID31812
Feature activation+8.54e-01

Pos logit contributions
ked+0.027
 Ow+0.026
anish+0.025
 anymore+0.025
joy+0.025
Neg logit contributions
asis-0.019
rig-0.019
place-0.018
old-0.017
row-0.016
Token together
Token ID1978
Feature activation-2.03e+00

Pos logit contributions
asis+0.044
rig+0.043
place+0.042
old+0.040
eh+0.039
Neg logit contributions
 anymore-0.030
ked-0.029
anish-0.027
 Ow-0.025
 again-0.025
Token,"
Token ID553
Feature activation-1.79e+00

Pos logit contributions
ked+0.092
anish+0.088
 Ow+0.086
joy+0.086
 anymore+0.082
Neg logit contributions
asis-0.085
rig-0.081
place-0.080
row-0.072
eh-0.070
Token Lily
Token ID20037
Feature activation+5.43e-01

Pos logit contributions
ked+0.072
anish+0.071
 Ow+0.066
adoes+0.065
 anymore+0.064
Neg logit contributions
asis-0.081
rig-0.079
place-0.078
old-0.072
 called-0.070
Token says
Token ID1139
Feature activation+4.97e-01

Pos logit contributions
asis+0.025
rig+0.023
place+0.023
row+0.021
eh+0.020
Neg logit contributions
ked-0.023
anish-0.022
 Ow-0.022
joy-0.021
 anymore-0.021
Token unt
Token ID1418
Feature activation-1.75e+00

Pos logit contributions
asis+0.002
rig+0.002
place+0.002
eh+0.001
old+0.001
Neg logit contributions
ked-0.001
anish-0.001
 Ow-0.001
 anymore-0.001
joy-0.001
Tokenies
Token ID444
Feature activation+1.13e+00

Pos logit contributions
ked+0.078
anish+0.075
 Ow+0.074
joy+0.072
 anymore+0.072
Neg logit contributions
asis-0.074
rig-0.071
place-0.069
row-0.062
eh-0.061
Token the
Token ID262
Feature activation+8.92e-01

Pos logit contributions
asis+0.050
place+0.048
rig+0.047
row+0.044
old+0.043
Neg logit contributions
ked-0.047
joy-0.044
 Ow-0.044
anish-0.044
 superstar-0.041
Token rope
Token ID17182
Feature activation+2.86e+00

Pos logit contributions
asis+0.033
place+0.032
rig+0.032
row+0.028
 stump+0.027
Neg logit contributions
ked-0.043
anish-0.042
 anymore-0.041
joy-0.040
 Ow-0.040
Token and
Token ID290
Feature activation-1.01e+00

Pos logit contributions
asis+0.152
rig+0.148
place+0.144
row+0.134
eh+0.131
Neg logit contributions
ked-0.095
anish-0.090
 Ow-0.089
joy-0.088
 anymore-0.084
Token fre
Token ID2030
Feature activation-4.75e+00

Pos logit contributions
ked+0.043
anish+0.043
 Ow+0.041
joy+0.041
 anymore+0.041
Neg logit contributions
asis-0.043
rig-0.042
place-0.041
old-0.037
eh-0.036
Tokenes
Token ID274
Feature activation-1.81e+00

Pos logit contributions
joy+0.148
ked+0.141
 anymore+0.139
 Ow+0.138
anish+0.138
Neg logit contributions
asis-0.259
place-0.247
rig-0.244
row-0.239
old-0.230
Token Ben
Token ID3932
Feature activation-9.35e-01

Pos logit contributions
anish+0.066
ked+0.065
joy+0.064
 Ow+0.064
 superstar+0.060
Neg logit contributions
asis-0.083
place-0.081
rig-0.081
row-0.077
old-0.077
Token.
Token ID13
Feature activation-4.92e-01

Pos logit contributions
ked+0.037
anish+0.035
 Ow+0.034
 anymore+0.034
joy+0.034
Neg logit contributions
asis-0.045
rig-0.043
place-0.042
row-0.038
eh-0.038
Token He
Token ID679
Feature activation-5.80e-01

Pos logit contributions
ked+0.020
anish+0.019
joy+0.018
 anymore+0.018
 Ow+0.018
Neg logit contributions
asis-0.022
rig-0.022
place-0.021
old-0.019
eh-0.018
Token lifts
Token ID27103
Feature activation-5.33e-01

Pos logit contributions
ked+0.022
anish+0.021
 Ow+0.021
joy+0.021
 anymore+0.020
Neg logit contributions
asis-0.028
rig-0.027
place-0.026
row-0.024
eh-0.024
Token He
Token ID679
Feature activation-2.48e-01

Pos logit contributions
asis+0.003
rig+0.003
place+0.003
row+0.003
eh+0.003
Neg logit contributions
ked-0.003
anish-0.003
 Ow-0.003
joy-0.003
 anymore-0.003
Token gives
Token ID3607
Feature activation+1.31e-01

Pos logit contributions
ked+0.009
anish+0.009
 Ow+0.009
joy+0.008
 anymore+0.008
Neg logit contributions
asis-0.012
rig-0.012
place-0.012
row-0.011
eh-0.011
Token them
Token ID606
Feature activation+1.96e+00

Pos logit contributions
place+0.007
asis+0.007
old+0.007
ion+0.007
 called+0.007
Neg logit contributions
anish-0.004
 prope-0.004
ked-0.004
arre-0.004
joy-0.004
Token each
Token ID1123
Feature activation+1.52e+00

Pos logit contributions
asis+0.107
rig+0.104
place+0.102
row+0.094
old+0.094
Neg logit contributions
ked-0.062
anish-0.060
 Ow-0.057
joy-0.057
 anymore-0.056
Token a
Token ID257
Feature activation-2.53e-01

Pos logit contributions
place+0.067
asis+0.066
rig+0.066
old+0.062
eh+0.061
Neg logit contributions
anish-0.060
ked-0.059
joy-0.057
adoes-0.056
 anymore-0.055
Token kiss
Token ID9245
Feature activation-3.77e+00

Pos logit contributions
ked+0.010
anish+0.010
 Ow+0.009
 anymore+0.009
joy+0.009
Neg logit contributions
asis-0.012
rig-0.012
place-0.011
row-0.010
eh-0.010
Token on
Token ID319
Feature activation-1.76e+00

Pos logit contributions
 Ow+0.157
joy+0.155
anish+0.152
ked+0.152
arre+0.146
Neg logit contributions
asis-0.161
place-0.150
row-0.147
rig-0.146
 called-0.137
Token the
Token ID262
Feature activation-2.25e-01

Pos logit contributions
ked+0.072
anish+0.071
joy+0.069
arre+0.067
 superstar+0.065
Neg logit contributions
place-0.072
aster-0.072
asis-0.070
rig-0.068
 called-0.068
Token lip
Token ID10645
Feature activation-1.61e+00

Pos logit contributions
ked+0.011
anish+0.010
 Ow+0.010
joy+0.010
 anymore+0.010
Neg logit contributions
asis-0.009
rig-0.008
place-0.008
row-0.007
eh-0.007
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
ked+0.062
anish+0.059
 anymore+0.059
 Ow+0.057
joy+0.054
Neg logit contributions
asis-0.079
rig-0.076
place-0.074
eh-0.067
old-0.066
Token Lily
Token ID20037
Feature activation+3.26e-02

Pos logit contributions
ked+0.009
anish+0.008
joy+0.008
 anymore+0.008
 Ow+0.008
Neg logit contributions
rig-0.008
asis-0.008
place-0.008
old-0.007
 called-0.007
Token."
Token ID526
Feature activation-5.86e-01

Pos logit contributions
asis+0.006
rig+0.006
place+0.006
row+0.005
old+0.005
Neg logit contributions
ked-0.007
anish-0.006
 Ow-0.006
joy-0.006
adoes-0.006
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
ked+0.021
anish+0.020
 Ow+0.019
joy+0.019
 anymore+0.019
Neg logit contributions
asis-0.031
rig-0.030
place-0.029
row-0.027
eh-0.026
Token
Token ID198
Feature activation+3.75e-02

Pos logit contributions
 Ow+0.003
ked+0.003
anish+0.003
 anymore+0.003
joy+0.003
Neg logit contributions
asis-0.009
place-0.008
rig-0.008
row-0.007
eh-0.007
TokenThe
Token ID464
Feature activation+3.21e-01

Pos logit contributions
asis+0.002
rig+0.002
place+0.002
at+0.002
row+0.002
Neg logit contributions
anish-0.001
ked-0.001
 Ow-0.001
Look-0.001
joy-0.001
Token mushroom
Token ID28520
Feature activation-9.89e-01

Pos logit contributions
asis+0.013
rig+0.012
place+0.012
eh+0.011
row+0.010
Neg logit contributions
ked-0.016
anish-0.014
 Ow-0.014
joy-0.014
 anymore-0.014
Token softened
Token ID41534
Feature activation-3.63e+00

Pos logit contributions
ked+0.034
anish+0.032
 Ow+0.032
joy+0.031
 anymore+0.030
Neg logit contributions
asis-0.052
rig-0.050
place-0.049
row-0.045
eh-0.045
Token.
Token ID13
Feature activation-5.09e-01

Pos logit contributions
ked+0.181
ifying+0.174
 Ow+0.173
joy+0.173
arre+0.172
Neg logit contributions
rig-0.116
 called-0.116
place-0.115
asis-0.111
row-0.110
Token It
Token ID632
Feature activation+4.62e-01

Pos logit contributions
ked+0.014
anish+0.012
 Ow+0.012
joy+0.012
 anymore+0.012
Neg logit contributions
asis-0.031
rig-0.030
place-0.029
old-0.027
row-0.027
Token saw
Token ID2497
Feature activation-8.82e-01

Pos logit contributions
asis+0.022
rig+0.021
place+0.021
row+0.019
eh+0.019
Neg logit contributions
ked-0.018
anish-0.017
 Ow-0.017
joy-0.017
 anymore-0.017
Token that
Token ID326
Feature activation-5.75e-01

Pos logit contributions
anish+0.034
joy+0.033
ked+0.032
arre+0.031
 superstar+0.030
Neg logit contributions
rig-0.039
place-0.039
asis-0.038
ion-0.038
 called-0.037
Token they
Token ID484
Feature activation-1.73e+00

Pos logit contributions
ked+0.024
joy+0.023
arre+0.022
anish+0.022
 tant+0.022
Neg logit contributions
asis-0.024
 called-0.023
place-0.023
rig-0.023
ion-0.022
Token f
Token ID277
Feature activation-3.99e-01

Pos logit contributions
rig+0.031
asis+0.031
place+0.028
eh+0.027
aling+0.027
Neg logit contributions
joy-0.027
 anymore-0.026
ked-0.026
adoes-0.025
anish-0.025
Tokenauc
Token ID14272
Feature activation-5.59e-01

Pos logit contributions
arre+0.016
ked+0.015
ifying+0.014
apped+0.014
ed+0.014
Neg logit contributions
asis-0.018
place-0.017
 stump-0.016
 pharmacy-0.016
rig-0.015
Tokenet
Token ID316
Feature activation+7.42e-01

Pos logit contributions
ked+0.021
 anymore+0.020
anish+0.020
arre+0.019
 tant+0.019
Neg logit contributions
asis-0.025
rig-0.025
place-0.024
old-0.023
 stump-0.023
Token all
Token ID477
Feature activation+3.87e-01

Pos logit contributions
asis+0.038
rig+0.037
place+0.036
eh+0.033
old+0.033
Neg logit contributions
ked-0.026
anish-0.025
 anymore-0.024
 Ow-0.024
joy-0.023
Token over
Token ID625
Feature activation-1.12e+00

Pos logit contributions
asis+0.018
rig+0.017
place+0.017
row+0.015
eh+0.015
Neg logit contributions
ked-0.016
anish-0.015
 anymore-0.015
joy-0.015
 Ow-0.015
Token again
Token ID757
Feature activation-4.36e+00

Pos logit contributions
ked+0.047
anish+0.044
 Ow+0.043
adoes+0.040
arre+0.039
Neg logit contributions
asis-0.051
place-0.050
rig-0.048
old-0.044
row-0.043
Token.
Token ID13
Feature activation-7.62e-01

Pos logit contributions
ked+0.180
anish+0.172
 Ow+0.169
joy+0.165
 anymore+0.163
Neg logit contributions
asis-0.201
rig-0.193
place-0.187
row-0.170
eh-0.168
Token<|endoftext|>
Token ID50256
Feature activation-6.09e-01

Pos logit contributions
ked+0.026
anish+0.025
 Ow+0.025
joy+0.024
 anymore+0.024
Neg logit contributions
asis-0.040
rig-0.039
place-0.038
row-0.035
eh-0.034
TokenOnce
Token ID7454
Feature activation-1.64e+00

Pos logit contributions
ked+0.031
anish+0.028
adoes+0.028
 tant+0.028
 prope+0.028
Neg logit contributions
asis-0.024
rig-0.021
place-0.021
row-0.019
old-0.019
Token upon
Token ID2402
Feature activation-5.30e-01

Pos logit contributions
ked+0.051
anish+0.047
 Ow+0.043
adoes+0.043
 prope+0.041
Neg logit contributions
asis-0.092
rig-0.091
place-0.087
old-0.085
row-0.082
Token a
Token ID257
Feature activation-1.13e-01

Pos logit contributions
ked+0.023
anish+0.022
adoes+0.021
joy+0.021
 tant+0.020
Neg logit contributions
place-0.023
asis-0.023
rig-0.023
eh-0.021
old-0.020
TokenBut
Token ID1537
Feature activation+1.64e+00

Pos logit contributions
asis+0.009
rig+0.009
place+0.008
eh+0.007
row+0.007
Neg logit contributions
ked-0.010
anish-0.010
joy-0.009
 Ow-0.009
 anymore-0.009
Token then
Token ID788
Feature activation+7.67e-01

Pos logit contributions
 called+0.036
asis+0.032
place+0.030
eh+0.028
aster+0.026
Neg logit contributions
anish-0.102
ked-0.099
joy-0.099
 Ow-0.099
arre-0.096
Token,
Token ID11
Feature activation-5.79e-01

Pos logit contributions
 called+0.020
place+0.017
asis+0.016
lly+0.015
aster+0.015
Neg logit contributions
ked-0.047
ifying-0.045
anish-0.045
 tant-0.043
 prope-0.043
Token something
Token ID1223
Feature activation-1.29e+00

Pos logit contributions
anish+0.031
ked+0.031
 prope+0.031
joy+0.030
arre+0.029
Neg logit contributions
 called-0.020
aster-0.016
place-0.015
eh-0.014
 exercise-0.014
Token bad
Token ID2089
Feature activation-3.47e+00

Pos logit contributions
ked+0.044
 anymore+0.041
anish+0.040
 Ow+0.039
joy+0.038
Neg logit contributions
asis-0.070
rig-0.065
place-0.062
row-0.059
old-0.058
Token happened
Token ID3022
Feature activation-4.16e+00

Pos logit contributions
joy+0.096
ked+0.085
 Ow+0.082
anish+0.082
 prope+0.079
Neg logit contributions
asis-0.201
place-0.198
 called-0.191
row-0.190
rig-0.189
Token.
Token ID13
Feature activation+1.20e-01

Pos logit contributions
ked+0.206
 Ow+0.201
anish+0.200
 tant+0.192
 prope+0.189
Neg logit contributions
asis-0.152
rig-0.144
place-0.140
row-0.126
eh-0.125
Token One
Token ID1881
Feature activation+9.25e-01

Pos logit contributions
place+0.005
eh+0.005
rig+0.005
 called+0.005
asis+0.004
Neg logit contributions
ked-0.005
joy-0.005
anish-0.005
 prope-0.004
ved-0.004
Token of
Token ID286
Feature activation-8.43e-01

Pos logit contributions
asis+0.035
rig+0.033
place+0.033
row+0.029
eh+0.028
Neg logit contributions
ked-0.046
anish-0.044
 Ow-0.043
joy-0.043
 anymore-0.042
Token the
Token ID262
Feature activation+8.32e-01

Pos logit contributions
ked+0.032
anish+0.030
joy+0.029
 Ow+0.029
 anymore+0.027
Neg logit contributions
asis-0.040
place-0.040
rig-0.039
eh-0.036
row-0.036
Token balloons
Token ID35485
Feature activation-1.14e+00

Pos logit contributions
asis+0.035
place+0.034
rig+0.032
eh+0.029
row+0.028
Neg logit contributions
ked-0.039
 Ow-0.037
anish-0.037
joy-0.035
adoes-0.033