TOP ACTIVATIONS
MAX = 0.099

He took the cr ay on and started to draw
draw and shared the cr ay ons . They were very
Let 's take the tw ig with us on all our
decide to share the cr ay ons . They color the
. She takes a cr ay on and writes on the
, he took the cr ay ons and some paper and
They all shared the tw ig and played games . The
. They grabbed the cr ay ons and markers and started
would take out a j igsaw puzzle and try to solve
Here , take a cr ay on ." They
. They had shared a lot and learned so much .
The bird threw the tw ig up in the air and
Todd took off the m ittens , put them under the
. He takes a cr ay on and tries to mark
. He took a cr ay on and drew something on
laughed and shared the cr ay ons .
." She took a cr ay on and drew some lines
He takes the cr ay ons from them . He
The doctor put the st eth oscope on Molly 's chest
bird and took the tw ig back to her nest to

MIN ACTIVATIONS
MIN = -0.107

away and c umin and cor i ander and card am
, but it 's not possible . We have to be
buckets and shovel s and seaw eed . Then we can
Like shells and rocks and seaw eed ." M
like fish and shells and seaw eed . But they did
some shells and rocks and seaw eed . He picked them
decorated it with shells and seaw eed . They had a
like fish and shells and seaw eed . One
added shells and stones and seaw eed to make it look
â € ™ s always possible to improve and move forward
ate it with shells and seaw eed . They find a
cand ies and fruits and vegetables and letters and numbers and
saw five fish and seven seaw eed . They were happy
of shells , rocks and seaw eed , but Jane was
sound , louder than his usual snap . The man was
see shells , rocks , seaw eed , crabs and fish
and the crabs and the seaw eed . Sam
sorry , that 's not possible ." The
of effort , it 's possible to make things better for
" Yes , that 's possible ." So Liz put a

INTERVAL 0.048 - 0.099
CONTAINS 0.296%

The moral of the story is that it is always
The moral of the story is that powerful machines must
The dog nodded and w agged his tail . He gave
, Tim !" From that day on , Tim
down and ate the y ummy pasta together . Lucy 's

INTERVAL -0.004 - 0.048
CONTAINS 61.208%

to do . She looked up and saw
excited . He bent over and picked it up , then
stretching across the sky . The family was absolutely amazed by
there was a little girl named Lily . She loved to
light . " Wow , what was that ,

INTERVAL -0.055 - -0.004
CONTAINS 38.392%

what did you do ? You should never touch the razor
made her feel very special . Every day ,
, I â € ™ d love to play with you
're going to fix them ." When they got home ,
room and have a snack ." Anna and Ben

INTERVAL -0.107 - -0.055
CONTAINS 0.104%

with things that are not yours . And you have to
eating her soup quietly and politely . She wished Sam would
a delicious carrot - but he decided not to share it
a new dress , but he didn 't know what to
had a toy helicopter that he played with every day .
Token
Token ID198
Feature activation+1.29e-02

Pos logit contributions
quet+0.005
isy+0.004
ue+0.004
comb+0.004
zie+0.004
Neg logit contributions
 asks-0.003
 writes-0.003
 pret-0.003
 meets-0.003
Jason-0.003
TokenHe
Token ID1544
Feature activation+3.79e-03

Pos logit contributions
quet+0.027
comb+0.024
isy+0.023
ue+0.021
zie+0.020
Neg logit contributions
 asks-0.019
 meets-0.018
Jason-0.018
 writes-0.017
 pret-0.016
Token took
Token ID1718
Feature activation+1.37e-02

Pos logit contributions
quet+0.007
comb+0.006
isy+0.006
ue+0.006
ie+0.005
Neg logit contributions
 asks-0.006
Jason-0.006
 meets-0.006
Ryan-0.005
 yells-0.005
Token the
Token ID262
Feature activation+3.08e-02

Pos logit contributions
quet+0.031
comb+0.027
isy+0.026
ue+0.024
lights+0.023
Neg logit contributions
 asks-0.019
 meets-0.018
 writes-0.017
Jason-0.017
 pret-0.016
Token cr
Token ID1067
Feature activation+6.11e-02

Pos logit contributions
quet+0.065
comb+0.056
isy+0.054
ue+0.049
zie+0.048
Neg logit contributions
 asks-0.045
 meets-0.043
Jason-0.042
 writes-0.041
 pret-0.039
Tokenay
Token ID323
Feature activation+9.89e-02

Pos logit contributions
comb+0.092
quet+0.088
isy+0.076
 Betty+0.075
zie+0.074
Neg logit contributions
Jason-0.096
 writes-0.095
us-0.091
Ryan-0.089
Daniel-0.087
Tokenon
Token ID261
Feature activation+5.84e-02

Pos logit contributions
quet+0.209
comb+0.207
lights+0.174
isy+0.172
zie+0.169
Neg logit contributions
 writes-0.124
 meets-0.121
Jason-0.118
 asks-0.112
 sees-0.110
Token and
Token ID290
Feature activation+1.23e-02

Pos logit contributions
quet+0.129
isy+0.109
ue+0.107
lights+0.106
comb+0.104
Neg logit contributions
 asks-0.056
 meets-0.055
 sees-0.053
 writes-0.053
Jason-0.052
Token started
Token ID2067
Feature activation-6.13e-03

Pos logit contributions
quet+0.026
comb+0.022
isy+0.021
ue+0.019
zie+0.019
Neg logit contributions
 asks-0.018
 meets-0.017
Jason-0.017
 writes-0.017
 pret-0.016
Token to
Token ID284
Feature activation+7.42e-03

Pos logit contributions
Jason+0.010
 asks+0.010
 meets+0.009
Ryan+0.009
Ready+0.009
Neg logit contributions
quet-0.012
comb-0.010
isy-0.009
 as-0.008
 cushion-0.008
Token draw
Token ID3197
Feature activation+8.79e-03

Pos logit contributions
quet+0.017
comb+0.014
isy+0.014
lights+0.013
ue+0.013
Neg logit contributions
 asks-0.010
 writes-0.010
 meets-0.009
 pret-0.009
Jason-0.009
Token draw
Token ID3197
Feature activation+2.28e-02

Pos logit contributions
quet+0.032
comb+0.027
isy+0.027
lights+0.025
ue+0.024
Neg logit contributions
 asks-0.022
 meets-0.021
 writes-0.021
 pret-0.020
Jason-0.019
Token and
Token ID290
Feature activation+9.43e-03

Pos logit contributions
quet+0.041
comb+0.034
isy+0.032
ue+0.029
zie+0.028
Neg logit contributions
 asks-0.040
 meets-0.039
Jason-0.038
 writes-0.038
 pret-0.037
Token shared
Token ID4888
Feature activation-5.43e-03

Pos logit contributions
quet+0.018
comb+0.015
isy+0.015
ue+0.013
zie+0.013
Neg logit contributions
 asks-0.015
 meets-0.015
Jason-0.014
 writes-0.014
 pret-0.014
Token the
Token ID262
Feature activation+2.89e-02

Pos logit contributions
 asks+0.008
 meets+0.008
Jason+0.008
 writes+0.008
 pret+0.007
Neg logit contributions
quet-0.011
comb-0.009
isy-0.009
ue-0.008
zie-0.008
Token cr
Token ID1067
Feature activation+5.77e-02

Pos logit contributions
quet+0.056
comb+0.048
isy+0.044
ue+0.041
lights+0.040
Neg logit contributions
 asks-0.046
 meets-0.046
Jason-0.044
 writes-0.044
 sees-0.042
Tokenay
Token ID323
Feature activation+9.84e-02

Pos logit contributions
comb+0.091
 surely+0.079
quet+0.077
 shade+0.068
 cushion+0.068
Neg logit contributions
us-0.087
Jason-0.084
 writes-0.083
 meets-0.079
ever-0.078
Tokenons
Token ID684
Feature activation+3.58e-02

Pos logit contributions
comb+0.244
quet+0.227
 surely+0.210
bush+0.194
zie+0.193
Neg logit contributions
 meets-0.089
 writes-0.089
Jason-0.080
 sees-0.075
 motorcycles-0.072
Token.
Token ID13
Feature activation+7.23e-03

Pos logit contributions
quet+0.078
comb+0.068
zie+0.066
isy+0.066
ue+0.064
Neg logit contributions
 meets-0.039
 asks-0.037
Jason-0.037
 writes-0.037
bers-0.035
Token They
Token ID1119
Feature activation+2.83e-02

Pos logit contributions
quet+0.015
comb+0.013
isy+0.013
ue+0.012
zie+0.012
Neg logit contributions
 asks-0.010
 meets-0.010
Jason-0.010
 writes-0.009
 pret-0.009
Token were
Token ID547
Feature activation+2.61e-02

Pos logit contributions
quet+0.062
comb+0.050
isy+0.049
ue+0.046
lights+0.045
Neg logit contributions
 asks-0.041
 meets-0.040
 writes-0.038
Jason-0.037
 pret-0.037
Token very
Token ID845
Feature activation-4.11e-04

Pos logit contributions
quet+0.059
comb+0.050
isy+0.047
ue+0.045
immer+0.043
Neg logit contributions
 meets-0.037
 asks-0.036
 met-0.034
 cheated-0.033
 sees-0.033
TokenLet
Token ID5756
Feature activation+1.08e-02

Pos logit contributions
 asks+0.033
 meets+0.031
Jason+0.029
 writes+0.029
 pret+0.028
Neg logit contributions
quet-0.059
comb-0.051
isy-0.050
ue-0.046
zie-0.045
Token's
Token ID338
Feature activation+2.10e-02

Pos logit contributions
quet+0.022
isy+0.020
ue+0.019
comb+0.018
ie+0.018
Neg logit contributions
 pret-0.015
 asks-0.015
bers-0.014
 writes-0.014
Jason-0.014
Token take
Token ID1011
Feature activation+3.40e-03

Pos logit contributions
quet+0.041
isy+0.033
comb+0.033
lights+0.031
ue+0.030
Neg logit contributions
 asks-0.035
 meets-0.032
 writes-0.031
Jason-0.030
 sees-0.029
Token the
Token ID262
Feature activation+2.60e-02

Pos logit contributions
quet+0.006
comb+0.005
isy+0.005
ue+0.005
zie+0.004
Neg logit contributions
 asks-0.006
Jason-0.005
 meets-0.005
 writes-0.005
 pret-0.005
Token tw
Token ID665
Feature activation+4.71e-02

Pos logit contributions
quet+0.046
comb+0.038
isy+0.037
ue+0.033
lights+0.033
Neg logit contributions
 asks-0.046
 meets-0.045
Jason-0.043
 writes-0.042
 pret-0.042
Tokenig
Token ID328
Feature activation+9.75e-02

Pos logit contributions
quet+0.073
comb+0.069
 Betty+0.065
 Ellie+0.063
ue+0.062
Neg logit contributions
 meets-0.073
bers-0.065
 sees-0.065
 asks-0.064
ever-0.064
Token with
Token ID351
Feature activation+1.10e-02

Pos logit contributions
quet+0.200
lights+0.175
isy+0.173
ue+0.171
comb+0.170
Neg logit contributions
 meets-0.114
 sees-0.100
 met-0.097
to-0.086
-0.086
Token us
Token ID514
Feature activation+4.36e-03

Pos logit contributions
quet+0.022
isy+0.018
comb+0.018
ue+0.016
zie+0.016
Neg logit contributions
 asks-0.017
Jason-0.016
 meets-0.016
 writes-0.016
 pret-0.015
Token on
Token ID319
Feature activation+1.23e-02

Pos logit contributions
quet+0.008
comb+0.007
isy+0.007
ue+0.006
zie+0.006
Neg logit contributions
 asks-0.007
 meets-0.007
Jason-0.007
 writes-0.007
 pret-0.006
Token all
Token ID477
Feature activation+3.44e-02

Pos logit contributions
quet+0.020
comb+0.017
isy+0.015
 as+0.014
lights+0.014
Neg logit contributions
 asks-0.023
Jason-0.022
 meets-0.022
 writes-0.021
Check-0.021
Token our
Token ID674
Feature activation-4.75e-03

Pos logit contributions
quet+0.062
comb+0.052
isy+0.049
ue+0.044
zie+0.041
Neg logit contributions
 asks-0.062
 meets-0.059
Jason-0.056
 writes-0.056
 sees-0.054
Token decide
Token ID5409
Feature activation-8.47e-03

Pos logit contributions
quet+0.054
comb+0.045
isy+0.044
ue+0.039
lights+0.038
Neg logit contributions
 asks-0.047
 meets-0.045
Jason-0.043
 writes-0.043
 pret-0.041
Token to
Token ID284
Feature activation+6.08e-03

Pos logit contributions
 asks+0.012
 meets+0.012
Jason+0.012
 writes+0.011
 pret+0.011
Neg logit contributions
quet-0.017
comb-0.015
isy-0.014
ue-0.013
lights-0.012
Token share
Token ID2648
Feature activation+1.40e-03

Pos logit contributions
quet+0.013
comb+0.012
isy+0.011
lights+0.011
zie+0.010
Neg logit contributions
 asks-0.009
 writes-0.008
 meets-0.008
 sees-0.007
 pret-0.007
Token the
Token ID262
Feature activation+2.05e-02

Pos logit contributions
quet+0.002
comb+0.002
isy+0.002
ue+0.002
lights+0.002
Neg logit contributions
 asks-0.002
 meets-0.002
Jason-0.002
Har-0.002
Ryan-0.002
Token cr
Token ID1067
Feature activation+5.64e-02

Pos logit contributions
quet+0.036
comb+0.030
isy+0.029
ue+0.026
zie+0.024
Neg logit contributions
 asks-0.037
 meets-0.036
Jason-0.035
 writes-0.034
Ryan-0.033
Tokenay
Token ID323
Feature activation+9.62e-02

Pos logit contributions
comb+0.087
quet+0.076
ishly+0.073
 Betty+0.072
 surely+0.070
Neg logit contributions
 writes-0.089
us-0.082
Jason-0.079
 meets-0.079
oly-0.078
Tokenons
Token ID684
Feature activation+4.39e-02

Pos logit contributions
comb+0.217
quet+0.211
zie+0.180
 surely+0.179
isy+0.175
Neg logit contributions
 writes-0.114
 meets-0.109
 asks-0.103
 sees-0.099
 pret-0.097
Token.
Token ID13
Feature activation-2.05e-03

Pos logit contributions
quet+0.108
comb+0.096
isy+0.093
zie+0.093
ue+0.088
Neg logit contributions
 asks-0.041
 meets-0.039
 writes-0.038
 sees-0.036
bers-0.036
Token They
Token ID1119
Feature activation+2.53e-02

Pos logit contributions
Jason+0.004
 meets+0.003
Har+0.003
 pret+0.003
 asks+0.003
Neg logit contributions
quet-0.003
ue-0.003
comb-0.002
lights-0.002
 shade-0.002
Token color
Token ID3124
Feature activation-1.03e-02

Pos logit contributions
quet+0.050
comb+0.042
isy+0.041
ue+0.036
zie+0.036
Neg logit contributions
 asks-0.041
 meets-0.039
 writes-0.038
Jason-0.038
 pret-0.036
Token the
Token ID262
Feature activation-1.43e-02

Pos logit contributions
 asks+0.014
 writes+0.014
 meets+0.013
 pret+0.013
 sees+0.013
Neg logit contributions
quet-0.023
comb-0.020
isy-0.019
zie-0.017
ue-0.017
Token.
Token ID13
Feature activation-2.62e-03

Pos logit contributions
quet+0.042
comb+0.035
isy+0.034
zie+0.033
lights+0.033
Neg logit contributions
 asks-0.027
 writes-0.025
 pret-0.024
 meets-0.024
 yells-0.022
Token She
Token ID1375
Feature activation+1.08e-02

Pos logit contributions
Jason+0.005
 meets+0.005
 wre+0.005
 pret+0.005
 risking+0.005
Neg logit contributions
quet-0.003
ue-0.002
comb-0.002
isy-0.002
zie-0.002
Token takes
Token ID2753
Feature activation+3.32e-03

Pos logit contributions
quet+0.020
isy+0.019
ue+0.018
comb+0.018
 cushion+0.018
Neg logit contributions
Jason-0.013
Ryan-0.013
bers-0.012
Simon-0.012
Har-0.012
Token a
Token ID257
Feature activation+1.24e-02

Pos logit contributions
quet+0.007
comb+0.006
isy+0.006
ue+0.005
zie+0.005
Neg logit contributions
 asks-0.005
 meets-0.005
 writes-0.005
Jason-0.005
 pret-0.005
Token cr
Token ID1067
Feature activation+5.16e-02

Pos logit contributions
quet+0.020
isy+0.017
comb+0.016
ue+0.014
 ray+0.013
Neg logit contributions
 asks-0.024
 meets-0.023
Jason-0.022
 writes-0.021
Ryan-0.021
Tokenay
Token ID323
Feature activation+9.59e-02

Pos logit contributions
quet+0.078
comb+0.076
isy+0.067
zie+0.063
 Betty+0.061
Neg logit contributions
 writes-0.087
Jason-0.085
Daniel-0.081
us-0.080
 asks-0.079
Tokenon
Token ID261
Feature activation+3.74e-02

Pos logit contributions
quet+0.190
comb+0.178
zie+0.151
lights+0.151
isy+0.149
Neg logit contributions
 writes-0.144
 asks-0.139
Jason-0.139
 meets-0.135
 pret-0.127
Token and
Token ID290
Feature activation+8.35e-03

Pos logit contributions
quet+0.082
zie+0.072
isy+0.070
lights+0.069
ue+0.069
Neg logit contributions
 writes-0.044
 asks-0.042
 pret-0.037
 St-0.037
 sees-0.037
Token writes
Token ID6797
Feature activation-9.03e-03

Pos logit contributions
quet+0.015
comb+0.013
 as+0.013
isy+0.012
 shade+0.012
Neg logit contributions
Ryan-0.012
Jason-0.012
 meets-0.011
Har-0.011
Simon-0.011
Token on
Token ID319
Feature activation+7.58e-03

Pos logit contributions
 asks+0.014
 meets+0.013
Jason+0.013
 writes+0.013
 pret+0.012
Neg logit contributions
quet-0.018
comb-0.015
isy-0.015
ue-0.014
zie-0.013
Token the
Token ID262
Feature activation+7.89e-04

Pos logit contributions
quet+0.015
comb+0.013
isy+0.012
ue+0.011
zie+0.011
Neg logit contributions
 asks-0.012
 meets-0.012
Jason-0.011
 writes-0.011
 pret-0.011
Token,
Token ID11
Feature activation+1.29e-02

Pos logit contributions
quet+0.026
comb+0.022
isy+0.021
immer+0.019
lights+0.018
Neg logit contributions
 asks-0.014
 sees-0.013
 wants-0.012
 met-0.011
-0.011
Token he
Token ID339
Feature activation-3.78e-02

Pos logit contributions
quet+0.035
comb+0.031
isy+0.030
immer+0.027
zie+0.027
Neg logit contributions
 asks-0.013
 motorcycles-0.011
 meets-0.010
 Whe-0.010
 sees-0.010
Token took
Token ID1718
Feature activation+9.94e-03

Pos logit contributions
Jason+0.050
 meets+0.050
 asks+0.050
Ryan+0.046
Har+0.045
Neg logit contributions
quet-0.079
comb-0.068
isy-0.068
ue-0.061
ie-0.059
Token the
Token ID262
Feature activation+2.47e-02

Pos logit contributions
quet+0.020
comb+0.017
isy+0.016
ue+0.015
zie+0.014
Neg logit contributions
 asks-0.016
 meets-0.015
Jason-0.015
 writes-0.014
 pret-0.014
Token cr
Token ID1067
Feature activation+6.07e-02

Pos logit contributions
quet+0.054
comb+0.047
isy+0.044
ue+0.041
zie+0.040
Neg logit contributions
 asks-0.034
 meets-0.033
 writes-0.032
Jason-0.031
 pret-0.030
Tokenay
Token ID323
Feature activation+9.57e-02

Pos logit contributions
comb+0.105
quet+0.093
isy+0.085
 surely+0.083
zie+0.082
Neg logit contributions
 writes-0.090
Jason-0.084
us-0.081
Ryan-0.079
 meets-0.079
Tokenons
Token ID684
Feature activation+4.60e-02

Pos logit contributions
comb+0.214
quet+0.212
isy+0.177
zie+0.170
 surely+0.168
Neg logit contributions
 writes-0.116
 meets-0.115
 asks-0.112
Jason-0.104
 sees-0.103
Token and
Token ID290
Feature activation+4.60e-03

Pos logit contributions
quet+0.113
isy+0.098
comb+0.096
ue+0.093
lights+0.090
Neg logit contributions
 asks-0.047
 meets-0.044
 writes-0.043
 sees-0.042
Jason-0.041
Token some
Token ID617
Feature activation+1.02e-02

Pos logit contributions
quet+0.010
comb+0.009
isy+0.008
ue+0.008
zie+0.007
Neg logit contributions
 asks-0.007
 meets-0.006
 writes-0.006
Jason-0.006
 pret-0.006
Token paper
Token ID3348
Feature activation-2.44e-02

Pos logit contributions
quet+0.020
comb+0.016
isy+0.016
ue+0.014
lights+0.014
Neg logit contributions
 asks-0.017
 meets-0.016
Jason-0.016
Ryan-0.015
 writes-0.015
Token and
Token ID290
Feature activation-2.30e-03

Pos logit contributions
 asks+0.035
 writes+0.033
 meets+0.033
 pret+0.030
 sees+0.030
Neg logit contributions
quet-0.052
comb-0.045
isy-0.044
ue-0.041
zie-0.040
Token They
Token ID1119
Feature activation+2.62e-02

Pos logit contributions
quet+0.005
comb+0.004
ue+0.004
isy+0.004
zie+0.003
Neg logit contributions
 asks-0.004
 meets-0.004
Jason-0.004
 writes-0.004
 pret-0.004
Token all
Token ID477
Feature activation+2.27e-02

Pos logit contributions
quet+0.049
comb+0.040
isy+0.038
ue+0.037
lights+0.034
Neg logit contributions
 asks-0.045
 meets-0.043
 writes-0.042
Jason-0.041
 met-0.041
Token shared
Token ID4888
Feature activation+7.30e-03

Pos logit contributions
quet+0.050
comb+0.043
isy+0.041
ue+0.038
zie+0.036
Neg logit contributions
 asks-0.032
 meets-0.030
 writes-0.029
Jason-0.029
 pret-0.027
Token the
Token ID262
Feature activation+3.11e-02

Pos logit contributions
quet+0.013
comb+0.011
isy+0.010
ue+0.009
lights+0.009
Neg logit contributions
 asks-0.013
 meets-0.012
Jason-0.012
 writes-0.012
 pret-0.011
Token tw
Token ID665
Feature activation+3.97e-02

Pos logit contributions
quet+0.056
comb+0.047
isy+0.045
ue+0.040
zie+0.038
Neg logit contributions
 asks-0.055
 meets-0.053
Jason-0.052
 writes-0.050
 pret-0.049
Tokenig
Token ID328
Feature activation+9.47e-02

Pos logit contributions
quet+0.070
comb+0.064
ue+0.054
isy+0.053
 Betty+0.051
Neg logit contributions
 meets-0.061
 asks-0.060
 pret-0.058
 writes-0.057
bers-0.057
Token and
Token ID290
Feature activation+1.49e-02

Pos logit contributions
quet+0.179
comb+0.157
ue+0.140
isy+0.140
 ray+0.133
Neg logit contributions
 meets-0.129
bers-0.116
 sees-0.113
Jason-0.112
 met-0.110
Token played
Token ID2826
Feature activation+1.99e-02

Pos logit contributions
quet+0.030
comb+0.025
isy+0.024
ue+0.022
zie+0.021
Neg logit contributions
 asks-0.023
 meets-0.022
Jason-0.022
 writes-0.021
 pret-0.021
Token games
Token ID1830
Feature activation+1.25e-02

Pos logit contributions
quet+0.033
comb+0.027
isy+0.025
ue+0.022
zie+0.021
Neg logit contributions
 asks-0.039
 meets-0.037
Jason-0.037
 writes-0.036
 yells-0.035
Token.
Token ID13
Feature activation+3.77e-04

Pos logit contributions
quet+0.023
comb+0.020
isy+0.019
ue+0.018
zie+0.017
Neg logit contributions
 asks-0.020
 meets-0.020
Jason-0.019
 writes-0.019
 pret-0.018
Token The
Token ID383
Feature activation+1.23e-02

Pos logit contributions
quet+0.001
comb+0.001
isy+0.001
ue+0.001
zie+0.001
Neg logit contributions
 asks-0.001
 meets-0.001
Jason-0.001
 writes-0.001
 pret-0.001
Token.
Token ID13
Feature activation-2.09e-03

Pos logit contributions
quet+0.082
comb+0.072
isy+0.070
zie+0.064
ue+0.064
Neg logit contributions
 asks-0.078
 writes-0.077
 meets-0.076
 pret-0.072
Jason-0.072
Token They
Token ID1119
Feature activation+2.85e-02

Pos logit contributions
 pret+0.003
 kidn+0.003
 risking+0.003
Jason+0.003
 meets+0.003
Neg logit contributions
quet-0.003
ue-0.003
zie-0.003
comb-0.003
ill-0.003
Token grabbed
Token ID13176
Feature activation+5.17e-03

Pos logit contributions
quet+0.060
comb+0.051
isy+0.049
ue+0.045
zie+0.043
Neg logit contributions
 asks-0.042
 meets-0.040
Jason-0.039
 writes-0.038
 pret-0.037
Token the
Token ID262
Feature activation+2.08e-02

Pos logit contributions
quet+0.011
comb+0.010
isy+0.009
ue+0.008
zie+0.008
Neg logit contributions
 asks-0.008
 meets-0.007
 writes-0.007
Jason-0.007
 pret-0.007
Token cr
Token ID1067
Feature activation+6.18e-02

Pos logit contributions
quet+0.040
comb+0.034
isy+0.032
ue+0.030
zie+0.029
Neg logit contributions
 asks-0.033
 meets-0.032
 writes-0.031
Jason-0.031
 sees-0.030
Tokenay
Token ID323
Feature activation+9.46e-02

Pos logit contributions
comb+0.097
quet+0.093
isy+0.083
 Betty+0.082
 shade+0.079
Neg logit contributions
 writes-0.092
Jason-0.090
Daniel-0.084
us-0.082
asper-0.081
Tokenons
Token ID684
Feature activation+4.52e-02

Pos logit contributions
quet+0.211
comb+0.209
isy+0.180
zie+0.173
 surely+0.168
Neg logit contributions
 writes-0.106
Jason-0.096
 meets-0.095
 asks-0.089
 motorcycles-0.088
Token and
Token ID290
Feature activation+8.25e-03

Pos logit contributions
quet+0.095
isy+0.081
comb+0.078
ue+0.077
zie+0.076
Neg logit contributions
 asks-0.055
Jason-0.054
 writes-0.051
 Daniel-0.050
 sees-0.050
Token markers
Token ID19736
Feature activation-5.57e-03

Pos logit contributions
quet+0.016
comb+0.014
isy+0.013
ue+0.012
zie+0.012
Neg logit contributions
 asks-0.013
 meets-0.012
Jason-0.012
 writes-0.011
 pret-0.011
Token and
Token ID290
Feature activation+4.22e-03

Pos logit contributions
 asks+0.009
 meets+0.009
Jason+0.009
 writes+0.009
 pret+0.009
Neg logit contributions
quet-0.010
comb-0.008
isy-0.008
ue-0.007
zie-0.007
Token started
Token ID2067
Feature activation-9.84e-03

Pos logit contributions
quet+0.008
comb+0.007
isy+0.007
ue+0.006
zie+0.006
Neg logit contributions
 asks-0.006
 meets-0.006
Jason-0.006
 writes-0.006
 pret-0.006
Token would
Token ID561
Feature activation-2.33e-02

Pos logit contributions
 asks+0.050
Jason+0.049
 meets+0.048
 yells+0.047
Ryan+0.047
Neg logit contributions
quet-0.063
comb-0.056
isy-0.053
ue-0.047
zie-0.047
Token take
Token ID1011
Feature activation+6.64e-03

Pos logit contributions
 asks+0.038
 writes+0.035
 meets+0.035
 pret+0.034
Jason+0.033
Neg logit contributions
quet-0.047
isy-0.039
comb-0.038
lights-0.036
ue-0.035
Token out
Token ID503
Feature activation+2.07e-04

Pos logit contributions
quet+0.012
comb+0.010
isy+0.010
ue+0.009
lights+0.008
Neg logit contributions
 asks-0.011
Jason-0.011
 meets-0.011
 writes-0.010
 yells-0.010
Token a
Token ID257
Feature activation+6.90e-03

Pos logit contributions
quet+0.000
comb+0.000
isy+0.000
ue+0.000
zie+0.000
Neg logit contributions
 asks-0.000
 meets-0.000
Jason-0.000
 writes-0.000
 pret-0.000
Token j
Token ID474
Feature activation+4.98e-02

Pos logit contributions
quet+0.014
comb+0.011
isy+0.011
ue+0.010
zie+0.010
Neg logit contributions
 asks-0.011
 meets-0.011
Jason-0.010
 writes-0.010
 pret-0.010
Tokenigsaw
Token ID45636
Feature activation+9.46e-02

Pos logit contributions
quet+0.092
comb+0.088
isy+0.074
flower+0.074
zie+0.067
Neg logit contributions
 asks-0.074
bers-0.072
 meets-0.071
Jason-0.069
 trips-0.068
Token puzzle
Token ID15027
Feature activation+3.94e-02

Pos logit contributions
quet+0.199
comb+0.188
zie+0.173
isy+0.171
ue+0.165
Neg logit contributions
 asks-0.109
 writes-0.109
 meets-0.104
 pret-0.104
 sees-0.103
Token and
Token ID290
Feature activation+4.10e-03

Pos logit contributions
quet+0.078
comb+0.067
isy+0.066
ue+0.062
zie+0.062
Neg logit contributions
 asks-0.058
 meets-0.055
 writes-0.055
Jason-0.053
 pret-0.052
Token try
Token ID1949
Feature activation-2.18e-02

Pos logit contributions
quet+0.008
comb+0.006
isy+0.006
ue+0.005
zie+0.005
Neg logit contributions
 asks-0.007
 meets-0.007
Jason-0.007
 writes-0.006
 pret-0.006
Token to
Token ID284
Feature activation+1.94e-02

Pos logit contributions
 asks+0.038
Jason+0.037
 meets+0.036
Ryan+0.035
 yells+0.034
Neg logit contributions
quet-0.037
isy-0.030
comb-0.030
ue-0.026
 as-0.025
Token solve
Token ID8494
Feature activation-1.89e-02

Pos logit contributions
quet+0.039
comb+0.033
isy+0.032
lights+0.030
zie+0.030
Neg logit contributions
 asks-0.030
 meets-0.028
 writes-0.028
Jason-0.027
 pret-0.026
Token Here
Token ID3423
Feature activation-2.63e-02

Pos logit contributions
quet+0.009
comb+0.008
isy+0.008
ue+0.007
zie+0.007
Neg logit contributions
 asks-0.004
 meets-0.004
Jason-0.004
 writes-0.004
 pret-0.004
Token,
Token ID11
Feature activation+8.87e-03

Pos logit contributions
Jason+0.057
Ryan+0.054
 meets+0.054
Simon+0.054
bers+0.053
Neg logit contributions
quet-0.033
isy-0.025
ue-0.025
comb-0.025
ie-0.021
Token take
Token ID1011
Feature activation-1.86e-03

Pos logit contributions
quet+0.017
comb+0.014
isy+0.014
ue+0.013
ie+0.012
Neg logit contributions
Jason-0.014
 meets-0.014
 asks-0.014
 writes-0.013
 yells-0.013
Token a
Token ID257
Feature activation+2.46e-03

Pos logit contributions
Jason+0.003
 asks+0.003
 meets+0.003
Har+0.003
 loudspe+0.003
Neg logit contributions
quet-0.003
isy-0.003
comb-0.003
ue-0.002
zie-0.002
Token cr
Token ID1067
Feature activation+4.77e-02

Pos logit contributions
quet+0.004
comb+0.004
isy+0.004
ue+0.003
zie+0.003
Neg logit contributions
 asks-0.004
 meets-0.004
Jason-0.004
 writes-0.004
 pret-0.004
Tokenay
Token ID323
Feature activation+9.44e-02

Pos logit contributions
comb+0.065
quet+0.064
isy+0.052
zie+0.051
 Betty+0.050
Neg logit contributions
 writes-0.089
Jason-0.086
 asks-0.085
 meets-0.082
Ryan-0.082
Tokenon
Token ID261
Feature activation+3.91e-02

Pos logit contributions
quet+0.182
comb+0.176
isy+0.147
zie+0.146
lights+0.145
Neg logit contributions
 writes-0.143
 asks-0.142
 meets-0.140
Jason-0.135
 sees-0.128
Token."
Token ID526
Feature activation-1.41e-03

Pos logit contributions
quet+0.082
comb+0.072
isy+0.070
zie+0.069
ue+0.067
Neg logit contributions
 asks-0.050
 writes-0.047
 meets-0.046
 pret-0.044
 sees-0.042
Token
Token ID198
Feature activation-5.42e-03

Pos logit contributions
 meets+0.002
Jason+0.002
 asks+0.002
 wre+0.002
 pret+0.002
Neg logit contributions
quet-0.003
comb-0.002
ue-0.002
isy-0.002
 Betty-0.002
Token
Token ID198
Feature activation+3.23e-03

Pos logit contributions
 pret+0.009
 meets+0.009
 asks+0.009
 cheated+0.008
 jury+0.008
Neg logit contributions
quet-0.009
isy-0.008
ue-0.008
comb-0.007
 of-0.007
TokenThey
Token ID2990
Feature activation+3.15e-02

Pos logit contributions
quet+0.007
comb+0.005
isy+0.005
ue+0.005
 cushion+0.004
Neg logit contributions
 asks-0.005
 meets-0.005
 pret-0.004
 writes-0.004
 yells-0.004
Token.
Token ID13
Feature activation+9.79e-03

Pos logit contributions
quet+0.038
comb+0.032
isy+0.031
ue+0.029
zie+0.028
Neg logit contributions
 asks-0.031
 meets-0.030
Jason-0.029
 writes-0.028
 pret-0.027
Token They
Token ID1119
Feature activation+3.17e-02

Pos logit contributions
quet+0.016
ue+0.014
comb+0.013
lights+0.012
zie+0.012
Neg logit contributions
 asks-0.016
 meets-0.015
Jason-0.015
 wre-0.015
 met-0.015
Token had
Token ID550
Feature activation+1.03e-02

Pos logit contributions
quet+0.065
comb+0.055
isy+0.053
ue+0.049
zie+0.047
Neg logit contributions
 asks-0.048
 meets-0.046
Jason-0.045
 writes-0.044
 pret-0.042
Token shared
Token ID4888
Feature activation+1.12e-02

Pos logit contributions
quet+0.018
comb+0.015
isy+0.015
ue+0.014
zie+0.013
Neg logit contributions
 asks-0.018
 pret-0.016
 meets-0.016
Jason-0.016
 yells-0.016
Token a
Token ID257
Feature activation+3.13e-02

Pos logit contributions
quet+0.022
comb+0.018
isy+0.017
ue+0.016
lights+0.015
Neg logit contributions
 asks-0.018
 meets-0.017
Jason-0.017
 writes-0.016
 pret-0.016
Token lot
Token ID1256
Feature activation+9.42e-02

Pos logit contributions
quet+0.066
comb+0.060
zie+0.055
isy+0.053
lights+0.052
Neg logit contributions
Jason-0.041
 meets-0.040
 writes-0.040
 sees-0.039
 asks-0.039
Token and
Token ID290
Feature activation+2.55e-02

Pos logit contributions
quet+0.134
comb+0.126
zie+0.106
isy+0.100
flower+0.097
Neg logit contributions
 meets-0.174
 asks-0.171
bers-0.167
 writes-0.165
Ryan-0.164
Token learned
Token ID4499
Feature activation+3.02e-02

Pos logit contributions
quet+0.048
comb+0.040
isy+0.039
ue+0.035
zie+0.034
Neg logit contributions
 asks-0.042
Jason-0.040
 meets-0.039
 writes-0.037
Har-0.036
Token so
Token ID523
Feature activation+6.32e-03

Pos logit contributions
quet+0.047
comb+0.037
isy+0.036
ue+0.031
lights+0.031
Neg logit contributions
 asks-0.059
 meets-0.058
Jason-0.057
 writes-0.054
 pret-0.054
Token much
Token ID881
Feature activation+2.22e-02

Pos logit contributions
quet+0.011
comb+0.009
isy+0.008
zie+0.008
ue+0.008
Neg logit contributions
 asks-0.012
 meets-0.011
Jason-0.011
 writes-0.011
 pret-0.010
Token.
Token ID13
Feature activation+9.70e-03

Pos logit contributions
quet+0.039
comb+0.035
isy+0.031
zie+0.031
ue+0.029
Neg logit contributions
 asks-0.039
 meets-0.036
 writes-0.036
Jason-0.035
 pret-0.035
Token The
Token ID383
Feature activation+1.08e-02

Pos logit contributions
quet+0.006
comb+0.005
isy+0.004
ue+0.004
zie+0.004
Neg logit contributions
Jason-0.005
 meets-0.005
 asks-0.005
Ryan-0.005
 writes-0.005
Token bird
Token ID6512
Feature activation+1.99e-02

Pos logit contributions
quet+0.020
comb+0.017
isy+0.015
lights+0.015
ue+0.014
Neg logit contributions
 asks-0.019
 meets-0.018
 sees-0.017
 pret-0.017
 writes-0.017
Token threw
Token ID9617
Feature activation+9.53e-03

Pos logit contributions
quet+0.051
comb+0.044
isy+0.040
ue+0.039
lights+0.038
Neg logit contributions
 asks-0.023
 meets-0.022
 met-0.020
 sees-0.020
 writes-0.020
Token the
Token ID262
Feature activation+3.15e-02

Pos logit contributions
quet+0.020
comb+0.017
isy+0.017
ue+0.015
zie+0.015
Neg logit contributions
 asks-0.014
 meets-0.014
 writes-0.013
 pret-0.013
Jason-0.013
Token tw
Token ID665
Feature activation+3.87e-02

Pos logit contributions
quet+0.066
comb+0.057
isy+0.053
ue+0.052
lights+0.049
Neg logit contributions
 asks-0.046
 meets-0.044
 pret-0.042
Jason-0.042
 writes-0.041
Tokenig
Token ID328
Feature activation+9.40e-02

Pos logit contributions
quet+0.065
comb+0.058
ue+0.051
 Betty+0.050
isy+0.048
Neg logit contributions
 asks-0.064
 meets-0.063
 pret-0.062
bers-0.060
 sees-0.060
Token up
Token ID510
Feature activation+5.04e-03

Pos logit contributions
quet+0.247
ue+0.210
comb+0.209
umm+0.203
zie+0.197
Neg logit contributions
 sees-0.064
 meets-0.061
 met-0.060
 scored-0.053
to-0.050
Token in
Token ID287
Feature activation-3.54e-03

Pos logit contributions
quet+0.012
comb+0.010
isy+0.010
ue+0.009
zie+0.009
Neg logit contributions
 asks-0.006
 sees-0.006
 meets-0.006
 pret-0.006
bers-0.005
Token the
Token ID262
Feature activation-5.91e-03

Pos logit contributions
 asks+0.005
 meets+0.005
Jason+0.004
 writes+0.004
 pret+0.004
Neg logit contributions
quet-0.008
comb-0.007
isy-0.007
ue-0.006
zie-0.006
Token air
Token ID1633
Feature activation+1.11e-02

Pos logit contributions
 asks+0.010
 meets+0.010
 writes+0.009
Jason+0.009
 sees+0.009
Neg logit contributions
quet-0.011
comb-0.010
isy-0.009
ue-0.008
lights-0.008
Token and
Token ID290
Feature activation+3.50e-03

Pos logit contributions
quet+0.020
comb+0.016
isy+0.016
ue+0.014
zie+0.014
Neg logit contributions
 asks-0.020
 meets-0.019
 writes-0.018
Jason-0.018
 pret-0.018
Token Todd
Token ID14377
Feature activation-2.69e-02

Pos logit contributions
Ryan+0.017
Jason+0.017
Check+0.017
 meets+0.017
 pret+0.016
Neg logit contributions
quet-0.018
comb-0.017
ue-0.015
zie-0.014
isy-0.014
Token took
Token ID1718
Feature activation+1.37e-02

Pos logit contributions
 asks+0.042
 meets+0.041
Jason+0.040
 writes+0.039
 pret+0.038
Neg logit contributions
quet-0.053
comb-0.045
isy-0.044
ue-0.040
zie-0.038
Token off
Token ID572
Feature activation+2.13e-02

Pos logit contributions
quet+0.027
comb+0.023
isy+0.022
ue+0.020
zie+0.019
Neg logit contributions
 asks-0.022
 meets-0.021
Jason-0.020
 writes-0.020
 pret-0.019
Token the
Token ID262
Feature activation+2.89e-02

Pos logit contributions
quet+0.051
comb+0.046
isy+0.045
ue+0.040
zie+0.040
Neg logit contributions
 asks-0.025
 meets-0.023
Jason-0.023
 writes-0.022
 pret-0.022
Token m
Token ID285
Feature activation+4.35e-02

Pos logit contributions
quet+0.052
isy+0.042
comb+0.042
ue+0.037
zie+0.037
Neg logit contributions
 asks-0.050
Jason-0.049
 meets-0.049
 writes-0.048
Ryan-0.045
Tokenittens
Token ID34978
Feature activation+9.30e-02

Pos logit contributions
quet+0.074
comb+0.063
isy+0.059
ue+0.051
zie+0.049
Neg logit contributions
 asks-0.079
 meets-0.075
 yells-0.072
bers-0.072
Jason-0.071
Token,
Token ID11
Feature activation+6.66e-03

Pos logit contributions
quet+0.185
isy+0.153
comb+0.150
ue+0.141
zie+0.135
Neg logit contributions
 asks-0.135
 meets-0.131
 yells-0.126
Jason-0.125
 Daniel-0.122
Token put
Token ID1234
Feature activation+9.75e-03

Pos logit contributions
quet+0.013
comb+0.011
isy+0.010
ue+0.009
zie+0.009
Neg logit contributions
 asks-0.011
 meets-0.011
Jason-0.010
 writes-0.010
 pret-0.010
Token them
Token ID606
Feature activation+3.38e-02

Pos logit contributions
quet+0.020
comb+0.017
isy+0.016
ue+0.015
zie+0.014
Neg logit contributions
 asks-0.015
 meets-0.014
Jason-0.014
 writes-0.014
 pret-0.013
Token under
Token ID739
Feature activation-9.75e-03

Pos logit contributions
quet+0.069
isy+0.059
comb+0.059
ue+0.054
zie+0.051
Neg logit contributions
 asks-0.048
 meets-0.048
Jason-0.046
 pret-0.044
 writes-0.044
Token the
Token ID262
Feature activation-2.31e-03

Pos logit contributions
 asks+0.019
 meets+0.018
Jason+0.018
 writes+0.017
Ryan+0.016
Neg logit contributions
quet-0.015
comb-0.013
isy-0.012
 as-0.011
 shade-0.011
Token.
Token ID13
Feature activation+7.69e-03

Pos logit contributions
 asks+0.036
 meets+0.034
Jason+0.033
 writes+0.033
 pret+0.032
Neg logit contributions
quet-0.047
comb-0.040
isy-0.038
ue-0.035
zie-0.034
Token He
Token ID679
Feature activation-5.70e-03

Pos logit contributions
quet+0.015
comb+0.013
isy+0.013
ue+0.012
lights+0.011
Neg logit contributions
 meets-0.012
Jason-0.011
 asks-0.011
Har-0.010
Ryan-0.010
Token takes
Token ID2753
Feature activation+4.84e-03

Pos logit contributions
Jason+0.007
Ryan+0.007
Har+0.007
Simon+0.006
 Ethan+0.006
Neg logit contributions
quet-0.011
comb-0.010
isy-0.010
 cushion-0.010
ue-0.009
Token a
Token ID257
Feature activation+1.24e-02

Pos logit contributions
quet+0.009
comb+0.007
isy+0.007
ue+0.006
zie+0.006
Neg logit contributions
 asks-0.008
Jason-0.008
 meets-0.008
 writes-0.008
Ryan-0.008
Token cr
Token ID1067
Feature activation+5.18e-02

Pos logit contributions
quet+0.021
isy+0.017
comb+0.017
ue+0.014
 ray+0.013
Neg logit contributions
 asks-0.023
 meets-0.023
Jason-0.022
 writes-0.021
Ryan-0.021
Tokenay
Token ID323
Feature activation+9.26e-02

Pos logit contributions
quet+0.072
comb+0.064
zie+0.053
lights+0.053
isy+0.053
Neg logit contributions
Jason-0.096
 writes-0.094
 asks-0.091
Marco-0.091
Daniel-0.090
Tokenon
Token ID261
Feature activation+3.81e-02

Pos logit contributions
quet+0.184
comb+0.168
lights+0.151
zie+0.146
ue+0.141
Neg logit contributions
 writes-0.132
 asks-0.132
Jason-0.130
 meets-0.127
 pret-0.119
Token and
Token ID290
Feature activation+7.37e-03

Pos logit contributions
quet+0.083
zie+0.072
ue+0.070
isy+0.069
comb+0.067
Neg logit contributions
 asks-0.045
 writes-0.043
 sees-0.040
 br-0.039
 meets-0.039
Token tries
Token ID8404
Feature activation+4.64e-03

Pos logit contributions
quet+0.015
comb+0.014
isy+0.013
 shade+0.012
ue+0.012
Neg logit contributions
Jason-0.009
Ryan-0.009
Har-0.009
 meets-0.009
Simon-0.008
Token to
Token ID284
Feature activation+1.31e-02

Pos logit contributions
quet+0.008
comb+0.007
isy+0.007
ue+0.006
 shade+0.006
Neg logit contributions
Jason-0.007
 asks-0.007
 meets-0.007
Ryan-0.007
Har-0.007
Token mark
Token ID1317
Feature activation-2.28e-02

Pos logit contributions
quet+0.029
comb+0.025
isy+0.023
lights+0.023
ue+0.022
Neg logit contributions
 asks-0.019
 writes-0.017
 meets-0.017
 pret-0.016
Jason-0.016
Token.
Token ID13
Feature activation+1.59e-02

Pos logit contributions
quet+0.013
comb+0.011
isy+0.010
ue+0.010
zie+0.009
Neg logit contributions
 asks-0.009
 meets-0.009
Jason-0.009
 writes-0.008
 pret-0.008
Token He
Token ID679
Feature activation+3.88e-04

Pos logit contributions
quet+0.025
comb+0.020
isy+0.019
ue+0.018
 Sue+0.018
Neg logit contributions
 meets-0.029
Jason-0.028
 writes-0.026
Ryan-0.026
Har-0.026
Token took
Token ID1718
Feature activation+9.24e-03

Pos logit contributions
quet+0.001
comb+0.001
isy+0.001
ue+0.001
zie+0.001
Neg logit contributions
 asks-0.001
Jason-0.001
 meets-0.001
Ryan-0.001
 writes-0.001
Token a
Token ID257
Feature activation+1.67e-02

Pos logit contributions
quet+0.016
comb+0.013
isy+0.013
ue+0.012
zie+0.011
Neg logit contributions
 asks-0.016
Jason-0.016
 meets-0.015
 writes-0.015
Ryan-0.014
Token cr
Token ID1067
Feature activation+5.00e-02

Pos logit contributions
quet+0.029
comb+0.024
isy+0.023
ue+0.020
zie+0.019
Neg logit contributions
 asks-0.031
 meets-0.030
Jason-0.029
 writes-0.028
 pret-0.027
Tokenay
Token ID323
Feature activation+9.25e-02

Pos logit contributions
quet+0.069
comb+0.066
isy+0.053
zie+0.052
 surely+0.051
Neg logit contributions
Jason-0.090
 writes-0.089
Daniel-0.086
Marco-0.086
us-0.085
Tokenon
Token ID261
Feature activation+4.33e-02

Pos logit contributions
quet+0.174
comb+0.159
lights+0.138
isy+0.134
zie+0.133
Neg logit contributions
 asks-0.145
 writes-0.143
Jason-0.142
 meets-0.142
 yells-0.133
Token and
Token ID290
Feature activation+7.43e-03

Pos logit contributions
quet+0.086
zie+0.075
isy+0.072
ue+0.072
comb+0.072
Neg logit contributions
 asks-0.055
 writes-0.054
 sees-0.050
 yells-0.049
 br-0.049
Token drew
Token ID9859
Feature activation+1.28e-02

Pos logit contributions
quet+0.013
comb+0.011
isy+0.010
 as+0.009
ue+0.009
Neg logit contributions
Jason-0.012
 meets-0.012
Ryan-0.012
 asks-0.011
Har-0.011
Token something
Token ID1223
Feature activation-1.19e-02

Pos logit contributions
quet+0.024
comb+0.020
isy+0.020
ue+0.017
lights+0.017
Neg logit contributions
 asks-0.021
 meets-0.021
Jason-0.020
 writes-0.019
 pret-0.019
Token on
Token ID319
Feature activation+1.90e-02

Pos logit contributions
 asks+0.021
 meets+0.020
Jason+0.020
 writes+0.019
 pret+0.019
Neg logit contributions
quet-0.021
comb-0.018
isy-0.017
ue-0.015
zie-0.015
Token laughed
Token ID13818
Feature activation+1.40e-02

Pos logit contributions
quet+0.012
comb+0.010
isy+0.010
ue+0.009
zie+0.009
Neg logit contributions
 asks-0.009
 meets-0.008
Jason-0.008
 writes-0.008
 pret-0.008
Token and
Token ID290
Feature activation+1.06e-02

Pos logit contributions
quet+0.027
comb+0.023
isy+0.022
ue+0.021
zie+0.020
Neg logit contributions
 asks-0.022
 writes-0.021
 meets-0.021
Jason-0.021
 pret-0.021
Token shared
Token ID4888
Feature activation-5.68e-03

Pos logit contributions
quet+0.022
comb+0.019
isy+0.018
ue+0.017
zie+0.016
Neg logit contributions
 asks-0.016
 meets-0.015
Jason-0.015
 writes-0.014
 pret-0.014
Token the
Token ID262
Feature activation+2.52e-02

Pos logit contributions
 asks+0.009
 meets+0.008
Jason+0.008
 writes+0.008
 pret+0.008
Neg logit contributions
quet-0.011
comb-0.010
isy-0.009
ue-0.009
zie-0.008
Token cr
Token ID1067
Feature activation+5.33e-02

Pos logit contributions
quet+0.052
comb+0.044
isy+0.040
lights+0.039
ue+0.038
Neg logit contributions
 meets-0.037
 asks-0.037
 writes-0.036
 sees-0.035
 pret-0.035
Tokenay
Token ID323
Feature activation+9.25e-02

Pos logit contributions
comb+0.082
quet+0.073
 surely+0.071
 shade+0.064
 quake+0.062
Neg logit contributions
us-0.084
Jason-0.080
 writes-0.080
asper-0.074
oly-0.074
Tokenons
Token ID684
Feature activation+3.28e-02

Pos logit contributions
comb+0.216
quet+0.210
 surely+0.184
zie+0.173
isy+0.173
Neg logit contributions
 writes-0.096
 meets-0.093
Jason-0.088
 asks-0.082
us-0.081
Token.
Token ID13
Feature activation-7.78e-03

Pos logit contributions
quet+0.076
comb+0.068
zie+0.068
isy+0.066
ue+0.064
Neg logit contributions
 meets-0.028
 writes-0.028
 asks-0.027
bers-0.026
Jason-0.026
Token
Token ID220
Feature activation-1.37e-02

Pos logit contributions
Jason+0.012
 asks+0.012
 meets+0.012
 writes+0.011
 pret+0.011
Neg logit contributions
quet-0.014
comb-0.012
ue-0.012
isy-0.011
zie-0.011
Token
Token ID198
Feature activation-2.69e-03

Pos logit contributions
 pret+0.021
 asks+0.021
 writes+0.020
 meets+0.020
Jason+0.019
Neg logit contributions
quet-0.025
ue-0.021
isy-0.021
comb-0.020
zie-0.019
Token
Token ID198
Feature activation+9.75e-03

Pos logit contributions
 writes+0.004
 asks+0.004
 pret+0.004
 meets+0.004
 jury+0.004
Neg logit contributions
quet-0.005
isy-0.004
ue-0.004
comb-0.004
zie-0.003
Token."
Token ID526
Feature activation-7.99e-03

Pos logit contributions
 asks+0.008
Jason+0.008
 meets+0.008
Har+0.008
Ryan+0.007
Neg logit contributions
quet-0.008
comb-0.006
isy-0.006
ue-0.005
zie-0.005
Token She
Token ID1375
Feature activation+1.55e-02

Pos logit contributions
 meets+0.014
Jason+0.013
 asks+0.013
 pret+0.013
 wre+0.013
Neg logit contributions
quet-0.013
ue-0.011
isy-0.010
comb-0.010
 Sue-0.010
Token took
Token ID1718
Feature activation+8.27e-03

Pos logit contributions
quet+0.031
isy+0.026
comb+0.026
ue+0.024
zie+0.022
Neg logit contributions
 meets-0.022
 asks-0.022
Jason-0.021
 writes-0.020
Ready-0.019
Token a
Token ID257
Feature activation+1.76e-02

Pos logit contributions
quet+0.016
comb+0.014
isy+0.013
ue+0.012
zie+0.011
Neg logit contributions
 asks-0.014
 meets-0.013
Jason-0.013
 writes-0.013
 pret-0.012
Token cr
Token ID1067
Feature activation+4.91e-02

Pos logit contributions
quet+0.031
isy+0.025
comb+0.025
ue+0.022
 cushion+0.021
Neg logit contributions
 asks-0.031
 meets-0.030
Jason-0.029
 writes-0.028
Har-0.027
Tokenay
Token ID323
Feature activation+9.25e-02

Pos logit contributions
quet+0.069
comb+0.068
isy+0.056
zie+0.051
 Betty+0.051
Neg logit contributions
 writes-0.093
Jason-0.093
Ryan-0.090
 asks-0.088
Daniel-0.088
Tokenon
Token ID261
Feature activation+4.14e-02

Pos logit contributions
quet+0.171
comb+0.157
isy+0.134
zie+0.127
ue+0.126
Neg logit contributions
 asks-0.152
Jason-0.150
 writes-0.149
 meets-0.148
Ryan-0.140
Token and
Token ID290
Feature activation+9.74e-03

Pos logit contributions
quet+0.091
isy+0.081
zie+0.080
comb+0.077
ue+0.077
Neg logit contributions
 writes-0.047
 asks-0.046
 sees-0.042
Jason-0.041
 pret-0.040
Token drew
Token ID9859
Feature activation+1.44e-02

Pos logit contributions
quet+0.016
comb+0.014
isy+0.013
 as+0.012
ue+0.011
Neg logit contributions
 meets-0.016
Jason-0.016
 asks-0.015
Har-0.015
Ryan-0.015
Token some
Token ID617
Feature activation+1.47e-02

Pos logit contributions
quet+0.029
comb+0.025
isy+0.024
ue+0.022
zie+0.021
Neg logit contributions
 asks-0.022
 meets-0.021
 writes-0.021
Jason-0.021
 pret-0.020
Token lines
Token ID3951
Feature activation+7.78e-03

Pos logit contributions
quet+0.025
isy+0.020
comb+0.019
lights+0.017
ue+0.017
Neg logit contributions
 asks-0.027
Jason-0.027
 meets-0.027
Har-0.025
Ryan-0.025
Token
Token ID198
Feature activation+5.59e-04

Pos logit contributions
 pret+0.016
 meets+0.015
bers+0.015
 asks+0.015
 jury+0.015
Neg logit contributions
quet-0.014
isy-0.011
ue-0.011
 of-0.011
 Sue-0.010
TokenHe
Token ID1544
Feature activation-1.79e-03

Pos logit contributions
quet+0.001
isy+0.001
ue+0.001
comb+0.001
 end+0.001
Neg logit contributions
 meets-0.001
 asks-0.001
 pret-0.001
 writes-0.001
 Daniel-0.001
Token takes
Token ID2753
Feature activation+2.59e-03

Pos logit contributions
Jason+0.002
Simon+0.002
 meets+0.002
 asks+0.002
Ryan+0.002
Neg logit contributions
quet-0.004
isy-0.003
comb-0.003
ue-0.003
 cushion-0.003
Token the
Token ID262
Feature activation+2.71e-02

Pos logit contributions
quet+0.005
comb+0.004
isy+0.004
ue+0.004
zie+0.004
Neg logit contributions
 asks-0.004
 meets-0.004
Jason-0.004
 writes-0.004
 pret-0.004
Token cr
Token ID1067
Feature activation+5.44e-02

Pos logit contributions
quet+0.050
comb+0.042
isy+0.041
ue+0.036
zie+0.034
Neg logit contributions
 asks-0.047
 meets-0.044
Jason-0.044
 writes-0.041
Ryan-0.041
Tokenay
Token ID323
Feature activation+9.15e-02

Pos logit contributions
comb+0.081
quet+0.078
isy+0.069
zie+0.062
 shade+0.061
Neg logit contributions
 writes-0.094
Jason-0.092
us-0.087
 asks-0.086
 meets-0.085
Tokenons
Token ID684
Feature activation+4.64e-02

Pos logit contributions
quet+0.199
comb+0.199
isy+0.169
zie+0.161
lights+0.156
Neg logit contributions
 writes-0.114
 meets-0.111
 asks-0.108
Jason-0.106
 sees-0.099
Token from
Token ID422
Feature activation+9.32e-03

Pos logit contributions
quet+0.095
isy+0.082
comb+0.080
zie+0.073
ue+0.072
Neg logit contributions
 asks-0.068
Jason-0.063
 writes-0.062
 meets-0.061
 yells-0.061
Token them
Token ID606
Feature activation+1.62e-02

Pos logit contributions
quet+0.017
comb+0.014
isy+0.014
ue+0.013
zie+0.012
Neg logit contributions
 asks-0.016
 meets-0.015
Jason-0.015
 writes-0.014
 pret-0.014
Token.
Token ID13
Feature activation+8.98e-03

Pos logit contributions
quet+0.031
comb+0.026
isy+0.025
ue+0.022
zie+0.021
Neg logit contributions
 asks-0.027
 meets-0.026
Jason-0.025
 writes-0.025
 pret-0.024
Token He
Token ID679
Feature activation-4.49e-03

Pos logit contributions
quet+0.014
comb+0.011
ue+0.011
 Sue+0.011
lights+0.011
Neg logit contributions
 meets-0.016
Jason-0.015
 asks-0.015
bers-0.015
 pret-0.015
TokenThe
Token ID464
Feature activation+8.55e-03

Pos logit contributions
quet+0.019
comb+0.015
isy+0.015
ue+0.013
zie+0.013
Neg logit contributions
 asks-0.019
 meets-0.019
 writes-0.018
Jason-0.018
 pret-0.018
Token doctor
Token ID6253
Feature activation-1.60e-02

Pos logit contributions
quet+0.016
isy+0.013
comb+0.013
 cushion+0.012
 end+0.011
Neg logit contributions
 asks-0.013
 meets-0.013
Jason-0.013
 writes-0.013
Ryan-0.012
Token put
Token ID1234
Feature activation+9.84e-03

Pos logit contributions
 meets+0.024
Jason+0.024
 asks+0.024
Har+0.023
Ready+0.022
Neg logit contributions
quet-0.030
isy-0.026
comb-0.026
ue-0.023
ie-0.022
Token the
Token ID262
Feature activation+2.97e-02

Pos logit contributions
quet+0.018
comb+0.015
isy+0.015
ue+0.013
zie+0.013
Neg logit contributions
 asks-0.017
 meets-0.016
Jason-0.016
 writes-0.015
 pret-0.015
Token st
Token ID336
Feature activation+1.19e-02

Pos logit contributions
quet+0.050
isy+0.042
comb+0.042
 cushion+0.039
 shade+0.038
Neg logit contributions
Jason-0.049
 asks-0.049
 meets-0.047
Ryan-0.047
Har-0.046
Tokeneth
Token ID2788
Feature activation+9.15e-02

Pos logit contributions
quet+0.023
comb+0.020
isy+0.019
ue+0.017
lights+0.016
Neg logit contributions
 asks-0.019
 meets-0.019
Jason-0.018
 writes-0.018
 pret-0.017
Tokenoscope
Token ID40326
Feature activation+5.15e-02

Pos logit contributions
quet+0.158
comb+0.133
isy+0.132
zie+0.112
lights+0.109
Neg logit contributions
 asks-0.165
Jason-0.157
 meets-0.156
 writes-0.150
Ryan-0.148
Token on
Token ID319
Feature activation+2.23e-02

Pos logit contributions
quet+0.101
comb+0.085
isy+0.083
ue+0.076
zie+0.073
Neg logit contributions
 asks-0.079
 meets-0.077
Jason-0.076
 writes-0.073
 pret-0.071
Token Molly
Token ID30236
Feature activation+3.22e-02

Pos logit contributions
quet+0.045
comb+0.037
isy+0.036
ue+0.033
zie+0.032
Neg logit contributions
 asks-0.035
 meets-0.033
Jason-0.033
 writes-0.032
 pret-0.031
Token's
Token ID338
Feature activation-6.83e-03

Pos logit contributions
quet+0.067
comb+0.062
isy+0.059
ue+0.052
zie+0.051
Neg logit contributions
 asks-0.043
Jason-0.041
 meets-0.041
Check-0.040
Ryan-0.039
Token chest
Token ID7721
Feature activation-5.34e-03

Pos logit contributions
 asks+0.015
 meets+0.014
Jason+0.014
Ryan+0.014
Ready+0.014
Neg logit contributions
quet-0.009
comb-0.008
isy-0.007
 cushion-0.006
 shade-0.006
Token bird
Token ID6512
Feature activation+3.78e-02

Pos logit contributions
quet+0.016
comb+0.013
isy+0.012
lights+0.011
zie+0.011
Neg logit contributions
 asks-0.015
 sees-0.013
 meets-0.013
 writes-0.013
 pret-0.013
Token and
Token ID290
Feature activation+2.86e-03

Pos logit contributions
quet+0.080
comb+0.065
lights+0.063
ue+0.060
 ray+0.058
Neg logit contributions
 asks-0.052
 meets-0.051
 writes-0.046
 sees-0.046
 met-0.043
Token took
Token ID1718
Feature activation-9.32e-04

Pos logit contributions
quet+0.006
comb+0.005
isy+0.005
ue+0.005
zie+0.005
Neg logit contributions
 asks-0.004
 meets-0.004
 writes-0.004
 pret-0.004
Jason-0.004
Token the
Token ID262
Feature activation+2.30e-02

Pos logit contributions
 asks+0.001
 meets+0.001
 writes+0.001
Jason+0.001
 pret+0.001
Neg logit contributions
quet-0.002
comb-0.002
isy-0.002
ue-0.002
lights-0.002
Token tw
Token ID665
Feature activation+3.85e-02

Pos logit contributions
quet+0.047
comb+0.039
lights+0.037
ue+0.036
isy+0.036
Neg logit contributions
 asks-0.035
 meets-0.033
 sees-0.032
 pret-0.031
Jason-0.031
Tokenig
Token ID328
Feature activation+9.15e-02

Pos logit contributions
quet+0.067
comb+0.061
 Betty+0.056
 Susan+0.056
ue+0.056
Neg logit contributions
 meets-0.054
 asks-0.053
bers-0.051
 pret-0.050
 sees-0.050
Token back
Token ID736
Feature activation+1.13e-02

Pos logit contributions
quet+0.199
ue+0.185
lights+0.180
umm+0.174
zie+0.169
Neg logit contributions
 meets-0.087
 met-0.080
to-0.079
 sees-0.072
 living-0.069
Token to
Token ID284
Feature activation+4.24e-03

Pos logit contributions
quet+0.027
isy+0.024
comb+0.024
ue+0.022
lights+0.021
Neg logit contributions
 asks-0.013
 meets-0.012
 sees-0.011
 writes-0.010
 yells-0.010
Token her
Token ID607
Feature activation+5.30e-03

Pos logit contributions
quet+0.008
comb+0.007
isy+0.006
ue+0.006
lights+0.006
Neg logit contributions
 asks-0.007
 meets-0.007
Jason-0.007
 writes-0.007
 pret-0.006
Token nest
Token ID16343
Feature activation+7.57e-03

Pos logit contributions
quet+0.009
comb+0.007
isy+0.007
ue+0.006
zie+0.006
Neg logit contributions
 asks-0.010
 meets-0.010
Jason-0.009
 writes-0.009
 pret-0.009
Token to
Token ID284
Feature activation+3.59e-03

Pos logit contributions
quet+0.017
isy+0.015
comb+0.014
ue+0.014
zie+0.014
Neg logit contributions
 asks-0.008
 meets-0.008
 writes-0.007
 sees-0.007
 met-0.007
Tokenaway
Token ID8272
Feature activation-8.12e-02

Pos logit contributions
Jason+0.097
 asks+0.095
 meets+0.092
Ryan+0.087
 writes+0.087
Neg logit contributions
quet-0.094
comb-0.078
isy-0.075
ue-0.067
zie-0.064
Token and
Token ID290
Feature activation-2.70e-02

Pos logit contributions
Jason+0.143
 meets+0.134
 asks+0.134
Ryan+0.129
Har+0.127
Neg logit contributions
quet-0.141
isy-0.121
comb-0.116
ue-0.108
zie-0.101
Token c
Token ID269
Feature activation-2.56e-02

Pos logit contributions
Jason+0.045
 meets+0.043
Ryan+0.043
 asks+0.042
rev+0.041
Neg logit contributions
quet-0.045
comb-0.039
isy-0.035
 surely-0.033
 as-0.032
Tokenumin
Token ID7230
Feature activation-4.52e-02

Pos logit contributions
 asks+0.039
Jason+0.039
 meets+0.037
 pret+0.036
 writes+0.036
Neg logit contributions
quet-0.051
comb-0.041
isy-0.041
lights-0.038
ue-0.038
Token and
Token ID290
Feature activation-2.84e-02

Pos logit contributions
Jason+0.078
 asks+0.078
 meets+0.076
Ryan+0.072
 writes+0.071
Neg logit contributions
quet-0.079
comb-0.067
isy-0.065
ue-0.056
zie-0.056
Token cor
Token ID1162
Feature activation-1.07e-01

Pos logit contributions
Jason+0.047
 meets+0.046
 asks+0.045
Ryan+0.045
rev+0.043
Neg logit contributions
quet-0.048
comb-0.042
isy-0.038
 surely-0.034
 shade-0.033
Tokeni
Token ID72
Feature activation-3.49e-02

Pos logit contributions
Jason+0.241
 asks+0.238
 writes+0.231
Ryan+0.226
rev+0.224
Neg logit contributions
quet-0.126
comb-0.096
isy-0.084
ow-0.074
flower-0.070
Tokenander
Token ID4066
Feature activation-5.10e-02

Pos logit contributions
Jason+0.065
Ryan+0.062
 asks+0.062
Check+0.060
Soc+0.059
Neg logit contributions
quet-0.055
comb-0.048
isy-0.045
ue-0.037
 as-0.037
Token and
Token ID290
Feature activation-3.08e-02

Pos logit contributions
Jason+0.091
 asks+0.090
 meets+0.086
Ryan+0.084
 writes+0.084
Neg logit contributions
quet-0.086
comb-0.074
isy-0.071
ue-0.060
zie-0.059
Token card
Token ID2657
Feature activation-5.12e-02

Pos logit contributions
Jason+0.051
 meets+0.050
 asks+0.049
Ryan+0.048
 writes+0.047
Neg logit contributions
quet-0.052
comb-0.046
isy-0.041
 surely-0.037
 shade-0.036
Tokenam
Token ID321
Feature activation-5.99e-02

Pos logit contributions
Jason+0.085
 asks+0.084
 meets+0.081
Ryan+0.078
Har+0.077
Neg logit contributions
quet-0.095
comb-0.080
isy-0.078
ue-0.068
lights-0.065
Token,
Token ID11
Feature activation-1.22e-02

Pos logit contributions
quet+0.001
comb+0.001
isy+0.001
ue+0.001
lights+0.001
Neg logit contributions
 asks-0.001
Jason-0.001
 meets-0.001
 writes-0.001
 yells-0.001
Token but
Token ID475
Feature activation+2.08e-03

Pos logit contributions
 asks+0.021
 meets+0.020
Jason+0.019
 pret+0.019
 writes+0.019
Neg logit contributions
quet-0.023
comb-0.020
isy-0.018
ue-0.016
zie-0.016
Token it
Token ID340
Feature activation-2.72e-02

Pos logit contributions
quet+0.004
comb+0.004
isy+0.004
ue+0.003
zie+0.003
Neg logit contributions
 asks-0.003
 meets-0.003
Jason-0.003
 writes-0.003
 pret-0.003
Token's
Token ID338
Feature activation-3.57e-02

Pos logit contributions
 asks+0.029
 meets+0.028
Jason+0.026
 writes+0.025
 pret+0.024
Neg logit contributions
quet-0.068
comb-0.059
isy-0.058
ue-0.054
zie-0.052
Token not
Token ID407
Feature activation-3.43e-03

Pos logit contributions
 asks+0.060
 meets+0.057
Jason+0.055
 writes+0.054
 pret+0.054
Neg logit contributions
quet-0.070
comb-0.058
isy-0.055
ue-0.051
zie-0.048
Token possible
Token ID1744
Feature activation-1.02e-01

Pos logit contributions
 asks+0.006
 meets+0.006
Jason+0.006
 writes+0.006
 pret+0.006
Neg logit contributions
quet-0.006
comb-0.005
isy-0.005
ue-0.004
zie-0.004
Token.
Token ID13
Feature activation+4.24e-03

Pos logit contributions
Jason+0.211
Check+0.201
Ryan+0.199
 asks+0.198
Har+0.197
Neg logit contributions
quet-0.139
comb-0.126
isy-0.111
 as-0.098
ue-0.092
Token We
Token ID775
Feature activation-8.53e-03

Pos logit contributions
quet+0.008
comb+0.007
isy+0.006
ue+0.006
zie+0.006
Neg logit contributions
 meets-0.006
Jason-0.006
 asks-0.006
 met-0.006
 yells-0.005
Token have
Token ID423
Feature activation+8.84e-04

Pos logit contributions
Jason+0.014
 asks+0.014
 meets+0.013
 writes+0.013
Ryan+0.013
Neg logit contributions
quet-0.015
comb-0.013
isy-0.012
ue-0.011
zie-0.010
Token to
Token ID284
Feature activation-5.60e-03

Pos logit contributions
quet+0.001
 too+0.001
 as+0.001
 shade+0.001
 of+0.001
Neg logit contributions
Jason-0.002
rob-0.002
rev-0.002
Ryan-0.002
Ready-0.002
Token be
Token ID307
Feature activation+1.56e-02

Pos logit contributions
 asks+0.010
 meets+0.010
Jason+0.010
 writes+0.010
 pret+0.009
Neg logit contributions
quet-0.009
comb-0.008
isy-0.007
ue-0.007
zie-0.006
Token buckets
Token ID38674
Feature activation+1.59e-02

Pos logit contributions
Jason+0.008
 asks+0.008
 meets+0.008
Ryan+0.008
rev+0.008
Neg logit contributions
quet-0.008
comb-0.006
isy-0.006
lights-0.005
 shade-0.005
Token and
Token ID290
Feature activation+2.38e-03

Pos logit contributions
quet+0.029
comb+0.024
isy+0.023
ue+0.021
zie+0.020
Neg logit contributions
 asks-0.028
 meets-0.027
 writes-0.026
Jason-0.026
 pret-0.025
Token shovel
Token ID33677
Feature activation-3.30e-02

Pos logit contributions
quet+0.004
comb+0.004
isy+0.003
 shade+0.003
lights+0.003
Neg logit contributions
Jason-0.004
Ryan-0.004
 asks-0.004
 meets-0.004
Har-0.004
Tokens
Token ID82
Feature activation+7.17e-04

Pos logit contributions
 asks+0.052
Jason+0.051
 meets+0.051
 writes+0.048
Har+0.048
Neg logit contributions
quet-0.062
comb-0.052
isy-0.051
lights-0.048
ue-0.047
Token and
Token ID290
Feature activation-1.93e-02

Pos logit contributions
quet+0.001
comb+0.001
isy+0.001
lights+0.001
ue+0.001
Neg logit contributions
 asks-0.001
Jason-0.001
 meets-0.001
Ryan-0.001
 writes-0.001
Token seaw
Token ID32085
Feature activation-1.01e-01

Pos logit contributions
Jason+0.034
 asks+0.033
Ryan+0.033
 meets+0.033
Har+0.032
Neg logit contributions
quet-0.032
comb-0.027
isy-0.025
 shade-0.023
lights-0.022
Tokeneed
Token ID2308
Feature activation-5.49e-02

Pos logit contributions
 asks+0.160
 meets+0.154
Jason+0.148
Ready+0.141
 writes+0.139
Neg logit contributions
quet-0.203
comb-0.172
isy-0.171
immer-0.147
ue-0.145
Token.
Token ID13
Feature activation-5.18e-03

Pos logit contributions
Jason+0.101
 asks+0.101
 meets+0.099
Har+0.095
Ryan+0.095
Neg logit contributions
quet-0.091
comb-0.077
isy-0.072
lights-0.063
ue-0.060
Token Then
Token ID3244
Feature activation-9.68e-03

Pos logit contributions
Jason+0.007
 meets+0.007
 asks+0.007
Har+0.007
Ryan+0.007
Neg logit contributions
quet-0.010
comb-0.009
isy-0.008
ue-0.008
lights-0.008
Token we
Token ID356
Feature activation-1.03e-02

Pos logit contributions
Jason+0.015
 asks+0.015
 meets+0.015
Ryan+0.015
Har+0.014
Neg logit contributions
quet-0.018
comb-0.016
isy-0.015
ue-0.014
zie-0.013
Token can
Token ID460
Feature activation-6.27e-03

Pos logit contributions
Jason+0.014
 asks+0.014
 meets+0.013
Ryan+0.013
Har+0.013
Neg logit contributions
quet-0.022
comb-0.019
isy-0.018
ue-0.016
zie-0.016
Token Like
Token ID4525
Feature activation-1.42e-02

Pos logit contributions
 meets+0.002
 asks+0.002
Jason+0.002
 sees+0.002
 writes+0.002
Neg logit contributions
quet-0.004
comb-0.004
isy-0.003
ue-0.003
zie-0.003
Token shells
Token ID19679
Feature activation-2.65e-02

Pos logit contributions
Jason+0.027
 asks+0.026
 meets+0.025
Ryan+0.025
 writes+0.024
Neg logit contributions
quet-0.023
comb-0.018
isy-0.018
 as-0.017
 shade-0.016
Token and
Token ID290
Feature activation-3.47e-03

Pos logit contributions
 asks+0.053
 meets+0.051
Jason+0.051
 writes+0.049
 pret+0.048
Neg logit contributions
quet-0.041
comb-0.033
isy-0.032
ue-0.028
zie-0.026
Token rocks
Token ID12586
Feature activation-3.32e-02

Pos logit contributions
Jason+0.006
Ryan+0.005
rev+0.005
 asks+0.005
Har+0.005
Neg logit contributions
quet-0.006
isy-0.005
comb-0.005
 shade-0.005
lights-0.005
Token and
Token ID290
Feature activation-1.06e-02

Pos logit contributions
 asks+0.062
Jason+0.061
 meets+0.060
 writes+0.058
Ryan+0.056
Neg logit contributions
quet-0.055
comb-0.045
isy-0.043
ue-0.038
lights-0.036
Token seaw
Token ID32085
Feature activation-1.01e-01

Pos logit contributions
Jason+0.018
Ryan+0.017
rev+0.017
 asks+0.017
Har+0.016
Neg logit contributions
quet-0.018
comb-0.015
isy-0.015
 shade-0.015
lights-0.014
Tokeneed
Token ID2308
Feature activation-5.47e-02

Pos logit contributions
 asks+0.169
Jason+0.159
 meets+0.158
Ryan+0.150
Enough+0.149
Neg logit contributions
quet-0.191
isy-0.161
comb-0.158
immer-0.137
ue-0.132
Token."
Token ID526
Feature activation-1.75e-02

Pos logit contributions
 asks+0.102
Jason+0.102
 meets+0.099
Ryan+0.096
Har+0.094
Neg logit contributions
quet-0.091
comb-0.075
isy-0.071
lights-0.061
ue-0.059
Token
Token ID198
Feature activation-3.91e-03

Pos logit contributions
 meets+0.031
 loudspe+0.030
 wre+0.030
 pret+0.030
Check+0.029
Neg logit contributions
quet-0.024
 Sue-0.024
 Betty-0.022
ue-0.022
 Suz-0.022
Token
Token ID198
Feature activation+5.41e-03

Pos logit contributions
 pret+0.006
 meets+0.006
 cheated+0.006
 writes+0.006
 wre+0.006
Neg logit contributions
quet-0.007
ue-0.006
isy-0.006
 Sue-0.005
comb-0.005
TokenM
Token ID44
Feature activation+1.69e-02

Pos logit contributions
quet+0.011
isy+0.009
comb+0.009
ue+0.008
zie+0.007
Neg logit contributions
 meets-0.009
 asks-0.009
 writes-0.008
 pret-0.008
 yells-0.008
Token like
Token ID588
Feature activation-9.61e-03

Pos logit contributions
quet+0.001
comb+0.001
isy+0.001
ue+0.000
lights+0.000
Neg logit contributions
 asks-0.001
 meets-0.001
Jason-0.001
 writes-0.001
Ryan-0.001
Token fish
Token ID5916
Feature activation-3.24e-02

Pos logit contributions
Jason+0.017
 asks+0.016
 meets+0.016
Ryan+0.016
Har+0.015
Neg logit contributions
quet-0.017
isy-0.014
comb-0.013
 shade-0.013
lights-0.012
Token and
Token ID290
Feature activation-1.56e-02

Pos logit contributions
 asks+0.067
 meets+0.065
Jason+0.064
 writes+0.063
 pret+0.061
Neg logit contributions
quet-0.048
comb-0.038
isy-0.036
ue-0.031
zie-0.030
Token shells
Token ID19679
Feature activation-5.11e-02

Pos logit contributions
Jason+0.026
Ryan+0.025
Har+0.024
 asks+0.024
rev+0.024
Neg logit contributions
quet-0.026
comb-0.024
isy-0.022
 shade-0.022
lights-0.020
Token and
Token ID290
Feature activation-8.92e-03

Pos logit contributions
 asks+0.081
 meets+0.077
Jason+0.074
 writes+0.074
 pret+0.071
Neg logit contributions
quet-0.101
comb-0.085
isy-0.082
ue-0.075
zie-0.073
Token seaw
Token ID32085
Feature activation-9.86e-02

Pos logit contributions
Jason+0.015
Ryan+0.015
Har+0.014
 asks+0.014
rev+0.014
Neg logit contributions
quet-0.015
comb-0.013
isy-0.013
 shade-0.013
lights-0.012
Tokeneed
Token ID2308
Feature activation-5.50e-02

Pos logit contributions
 asks+0.139
 meets+0.132
Jason+0.130
 writes+0.122
Ryan+0.119
Neg logit contributions
quet-0.214
comb-0.183
isy-0.181
ue-0.162
lights-0.155
Token.
Token ID13
Feature activation-6.26e-03

Pos logit contributions
 asks+0.092
 meets+0.089
Jason+0.089
 writes+0.084
Ryan+0.082
Neg logit contributions
quet-0.103
comb-0.087
isy-0.083
ue-0.074
lights-0.071
Token But
Token ID887
Feature activation+1.87e-02

Pos logit contributions
 writes+0.011
Jason+0.011
 meets+0.010
Har+0.010
 yells+0.010
Neg logit contributions
quet-0.009
ue-0.009
comb-0.008
lights-0.008
 Sue-0.008
Token they
Token ID484
Feature activation-8.47e-03

Pos logit contributions
quet+0.034
comb+0.027
isy+0.026
ue+0.023
zie+0.022
Neg logit contributions
 asks-0.034
 meets-0.033
Jason-0.032
 writes-0.031
 pret-0.031
Token did
Token ID750
Feature activation+2.24e-02

Pos logit contributions
 asks+0.012
 meets+0.012
Jason+0.011
 writes+0.011
 pret+0.011
Neg logit contributions
quet-0.018
comb-0.015
isy-0.015
ue-0.014
zie-0.013
Token some
Token ID617
Feature activation+7.63e-03

Pos logit contributions
 asks+0.022
 meets+0.022
Jason+0.021
 writes+0.020
 pret+0.020
Neg logit contributions
quet-0.025
comb-0.021
isy-0.021
ue-0.018
lights-0.018
Token shells
Token ID19679
Feature activation-2.47e-02

Pos logit contributions
quet+0.014
isy+0.012
comb+0.011
lights+0.011
 ray+0.011
Neg logit contributions
 asks-0.012
Jason-0.012
 meets-0.012
 writes-0.011
Har-0.011
Token and
Token ID290
Feature activation-3.76e-03

Pos logit contributions
 asks+0.044
 meets+0.043
 writes+0.041
Jason+0.040
 sees+0.040
Neg logit contributions
quet-0.044
comb-0.036
isy-0.035
ue-0.032
zie-0.031
Token rocks
Token ID12586
Feature activation-3.01e-02

Pos logit contributions
Jason+0.006
Ryan+0.006
 asks+0.006
 meets+0.006
Har+0.006
Neg logit contributions
quet-0.006
comb-0.005
isy-0.005
lights-0.005
 shade-0.005
Token and
Token ID290
Feature activation-1.04e-02

Pos logit contributions
 asks+0.053
 meets+0.051
 writes+0.049
Jason+0.049
 pret+0.048
Neg logit contributions
quet-0.054
comb-0.045
isy-0.043
ue-0.039
zie-0.038
Token seaw
Token ID32085
Feature activation-9.74e-02

Pos logit contributions
Jason+0.017
Ryan+0.017
Har+0.017
 asks+0.016
 meets+0.016
Neg logit contributions
quet-0.017
comb-0.015
isy-0.015
lights-0.014
 shade-0.014
Tokeneed
Token ID2308
Feature activation-5.19e-02

Pos logit contributions
 asks+0.145
 meets+0.138
Jason+0.134
 writes+0.126
Ryan+0.122
Neg logit contributions
quet-0.206
comb-0.176
isy-0.173
ue-0.153
immer-0.147
Token.
Token ID13
Feature activation-2.31e-03

Pos logit contributions
 asks+0.094
Jason+0.092
 meets+0.091
 writes+0.086
Ryan+0.085
Neg logit contributions
quet-0.090
comb-0.075
isy-0.071
ue-0.062
lights-0.061
Token He
Token ID679
Feature activation-1.09e-02

Pos logit contributions
Jason+0.004
 meets+0.004
 asks+0.004
Har+0.003
 writes+0.003
Neg logit contributions
quet-0.004
comb-0.004
ue-0.003
isy-0.003
lights-0.003
Token picked
Token ID6497
Feature activation+1.92e-02

Pos logit contributions
Jason+0.017
 meets+0.016
 asks+0.016
 writes+0.015
Ready+0.015
Neg logit contributions
quet-0.019
isy-0.017
comb-0.017
ue-0.015
lights-0.014
Token them
Token ID606
Feature activation+3.68e-02

Pos logit contributions
quet+0.028
isy+0.024
comb+0.023
ie+0.021
ue+0.020
Neg logit contributions
Jason-0.037
 asks-0.036
 meets-0.034
Har-0.034
Ryan-0.034
Token decorated
Token ID24789
Feature activation-5.23e-03

Pos logit contributions
 asks+0.013
Jason+0.013
 meets+0.012
Ryan+0.012
Har+0.012
Neg logit contributions
quet-0.014
comb-0.012
isy-0.011
ue-0.010
lights-0.010
Token it
Token ID340
Feature activation+2.52e-03

Pos logit contributions
 asks+0.009
Jason+0.008
 meets+0.008
 writes+0.008
Ryan+0.008
Neg logit contributions
quet-0.010
comb-0.008
isy-0.008
ue-0.007
lights-0.007
Token with
Token ID351
Feature activation-6.64e-03

Pos logit contributions
quet+0.005
comb+0.004
isy+0.004
zie+0.004
ue+0.004
Neg logit contributions
 asks-0.004
 meets-0.004
 writes-0.003
 pret-0.003
 sees-0.003
Token shells
Token ID19679
Feature activation-3.96e-02

Pos logit contributions
 asks+0.011
 meets+0.011
Jason+0.011
 writes+0.010
Ryan+0.010
Neg logit contributions
quet-0.012
comb-0.010
isy-0.010
lights-0.009
ue-0.009
Token and
Token ID290
Feature activation-7.74e-03

Pos logit contributions
 asks+0.065
 meets+0.063
Jason+0.060
 writes+0.060
 pret+0.058
Neg logit contributions
quet-0.075
comb-0.063
isy-0.061
ue-0.056
zie-0.054
Token seaw
Token ID32085
Feature activation-9.71e-02

Pos logit contributions
 asks+0.012
Jason+0.012
Ryan+0.012
 meets+0.012
Har+0.012
Neg logit contributions
quet-0.014
comb-0.012
isy-0.011
lights-0.011
 shade-0.010
Tokeneed
Token ID2308
Feature activation-5.12e-02

Pos logit contributions
 asks+0.143
 meets+0.135
Jason+0.133
 writes+0.124
Ryan+0.122
Neg logit contributions
quet-0.207
comb-0.177
isy-0.176
ue-0.154
lights-0.147
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
 asks+0.090
Jason+0.089
 meets+0.088
 writes+0.082
Ryan+0.082
Neg logit contributions
quet-0.091
comb-0.077
isy-0.073
lights-0.063
ue-0.063
Token They
Token ID1119
Feature activation+1.98e-02

Pos logit contributions
 meets+0.021
Jason+0.020
 wre+0.020
 kidn+0.020
rob+0.019
Neg logit contributions
quet-0.014
ue-0.013
 Sue-0.012
 Betty-0.011
comb-0.011
Token had
Token ID550
Feature activation+1.68e-03

Pos logit contributions
quet+0.039
comb+0.033
isy+0.032
ue+0.029
zie+0.028
Neg logit contributions
 asks-0.031
 meets-0.030
Jason-0.029
 writes-0.028
 pret-0.027
Token a
Token ID257
Feature activation-2.08e-02

Pos logit contributions
quet+0.003
comb+0.002
isy+0.002
 shade+0.002
ue+0.002
Neg logit contributions
 asks-0.003
Jason-0.003
 meets-0.003
Ryan-0.003
Har-0.003
Token like
Token ID588
Feature activation-1.02e-02

Pos logit contributions
quet+0.003
comb+0.003
isy+0.003
ue+0.002
zie+0.002
Neg logit contributions
 asks-0.004
 meets-0.004
Jason-0.004
 writes-0.003
 pret-0.003
Token fish
Token ID5916
Feature activation-3.30e-02

Pos logit contributions
Jason+0.018
 asks+0.018
 meets+0.017
Ryan+0.017
Har+0.016
Neg logit contributions
quet-0.017
isy-0.014
comb-0.014
 shade-0.014
lights-0.013
Token and
Token ID290
Feature activation-1.24e-02

Pos logit contributions
 asks+0.069
 meets+0.067
Jason+0.066
 writes+0.065
 pret+0.063
Neg logit contributions
quet-0.048
comb-0.039
isy-0.037
ue-0.031
zie-0.030
Token shells
Token ID19679
Feature activation-5.00e-02

Pos logit contributions
Jason+0.021
Ryan+0.020
 asks+0.020
Har+0.020
 meets+0.019
Neg logit contributions
quet-0.021
comb-0.018
isy-0.017
 shade-0.017
lights-0.016
Token and
Token ID290
Feature activation-5.99e-03

Pos logit contributions
 asks+0.081
 meets+0.077
Jason+0.075
 writes+0.074
 pret+0.072
Neg logit contributions
quet-0.097
comb-0.082
isy-0.079
ue-0.072
zie-0.070
Token seaw
Token ID32085
Feature activation-9.70e-02

Pos logit contributions
Jason+0.010
Ryan+0.010
 asks+0.010
Har+0.010
 meets+0.009
Neg logit contributions
quet-0.010
comb-0.009
isy-0.008
 shade-0.008
lights-0.008
Tokeneed
Token ID2308
Feature activation-5.33e-02

Pos logit contributions
 asks+0.143
 meets+0.134
Jason+0.134
 writes+0.125
Ryan+0.122
Neg logit contributions
quet-0.206
comb-0.176
isy-0.175
ue-0.154
immer-0.148
Token.
Token ID13
Feature activation-4.45e-03

Pos logit contributions
 asks+0.090
 meets+0.087
Jason+0.086
 writes+0.082
Ryan+0.080
Neg logit contributions
quet-0.100
comb-0.084
isy-0.081
ue-0.071
lights-0.069
Token
Token ID198
Feature activation-2.25e-03

Pos logit contributions
Jason+0.007
 writes+0.007
 meets+0.007
 pret+0.006
Har+0.006
Neg logit contributions
quet-0.008
ue-0.007
comb-0.007
 Suz-0.006
isy-0.006
Token
Token ID198
Feature activation+9.49e-03

Pos logit contributions
 asks+0.003
 writes+0.003
 pret+0.003
 meets+0.003
Jason+0.003
Neg logit contributions
quet-0.004
ue-0.004
isy-0.004
comb-0.003
 Suz-0.003
TokenOne
Token ID3198
Feature activation+1.87e-02

Pos logit contributions
quet+0.017
isy+0.014
comb+0.014
ue+0.013
zie+0.012
Neg logit contributions
 asks-0.017
 meets-0.016
 writes-0.016
 pret-0.015
Jason-0.015
Token added
Token ID2087
Feature activation-7.58e-03

Pos logit contributions
quet+0.052
comb+0.045
isy+0.043
ue+0.039
zie+0.038
Neg logit contributions
 asks-0.040
 meets-0.038
Jason-0.037
 writes-0.036
 pret-0.035
Token shells
Token ID19679
Feature activation-1.34e-02

Pos logit contributions
 asks+0.013
 meets+0.012
Jason+0.012
 writes+0.012
Ryan+0.011
Neg logit contributions
quet-0.014
comb-0.012
isy-0.011
ue-0.010
lights-0.010
Token and
Token ID290
Feature activation+1.19e-02

Pos logit contributions
 asks+0.019
 meets+0.018
 sees+0.018
 writes+0.018
 pret+0.017
Neg logit contributions
quet-0.028
comb-0.024
isy-0.024
zie-0.022
ue-0.021
Token stones
Token ID14966
Feature activation-2.33e-02

Pos logit contributions
quet+0.022
comb+0.019
isy+0.018
lights+0.017
 shade+0.016
Neg logit contributions
 asks-0.019
Jason-0.018
 meets-0.018
Ryan-0.017
Har-0.017
Token and
Token ID290
Feature activation+5.94e-04

Pos logit contributions
 asks+0.035
 meets+0.033
 writes+0.032
 sees+0.032
 pret+0.031
Neg logit contributions
quet-0.047
comb-0.040
isy-0.039
zie-0.035
ue-0.035
Token seaw
Token ID32085
Feature activation-9.54e-02

Pos logit contributions
quet+0.001
comb+0.001
isy+0.001
lights+0.001
 shade+0.001
Neg logit contributions
 asks-0.001
Jason-0.001
Ryan-0.001
 meets-0.001
Har-0.001
Tokeneed
Token ID2308
Feature activation-4.75e-02

Pos logit contributions
 asks+0.133
 meets+0.126
Jason+0.124
 writes+0.115
Ryan+0.112
Neg logit contributions
quet-0.209
comb-0.177
isy-0.175
ue-0.159
lights-0.152
Token to
Token ID284
Feature activation-1.40e-02

Pos logit contributions
 asks+0.085
 meets+0.082
Jason+0.080
 writes+0.078
 pret+0.076
Neg logit contributions
quet-0.084
comb-0.070
isy-0.067
ue-0.060
zie-0.058
Token make
Token ID787
Feature activation+4.50e-03

Pos logit contributions
 asks+0.023
 meets+0.022
Jason+0.021
 writes+0.021
 pret+0.020
Neg logit contributions
quet-0.027
comb-0.023
isy-0.022
ue-0.020
zie-0.019
Token it
Token ID340
Feature activation+1.21e-02

Pos logit contributions
quet+0.008
isy+0.006
comb+0.006
lights+0.005
ue+0.005
Neg logit contributions
 asks-0.008
Jason-0.008
 meets-0.008
Har-0.008
Ryan-0.007
Token look
Token ID804
Feature activation+8.84e-03

Pos logit contributions
quet+0.024
comb+0.020
isy+0.020
ue+0.019
zie+0.018
Neg logit contributions
 asks-0.018
 meets-0.018
 pret-0.018
 writes-0.018
 sees-0.017
Tokenâ
Token ID22940
Feature activation-2.22e-02

Pos logit contributions
Jason+0.021
 asks+0.020
 meets+0.020
Ryan+0.019
 writes+0.019
Neg logit contributions
quet-0.036
comb-0.032
isy-0.032
ue-0.028
zie-0.028
Token€
Token ID26391
Feature activation-8.40e-04

Pos logit contributions
 asks+0.034
 meets+0.033
Jason+0.032
 writes+0.031
 pret+0.030
Neg logit contributions
quet-0.045
comb-0.038
isy-0.037
ue-0.034
zie-0.032
Tokenâ„¢
Token ID8151
Feature activation+2.41e-03

Pos logit contributions
 asks+0.001
Jason+0.001
 yells+0.001
 writes+0.001
 pret+0.001
Neg logit contributions
quet-0.002
comb-0.001
ue-0.001
house-0.001
isy-0.001
Tokens
Token ID82
Feature activation-1.56e-02

Pos logit contributions
quet+0.004
comb+0.004
isy+0.004
ue+0.003
zie+0.003
Neg logit contributions
 asks-0.004
 meets-0.004
 writes-0.004
Jason-0.004
 pret-0.004
Token always
Token ID1464
Feature activation-4.45e-02

Pos logit contributions
 asks+0.027
 meets+0.026
Jason+0.025
 writes+0.024
 pret+0.024
Neg logit contributions
quet-0.029
comb-0.024
isy-0.023
ue-0.021
zie-0.020
Token possible
Token ID1744
Feature activation-9.46e-02

Pos logit contributions
 asks+0.079
Jason+0.078
 meets+0.077
 writes+0.074
Ryan+0.073
Neg logit contributions
quet-0.074
comb-0.062
isy-0.061
ue-0.052
zie-0.052
Token to
Token ID284
Feature activation-1.26e-02

Pos logit contributions
Jason+0.164
 asks+0.161
 writes+0.158
 meets+0.156
 loudspe+0.154
Neg logit contributions
quet-0.157
comb-0.141
isy-0.131
 as-0.113
ue-0.109
Token improve
Token ID2987
Feature activation-3.14e-02

Pos logit contributions
 asks+0.023
 meets+0.023
Jason+0.022
 writes+0.022
 pret+0.021
Neg logit contributions
quet-0.021
comb-0.017
isy-0.017
ue-0.014
zie-0.014
Token and
Token ID290
Feature activation-3.67e-03

Pos logit contributions
 asks+0.060
 meets+0.058
Jason+0.057
Ready+0.055
 writes+0.055
Neg logit contributions
quet-0.047
isy-0.038
comb-0.038
 as-0.034
ie-0.032
Token move
Token ID1445
Feature activation-2.43e-02

Pos logit contributions
Jason+0.007
 asks+0.007
 meets+0.007
Ryan+0.006
rev+0.006
Neg logit contributions
quet-0.006
comb-0.005
isy-0.005
 surely-0.004
ue-0.004
Token forward
Token ID2651
Feature activation-2.00e-02

Pos logit contributions
 asks+0.048
 meets+0.047
Jason+0.046
 writes+0.045
 pret+0.044
Neg logit contributions
quet-0.036
comb-0.028
isy-0.028
lights-0.026
 as-0.024
Tokenate
Token ID378
Feature activation-1.97e-02

Pos logit contributions
quet+0.010
comb+0.009
isy+0.008
ue+0.008
zie+0.007
Neg logit contributions
 asks-0.006
 meets-0.006
Jason-0.006
 writes-0.006
 pret-0.005
Token it
Token ID340
Feature activation-1.07e-03

Pos logit contributions
 asks+0.028
 meets+0.026
Jason+0.025
 writes+0.025
 pret+0.024
Neg logit contributions
quet-0.043
comb-0.037
isy-0.036
ue-0.033
zie-0.032
Token with
Token ID351
Feature activation-8.24e-03

Pos logit contributions
 asks+0.001
 meets+0.001
 pret+0.001
 writes+0.001
 sees+0.001
Neg logit contributions
quet-0.002
isy-0.002
comb-0.002
zie-0.002
ue-0.002
Token shells
Token ID19679
Feature activation-3.75e-02

Pos logit contributions
 asks+0.014
 meets+0.013
Jason+0.013
 writes+0.012
Ryan+0.012
Neg logit contributions
quet-0.015
comb-0.013
isy-0.012
lights-0.011
ue-0.011
Token and
Token ID290
Feature activation-7.74e-03

Pos logit contributions
 asks+0.060
 meets+0.058
Jason+0.056
 writes+0.055
 pret+0.053
Neg logit contributions
quet-0.073
comb-0.062
isy-0.059
ue-0.054
zie-0.053
Token seaw
Token ID32085
Feature activation-9.38e-02

Pos logit contributions
 asks+0.012
Jason+0.012
 meets+0.012
Ryan+0.012
Har+0.012
Neg logit contributions
quet-0.014
comb-0.012
isy-0.011
lights-0.011
 shade-0.011
Tokeneed
Token ID2308
Feature activation-5.11e-02

Pos logit contributions
 asks+0.139
 meets+0.131
Jason+0.128
 writes+0.119
Ryan+0.118
Neg logit contributions
quet-0.200
isy-0.167
comb-0.167
ue-0.148
lights-0.143
Token.
Token ID13
Feature activation-6.97e-03

Pos logit contributions
 asks+0.090
Jason+0.088
 meets+0.088
 writes+0.082
Ryan+0.082
Neg logit contributions
quet-0.091
comb-0.076
isy-0.073
ue-0.063
lights-0.063
Token They
Token ID1119
Feature activation+1.98e-02

Pos logit contributions
Jason+0.013
 meets+0.013
 asks+0.012
 yells+0.012
Har+0.012
Neg logit contributions
quet-0.010
ue-0.008
lights-0.008
 Sue-0.008
comb-0.008
Token find
Token ID1064
Feature activation-8.46e-03

Pos logit contributions
quet+0.033
comb+0.028
isy+0.027
ue+0.023
zie+0.023
Neg logit contributions
 asks-0.035
Jason-0.034
 meets-0.034
 writes-0.032
Ryan-0.032
Token a
Token ID257
Feature activation-2.42e-02

Pos logit contributions
 asks+0.015
 meets+0.014
Jason+0.014
 writes+0.013
Har+0.013
Neg logit contributions
quet-0.015
isy-0.012
comb-0.012
lights-0.011
 shade-0.010
Token cand
Token ID2658
Feature activation-2.42e-02

Pos logit contributions
 asks+0.039
Jason+0.038
 meets+0.037
Ryan+0.036
Har+0.035
Neg logit contributions
quet-0.040
comb-0.034
isy-0.031
lights-0.028
ue-0.027
Tokenies
Token ID444
Feature activation-4.67e-02

Pos logit contributions
 asks+0.057
 meets+0.055
Jason+0.055
 writes+0.053
Ready+0.053
Neg logit contributions
quet-0.030
comb-0.022
isy-0.021
lights-0.017
ue-0.016
Token and
Token ID290
Feature activation-3.23e-02

Pos logit contributions
 asks+0.085
Jason+0.081
 meets+0.081
 writes+0.077
 yells+0.076
Neg logit contributions
quet-0.083
comb-0.069
isy-0.065
ue-0.054
lights-0.054
Token fruits
Token ID15921
Feature activation-7.00e-02

Pos logit contributions
Jason+0.056
 asks+0.056
Ryan+0.055
 meets+0.054
Har+0.053
Neg logit contributions
quet-0.054
comb-0.047
isy-0.043
 shade-0.041
lights-0.039
Token and
Token ID290
Feature activation-2.02e-02

Pos logit contributions
 asks+0.121
 meets+0.117
Jason+0.116
 writes+0.111
 pret+0.109
Neg logit contributions
quet-0.129
comb-0.108
isy-0.102
ue-0.090
lights-0.087
Token vegetables
Token ID13701
Feature activation-9.29e-02

Pos logit contributions
Jason+0.037
Ryan+0.036
 asks+0.036
Jes+0.035
Har+0.035
Neg logit contributions
quet-0.032
comb-0.027
isy-0.026
 shade-0.025
lights-0.023
Token and
Token ID290
Feature activation-2.47e-02

Pos logit contributions
 asks+0.175
Jason+0.172
 meets+0.169
Ryan+0.163
 writes+0.160
Neg logit contributions
quet-0.158
comb-0.132
isy-0.119
lights-0.098
ue-0.097
Token letters
Token ID7475
Feature activation-5.17e-02

Pos logit contributions
Jason+0.045
Ryan+0.045
 asks+0.044
Har+0.043
Jes+0.042
Neg logit contributions
quet-0.039
comb-0.033
isy-0.031
 shade-0.030
lights-0.028
Token and
Token ID290
Feature activation-1.69e-02

Pos logit contributions
 asks+0.096
Jason+0.093
 meets+0.092
 pret+0.086
Ryan+0.086
Neg logit contributions
quet-0.090
comb-0.073
isy-0.069
ue-0.059
lights-0.059
Token numbers
Token ID3146
Feature activation-5.67e-02

Pos logit contributions
Jason+0.030
Ryan+0.030
 asks+0.030
 meets+0.029
Har+0.029
Neg logit contributions
quet-0.028
comb-0.023
isy-0.022
 shade-0.021
 ray-0.019
Token and
Token ID290
Feature activation-1.74e-02

Pos logit contributions
 asks+0.111
Jason+0.109
 meets+0.108
Ryan+0.102
Har+0.101
Neg logit contributions
quet-0.092
comb-0.073
isy-0.068
lights-0.059
 as-0.057
Token saw
Token ID2497
Feature activation-1.87e-02

Pos logit contributions
 asks+0.012
Jason+0.012
 meets+0.012
 writes+0.011
 yells+0.011
Neg logit contributions
quet-0.013
comb-0.011
isy-0.011
ue-0.010
zie-0.009
Token five
Token ID1936
Feature activation+3.00e-03

Pos logit contributions
Jason+0.039
Har+0.037
Ryan+0.036
 meets+0.036
 asks+0.036
Neg logit contributions
quet-0.025
isy-0.019
comb-0.019
lights-0.018
 shade-0.018
Token fish
Token ID5916
Feature activation-2.74e-02

Pos logit contributions
quet+0.006
isy+0.005
comb+0.005
lights+0.004
ue+0.004
Neg logit contributions
Jason-0.005
 asks-0.005
 meets-0.005
Ryan-0.005
 writes-0.005
Token and
Token ID290
Feature activation-6.48e-03

Pos logit contributions
 asks+0.050
 meets+0.049
Jason+0.048
 writes+0.047
 pret+0.045
Neg logit contributions
quet-0.047
comb-0.039
isy-0.037
ue-0.033
zie-0.031
Token seven
Token ID3598
Feature activation-2.11e-02

Pos logit contributions
Jason+0.011
Ryan+0.010
Har+0.010
 asks+0.010
rev+0.010
Neg logit contributions
quet-0.011
comb-0.010
isy-0.009
 as-0.008
 shade-0.008
Token seaw
Token ID32085
Feature activation-9.26e-02

Pos logit contributions
Jason+0.040
Ryan+0.039
Ready+0.038
Thomas+0.037
Har+0.037
Neg logit contributions
quet-0.032
isy-0.026
ue-0.025
 as-0.024
lights-0.024
Tokeneed
Token ID2308
Feature activation-4.56e-02

Pos logit contributions
 asks+0.138
 meets+0.131
Jason+0.127
 writes+0.120
 yells+0.118
Neg logit contributions
quet-0.195
comb-0.167
isy-0.165
ue-0.149
immer-0.137
Token.
Token ID13
Feature activation+1.43e-03

Pos logit contributions
 asks+0.082
Jason+0.081
 meets+0.080
 writes+0.075
Ryan+0.074
Neg logit contributions
quet-0.080
comb-0.067
isy-0.064
ue-0.056
lights-0.054
Token They
Token ID1119
Feature activation+2.43e-02

Pos logit contributions
quet+0.002
ue+0.002
 Sue+0.002
comb+0.001
 Betty+0.001
Neg logit contributions
 meets-0.003
Jason-0.003
 risking-0.003
 asks-0.003
Har-0.003
Token were
Token ID547
Feature activation+1.60e-02

Pos logit contributions
quet+0.047
comb+0.040
isy+0.039
ue+0.035
zie+0.033
Neg logit contributions
 asks-0.038
 meets-0.037
Jason-0.037
 writes-0.035
 pret-0.034
Token happy
Token ID3772
Feature activation+2.66e-02

Pos logit contributions
quet+0.031
comb+0.026
isy+0.025
ue+0.023
zie+0.022
Neg logit contributions
 asks-0.028
 meets-0.026
 writes-0.025
Jason-0.024
 pret-0.024
Token of
Token ID286
Feature activation+2.83e-02

Pos logit contributions
comb+0.062
quet+0.061
ue+0.049
zie+0.046
isy+0.044
Neg logit contributions
 asks-0.087
 points-0.083
 meets-0.082
 yells-0.080
 shouts-0.079
Token shells
Token ID19679
Feature activation-2.32e-02

Pos logit contributions
quet+0.042
isy+0.035
ie+0.033
 shade+0.033
lights+0.032
Neg logit contributions
Jason-0.054
 asks-0.051
 meets-0.051
 writes-0.050
Ryan-0.049
Token,
Token ID11
Feature activation-4.45e-04

Pos logit contributions
 asks+0.041
 meets+0.040
Jason+0.038
 writes+0.038
 pret+0.037
Neg logit contributions
quet-0.040
comb-0.033
isy-0.032
ue-0.029
zie-0.028
Token rocks
Token ID12586
Feature activation-2.60e-02

Pos logit contributions
 asks+0.001
Jason+0.001
 meets+0.001
 writes+0.001
Ryan+0.001
Neg logit contributions
quet-0.001
comb-0.001
isy-0.001
lights-0.001
ue-0.001
Token and
Token ID290
Feature activation-1.09e-03

Pos logit contributions
 asks+0.049
 meets+0.048
Jason+0.046
 writes+0.046
 pret+0.045
Neg logit contributions
quet-0.042
comb-0.035
isy-0.033
ue-0.029
zie-0.028
Token seaw
Token ID32085
Feature activation-9.23e-02

Pos logit contributions
 asks+0.002
Jason+0.002
 meets+0.002
Ryan+0.002
 writes+0.002
Neg logit contributions
quet-0.002
isy-0.002
comb-0.002
lights-0.001
 shade-0.001
Tokeneed
Token ID2308
Feature activation-4.91e-02

Pos logit contributions
 asks+0.145
 meets+0.136
Jason+0.133
 writes+0.126
 yells+0.123
Neg logit contributions
quet-0.191
isy-0.161
comb-0.159
ue-0.141
immer-0.135
Token,
Token ID11
Feature activation-1.76e-02

Pos logit contributions
 asks+0.088
 meets+0.085
Jason+0.083
 writes+0.081
 pret+0.079
Neg logit contributions
quet-0.087
comb-0.072
isy-0.069
ue-0.061
zie-0.059
Token but
Token ID475
Feature activation+5.22e-03

Pos logit contributions
 asks+0.035
Jason+0.034
 meets+0.034
 writes+0.033
Ryan+0.032
Neg logit contributions
quet-0.027
comb-0.022
isy-0.021
ue-0.017
zie-0.017
Token Jane
Token ID12091
Feature activation-1.99e-02

Pos logit contributions
quet+0.011
isy+0.009
comb+0.008
ue+0.008
lights+0.007
Neg logit contributions
 asks-0.008
 meets-0.008
 sees-0.007
 writes-0.007
 met-0.007
Token was
Token ID373
Feature activation+5.88e-03

Pos logit contributions
 asks+0.031
 meets+0.030
Jason+0.030
 writes+0.029
 pret+0.028
Neg logit contributions
quet-0.039
comb-0.034
isy-0.033
ue-0.029
zie-0.029
Token sound
Token ID2128
Feature activation+5.11e-03

Pos logit contributions
quet+0.002
comb+0.002
isy+0.002
zie+0.002
lights+0.002
Neg logit contributions
 pret-0.002
 asks-0.002
 writes-0.002
 meets-0.002
 sees-0.002
Token,
Token ID11
Feature activation-6.58e-03

Pos logit contributions
quet+0.009
comb+0.008
isy+0.007
ue+0.007
zie+0.006
Neg logit contributions
 asks-0.009
 meets-0.009
 writes-0.008
Jason-0.008
 pret-0.008
Token louder
Token ID27089
Feature activation-2.39e-02

Pos logit contributions
 asks+0.013
 meets+0.013
Jason+0.013
Har+0.012
 writes+0.012
Neg logit contributions
quet-0.010
comb-0.008
isy-0.008
ue-0.007
lights-0.007
Token than
Token ID621
Feature activation-2.16e-02

Pos logit contributions
 asks+0.044
 meets+0.043
Jason+0.042
 writes+0.040
Ryan+0.039
Neg logit contributions
quet-0.041
comb-0.034
isy-0.033
ue-0.028
zie-0.027
Token his
Token ID465
Feature activation-3.41e-02

Pos logit contributions
 asks+0.042
 meets+0.041
Jason+0.040
 writes+0.039
Har+0.038
Neg logit contributions
quet-0.034
comb-0.028
isy-0.027
zie-0.023
lights-0.022
Token usual
Token ID6678
Feature activation-9.18e-02

Pos logit contributions
 asks+0.064
 meets+0.062
Jason+0.062
 writes+0.059
Ryan+0.058
Neg logit contributions
quet-0.057
comb-0.047
isy-0.045
ue-0.040
zie-0.038
Token snap
Token ID11495
Feature activation-2.73e-02

Pos logit contributions
 asks+0.181
 meets+0.175
Jason+0.173
 writes+0.165
Ryan+0.164
Neg logit contributions
quet-0.146
comb-0.124
isy-0.117
ue-0.101
zie-0.097
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
 asks+0.048
 meets+0.047
Jason+0.046
 writes+0.044
 pret+0.043
Neg logit contributions
quet-0.049
comb-0.041
isy-0.039
ue-0.035
zie-0.034
Token The
Token ID383
Feature activation+4.76e-03

Pos logit contributions
Jason+0.021
 meets+0.021
 pret+0.020
Ryan+0.020
 jury+0.020
Neg logit contributions
quet-0.019
ue-0.016
comb-0.015
 Betty-0.015
isy-0.015
Token man
Token ID582
Feature activation-1.56e-02

Pos logit contributions
quet+0.009
isy+0.008
comb+0.008
ue+0.007
 end+0.007
Neg logit contributions
 asks-0.007
 meets-0.007
Jason-0.007
Ryan-0.007
Har-0.007
Token was
Token ID373
Feature activation+8.31e-03

Pos logit contributions
 asks+0.022
 meets+0.021
Jason+0.020
 writes+0.020
 pret+0.019
Neg logit contributions
quet-0.033
comb-0.029
isy-0.028
ue-0.025
zie-0.025
Token see
Token ID766
Feature activation-1.41e-02

Pos logit contributions
quet+0.036
comb+0.033
isy+0.030
zie+0.028
 end+0.028
Neg logit contributions
Jason-0.037
 asks-0.036
 meets-0.036
Ryan-0.035
 writes-0.035
Token shells
Token ID19679
Feature activation-2.51e-02

Pos logit contributions
Jason+0.026
 asks+0.025
 meets+0.025
Ryan+0.025
Har+0.024
Neg logit contributions
quet-0.021
 shade-0.018
isy-0.017
comb-0.017
lights-0.017
Token,
Token ID11
Feature activation-1.51e-03

Pos logit contributions
 asks+0.044
 meets+0.043
 sees+0.041
 writes+0.041
 pret+0.040
Neg logit contributions
quet-0.045
comb-0.037
isy-0.036
ue-0.032
zie-0.032
Token rocks
Token ID12586
Feature activation-2.49e-02

Pos logit contributions
 asks+0.002
 meets+0.002
Jason+0.002
 writes+0.002
Ryan+0.002
Neg logit contributions
quet-0.003
comb-0.003
isy-0.003
lights-0.002
ue-0.002
Token,
Token ID11
Feature activation-1.16e-02

Pos logit contributions
 asks+0.046
 meets+0.044
 writes+0.042
 sees+0.042
 pret+0.041
Neg logit contributions
quet-0.043
comb-0.035
isy-0.034
ue-0.030
zie-0.030
Token seaw
Token ID32085
Feature activation-9.18e-02

Pos logit contributions
 asks+0.017
 meets+0.016
Jason+0.016
 writes+0.015
Ryan+0.015
Neg logit contributions
quet-0.024
comb-0.021
isy-0.020
ue-0.018
zie-0.018
Tokeneed
Token ID2308
Feature activation-4.90e-02

Pos logit contributions
 asks+0.135
 meets+0.126
Jason+0.123
 writes+0.117
 yells+0.114
Neg logit contributions
quet-0.195
comb-0.166
isy-0.166
ue-0.149
lights-0.140
Token,
Token ID11
Feature activation-1.91e-02

Pos logit contributions
 asks+0.100
 meets+0.097
Jason+0.094
 writes+0.093
 pret+0.091
Neg logit contributions
quet-0.074
comb-0.059
isy-0.057
ue-0.049
zie-0.047
Token crabs
Token ID49172
Feature activation-5.54e-02

Pos logit contributions
 asks+0.034
 meets+0.033
Jason+0.033
 writes+0.032
 pret+0.031
Neg logit contributions
quet-0.033
comb-0.028
isy-0.027
ue-0.023
zie-0.023
Token and
Token ID290
Feature activation-1.72e-02

Pos logit contributions
 asks+0.120
 meets+0.117
Jason+0.116
 writes+0.112
 pret+0.110
Neg logit contributions
quet-0.076
comb-0.060
isy-0.057
ue-0.048
zie-0.045
Token fish
Token ID5916
Feature activation-6.27e-02

Pos logit contributions
Jason+0.028
 asks+0.027
Ryan+0.027
 meets+0.026
Har+0.026
Neg logit contributions
quet-0.030
comb-0.026
isy-0.025
 shade-0.024
lights-0.023
Token and
Token ID290
Feature activation-2.34e-02

Pos logit contributions
 asks+0.040
 meets+0.039
 writes+0.037
Jason+0.037
 pret+0.036
Neg logit contributions
quet-0.042
comb-0.035
isy-0.034
ue-0.030
zie-0.029
Token the
Token ID262
Feature activation-3.27e-02

Pos logit contributions
Jason+0.040
 asks+0.040
 meets+0.038
Ryan+0.038
 writes+0.037
Neg logit contributions
quet-0.040
comb-0.035
isy-0.033
ue-0.029
lights-0.029
Token crabs
Token ID49172
Feature activation-4.44e-02

Pos logit contributions
 asks+0.062
Jason+0.061
Ryan+0.060
Har+0.059
 writes+0.059
Neg logit contributions
quet-0.046
comb-0.041
 shade-0.040
isy-0.040
 end-0.038
Token and
Token ID290
Feature activation-2.63e-02

Pos logit contributions
 asks+0.078
Jason+0.076
 meets+0.075
 writes+0.072
Ryan+0.072
Neg logit contributions
quet-0.079
comb-0.067
isy-0.063
ue-0.054
lights-0.052
Token the
Token ID262
Feature activation-4.03e-02

Pos logit contributions
Jason+0.046
 asks+0.045
 meets+0.044
Ryan+0.043
 writes+0.042
Neg logit contributions
quet-0.045
comb-0.039
isy-0.036
ue-0.031
zie-0.031
Token seaw
Token ID32085
Feature activation-9.04e-02

Pos logit contributions
 asks+0.075
Jason+0.074
Ryan+0.072
Har+0.072
 writes+0.071
Neg logit contributions
quet-0.058
comb-0.052
 shade-0.050
isy-0.050
 end-0.048
Tokeneed
Token ID2308
Feature activation-4.71e-02

Pos logit contributions
 asks+0.135
 meets+0.126
Jason+0.124
 writes+0.119
 yells+0.115
Neg logit contributions
quet-0.191
comb-0.166
isy-0.165
ue-0.145
immer-0.138
Token.
Token ID13
Feature activation-8.36e-03

Pos logit contributions
 asks+0.081
Jason+0.078
 meets+0.078
 writes+0.074
Ryan+0.073
Neg logit contributions
quet-0.086
comb-0.073
isy-0.070
ue-0.061
lights-0.059
Token
Token ID198
Feature activation-6.81e-03

Pos logit contributions
 asks+0.012
Jason+0.012
 meets+0.012
 writes+0.011
 pret+0.011
Neg logit contributions
quet-0.017
comb-0.014
ue-0.014
isy-0.013
lights-0.013
Token
Token ID198
Feature activation+4.77e-03

Pos logit contributions
 asks+0.009
Jason+0.009
 meets+0.008
 pret+0.008
 writes+0.008
Neg logit contributions
quet-0.014
isy-0.013
comb-0.012
ue-0.012
zie-0.011
TokenSam
Token ID16305
Feature activation+5.12e-03

Pos logit contributions
quet+0.010
comb+0.009
isy+0.008
zie+0.007
ue+0.007
Neg logit contributions
 asks-0.007
 meets-0.007
Jason-0.006
 writes-0.006
 sees-0.006
Token sorry
Token ID7926
Feature activation+6.77e-03

Pos logit contributions
quet+0.003
comb+0.003
isy+0.003
ue+0.002
zie+0.002
Neg logit contributions
 asks-0.004
 meets-0.004
Jason-0.004
 writes-0.004
 pret-0.003
Token,
Token ID11
Feature activation-3.04e-03

Pos logit contributions
quet+0.011
comb+0.009
isy+0.009
ue+0.008
zie+0.007
Neg logit contributions
 asks-0.013
 meets-0.013
Jason-0.012
 writes-0.012
 pret-0.012
Token that
Token ID326
Feature activation+3.11e-03

Pos logit contributions
 asks+0.005
 meets+0.005
Jason+0.005
 writes+0.004
 pret+0.004
Neg logit contributions
quet-0.006
comb-0.005
isy-0.005
ue-0.004
zie-0.004
Token's
Token ID338
Feature activation-1.91e-02

Pos logit contributions
quet+0.005
isy+0.004
comb+0.004
 end+0.004
 of+0.004
Neg logit contributions
Jason-0.005
 loudspe-0.005
Daniel-0.005
Har-0.005
Ryan-0.005
Token not
Token ID407
Feature activation+6.45e-03

Pos logit contributions
 asks+0.034
 meets+0.032
Jason+0.032
 writes+0.031
 pret+0.030
Neg logit contributions
quet-0.035
comb-0.029
isy-0.028
ue-0.025
zie-0.024
Token possible
Token ID1744
Feature activation-8.86e-02

Pos logit contributions
quet+0.010
comb+0.008
isy+0.008
 as+0.007
ue+0.007
Neg logit contributions
 asks-0.013
 meets-0.012
Jason-0.012
 writes-0.012
 pret-0.011
Token."
Token ID526
Feature activation-5.52e-03

Pos logit contributions
Jason+0.166
 asks+0.160
 writes+0.159
 meets+0.158
Check+0.158
Neg logit contributions
quet-0.140
comb-0.125
isy-0.117
ue-0.098
ie-0.096
Token
Token ID220
Feature activation-1.01e-02

Pos logit contributions
 meets+0.010
Jason+0.010
 asks+0.010
Jes+0.009
 risking+0.009
Neg logit contributions
quet-0.008
ue-0.007
comb-0.006
 as-0.006
isy-0.006
Token
Token ID198
Feature activation-5.72e-03

Pos logit contributions
 pret+0.018
 writes+0.017
 jury+0.017
Check+0.017
Jason+0.017
Neg logit contributions
quet-0.014
ue-0.013
comb-0.012
 of-0.011
isy-0.011
Token
Token ID198
Feature activation+4.05e-03

Pos logit contributions
 pret+0.010
 writes+0.010
 asks+0.010
 meets+0.010
 wants+0.009
Neg logit contributions
quet-0.009
ue-0.008
isy-0.008
 of-0.006
 Betty-0.006
TokenThe
Token ID464
Feature activation+7.13e-03

Pos logit contributions
quet+0.007
isy+0.005
ue+0.005
comb+0.005
zie+0.004
Neg logit contributions
 asks-0.008
 meets-0.008
 pret-0.008
 writes-0.007
Jason-0.007
Token of
Token ID286
Feature activation+2.87e-02

Pos logit contributions
Jason+0.032
 meets+0.032
 asks+0.032
 writes+0.031
 pret+0.031
Neg logit contributions
quet-0.015
isy-0.011
comb-0.011
lights-0.008
ue-0.008
Token effort
Token ID3626
Feature activation-2.81e-03

Pos logit contributions
quet+0.043
isy+0.034
comb+0.033
 surely+0.027
 ray+0.027
Neg logit contributions
 asks-0.055
 meets-0.055
Jason-0.054
 pret-0.052
 writes-0.052
Token,
Token ID11
Feature activation+6.98e-03

Pos logit contributions
 asks+0.006
Jason+0.006
 meets+0.006
 writes+0.006
 pret+0.006
Neg logit contributions
quet-0.004
comb-0.003
isy-0.003
lights-0.002
ue-0.002
Token it
Token ID340
Feature activation-1.36e-02

Pos logit contributions
quet+0.012
comb+0.010
isy+0.009
ue+0.008
 surely+0.008
Neg logit contributions
 asks-0.012
Jason-0.012
 meets-0.012
 writes-0.012
 pret-0.011
Token's
Token ID338
Feature activation-1.78e-02

Pos logit contributions
 asks+0.017
Jason+0.017
 meets+0.016
 writes+0.016
Ryan+0.015
Neg logit contributions
quet-0.030
comb-0.026
isy-0.026
ue-0.023
zie-0.023
Token possible
Token ID1744
Feature activation-8.80e-02

Pos logit contributions
 asks+0.032
 meets+0.031
Jason+0.030
 writes+0.029
 pret+0.028
Neg logit contributions
quet-0.032
comb-0.027
isy-0.026
ue-0.023
zie-0.022
Token to
Token ID284
Feature activation-8.05e-03

Pos logit contributions
 asks+0.155
Jason+0.151
 meets+0.150
 writes+0.146
 pret+0.145
Neg logit contributions
quet-0.150
comb-0.131
isy-0.123
ue-0.105
zie-0.103
Token make
Token ID787
Feature activation+7.76e-03

Pos logit contributions
 asks+0.015
 meets+0.015
Jason+0.014
 writes+0.014
 pret+0.014
Neg logit contributions
quet-0.013
comb-0.011
isy-0.011
ue-0.009
zie-0.009
Token things
Token ID1243
Feature activation-1.52e-03

Pos logit contributions
quet+0.013
isy+0.011
comb+0.010
ie+0.009
ue+0.008
Neg logit contributions
 asks-0.014
 meets-0.013
Jason-0.013
 pret-0.013
Ready-0.013
Token better
Token ID1365
Feature activation-2.23e-02

Pos logit contributions
 asks+0.003
 meets+0.003
Jason+0.003
 writes+0.003
 pret+0.003
Neg logit contributions
quet-0.003
comb-0.002
isy-0.002
ue-0.002
zie-0.002
Token for
Token ID329
Feature activation-1.58e-02

Pos logit contributions
 asks+0.043
Jason+0.042
 meets+0.041
 writes+0.040
Ryan+0.040
Neg logit contributions
quet-0.035
comb-0.030
isy-0.028
ue-0.024
lights-0.023
Token "
Token ID366
Feature activation-2.03e-02

Pos logit contributions
 meets+0.012
 asks+0.012
Jason+0.011
 writes+0.011
Check+0.011
Neg logit contributions
quet-0.013
comb-0.011
isy-0.011
ue-0.009
zie-0.009
TokenYes
Token ID5297
Feature activation+1.82e-02

Pos logit contributions
 asks+0.039
 meets+0.039
 pret+0.038
Jason+0.037
 writes+0.037
Neg logit contributions
quet-0.034
isy-0.025
comb-0.025
ue-0.022
zie-0.020
Token,
Token ID11
Feature activation-2.23e-03

Pos logit contributions
quet+0.036
comb+0.031
isy+0.026
flower+0.026
lights+0.025
Neg logit contributions
 asks-0.027
 Daniel-0.026
 Ethan-0.024
 yells-0.024
Jason-0.023
Token that
Token ID326
Feature activation+6.03e-03

Pos logit contributions
 asks+0.003
 yells+0.003
 pret+0.003
 Daniel+0.003
 meets+0.003
Neg logit contributions
quet-0.005
comb-0.004
isy-0.003
flower-0.003
zie-0.003
Token's
Token ID338
Feature activation-1.88e-02

Pos logit contributions
quet+0.013
comb+0.011
isy+0.011
ue+0.010
ie+0.010
Neg logit contributions
 asks-0.008
 meets-0.008
Jason-0.008
Ryan-0.007
Har-0.007
Token possible
Token ID1744
Feature activation-8.62e-02

Pos logit contributions
 asks+0.029
 meets+0.027
Jason+0.026
 writes+0.026
 pret+0.025
Neg logit contributions
quet-0.039
comb-0.033
isy-0.032
ue-0.029
zie-0.028
Token."
Token ID526
Feature activation-3.65e-03

Pos logit contributions
 asks+0.145
 meets+0.141
Jason+0.139
 writes+0.134
 pret+0.130
Neg logit contributions
quet-0.160
comb-0.137
isy-0.131
ue-0.116
zie-0.112
Token So
Token ID1406
Feature activation+9.62e-03

Pos logit contributions
 asks+0.006
 meets+0.006
 writes+0.006
Jason+0.006
 pret+0.006
Neg logit contributions
quet-0.007
comb-0.006
isy-0.006
ue-0.005
zie-0.005
Token Liz
Token ID28313
Feature activation+5.28e-02

Pos logit contributions
quet+0.020
comb+0.018
isy+0.017
umbs+0.015
immer+0.015
Neg logit contributions
 asks-0.014
 Daniel-0.013
 pret-0.012
 yells-0.012
 sees-0.012
Token put
Token ID1234
Feature activation+8.90e-03

Pos logit contributions
quet+0.099
comb+0.084
isy+0.082
ue+0.074
ie+0.071
Neg logit contributions
 asks-0.083
 meets-0.082
Jason-0.081
 yells-0.076
Ryan-0.076
Token a
Token ID257
Feature activation+1.53e-02

Pos logit contributions
quet+0.019
comb+0.017
isy+0.016
ue+0.015
zie+0.014
Neg logit contributions
 asks-0.013
 meets-0.012
 writes-0.012
Jason-0.012
 pret-0.011
Token
Token ID198
Feature activation+1.08e-02

Pos logit contributions
quet+0.003
isy+0.003
comb+0.003
ue+0.003
zie+0.002
Neg logit contributions
 asks-0.002
 meets-0.002
 writes-0.002
 pret-0.002
Jason-0.001
TokenThe
Token ID464
Feature activation+6.42e-03

Pos logit contributions
quet+0.018
comb+0.015
isy+0.014
ue+0.013
zie+0.012
Neg logit contributions
 asks-0.020
 meets-0.019
Jason-0.019
 writes-0.018
Ryan-0.018
Token moral
Token ID6573
Feature activation+1.58e-02

Pos logit contributions
quet+0.012
comb+0.010
isy+0.009
ue+0.009
lights+0.009
Neg logit contributions
 asks-0.011
 meets-0.010
Jason-0.010
 sees-0.009
 writes-0.009
Token of
Token ID286
Feature activation+1.82e-02

Pos logit contributions
quet+0.015
comb+0.010
isy+0.009
ue+0.007
zie+0.006
Neg logit contributions
 asks-0.042
 meets-0.041
Jason-0.040
 writes-0.039
 pret-0.039
Token the
Token ID262
Feature activation+6.32e-03

Pos logit contributions
quet+0.040
comb+0.034
isy+0.032
ue+0.030
lights+0.029
Neg logit contributions
 asks-0.026
 meets-0.025
Jason-0.024
 writes-0.023
 pret-0.022
Token story
Token ID1621
Feature activation+5.07e-02

Pos logit contributions
quet+0.012
comb+0.011
isy+0.009
ue+0.009
lights+0.009
Neg logit contributions
 asks-0.010
 meets-0.010
Jason-0.009
 writes-0.009
 pret-0.009
Token is
Token ID318
Feature activation+2.67e-02

Pos logit contributions
quet+0.135
comb+0.119
isy+0.117
zie+0.106
ue+0.104
Neg logit contributions
 asks-0.048
 meets-0.044
 writes-0.041
Jason-0.038
 sees-0.038
Token that
Token ID326
Feature activation+2.61e-02

Pos logit contributions
quet+0.046
comb+0.038
isy+0.035
ue+0.032
lights+0.031
Neg logit contributions
 asks-0.051
 meets-0.049
Jason-0.046
 writes-0.046
 yells-0.044
Token it
Token ID340
Feature activation-7.34e-04

Pos logit contributions
quet+0.049
comb+0.041
isy+0.040
ue+0.035
zie+0.034
Neg logit contributions
 asks-0.043
 meets-0.042
Jason-0.042
 writes-0.040
 pret-0.039
Token is
Token ID318
Feature activation+1.42e-02

Pos logit contributions
Jason+0.001
 asks+0.001
 meets+0.001
 writes+0.001
Ryan+0.001
Neg logit contributions
quet-0.002
comb-0.001
isy-0.001
ue-0.001
zie-0.001
Token always
Token ID1464
Feature activation-2.36e-02

Pos logit contributions
quet+0.027
comb+0.023
isy+0.022
ue+0.020
zie+0.019
Neg logit contributions
 asks-0.023
 meets-0.022
Jason-0.022
 writes-0.021
 pret-0.021
Token
Token ID198
Feature activation+6.25e-03

Pos logit contributions
 pret+0.005
 asks+0.005
 meets+0.004
 writes+0.004
Jason+0.004
Neg logit contributions
quet-0.006
ue-0.005
isy-0.005
comb-0.004
 Betty-0.004
TokenThe
Token ID464
Feature activation+3.39e-03

Pos logit contributions
quet+0.012
isy+0.009
ue+0.009
comb+0.009
zie+0.008
Neg logit contributions
 asks-0.011
 meets-0.011
 pret-0.011
 writes-0.010
Jason-0.010
Token moral
Token ID6573
Feature activation+1.19e-02

Pos logit contributions
quet+0.005
isy+0.004
comb+0.004
 end+0.004
ue+0.004
Neg logit contributions
 asks-0.006
 meets-0.006
Jason-0.006
 writes-0.006
 Daniel-0.006
Token of
Token ID286
Feature activation+1.50e-02

Pos logit contributions
quet+0.011
comb+0.007
isy+0.006
ue+0.005
zie+0.004
Neg logit contributions
 asks-0.032
 meets-0.031
Jason-0.031
 writes-0.030
 pret-0.030
Token the
Token ID262
Feature activation+3.72e-03

Pos logit contributions
quet+0.031
comb+0.026
isy+0.025
ue+0.023
lights+0.022
Neg logit contributions
 asks-0.022
 meets-0.022
Jason-0.021
 writes-0.020
 pret-0.020
Token story
Token ID1621
Feature activation+5.11e-02

Pos logit contributions
quet+0.006
isy+0.005
comb+0.005
ue+0.004
zie+0.004
Neg logit contributions
 asks-0.007
 meets-0.007
Jason-0.007
 writes-0.007
 pret-0.007
Token is
Token ID318
Feature activation+2.47e-02

Pos logit contributions
quet+0.132
comb+0.116
isy+0.113
ue+0.103
zie+0.103
Neg logit contributions
 asks-0.052
 meets-0.048
 writes-0.045
Jason-0.043
 pret-0.041
Token that
Token ID326
Feature activation+2.68e-02

Pos logit contributions
quet+0.038
comb+0.030
isy+0.029
ue+0.025
zie+0.024
Neg logit contributions
 asks-0.051
 meets-0.049
Jason-0.048
 writes-0.047
 pret-0.046
Token powerful
Token ID3665
Feature activation-1.56e-02

Pos logit contributions
quet+0.041
comb+0.035
isy+0.033
 surely+0.029
 Betty+0.028
Neg logit contributions
Jason-0.049
 asks-0.048
 meets-0.048
Ryan-0.047
Har-0.046
Token machines
Token ID8217
Feature activation-1.36e-02

Pos logit contributions
Jason+0.024
 asks+0.024
 meets+0.023
Har+0.023
Ryan+0.022
Neg logit contributions
quet-0.029
comb-0.024
isy-0.024
lights-0.022
zie-0.021
Token must
Token ID1276
Feature activation+3.18e-03

Pos logit contributions
Jason+0.020
 asks+0.020
 meets+0.019
Har+0.018
 writes+0.018
Neg logit contributions
quet-0.027
comb-0.023
isy-0.022
ue-0.020
lights-0.020
TokenThe
Token ID464
Feature activation+1.19e-03

Pos logit contributions
 asks+0.001
 meets+0.001
 pret+0.001
 writes+0.001
 Ethan+0.001
Neg logit contributions
quet-0.001
isy-0.001
ue-0.001
comb-0.001
lights-0.001
Token dog
Token ID3290
Feature activation+1.71e-04

Pos logit contributions
quet+0.002
isy+0.002
comb+0.002
ue+0.002
 cushion+0.002
Neg logit contributions
 meets-0.002
 asks-0.002
Jason-0.002
 writes-0.002
 pret-0.001
Token nodded
Token ID14464
Feature activation+3.56e-03

Pos logit contributions
quet+0.000
comb+0.000
isy+0.000
ue+0.000
zie+0.000
Neg logit contributions
 asks-0.000
 meets-0.000
Jason-0.000
 writes-0.000
 pret-0.000
Token and
Token ID290
Feature activation-4.87e-03

Pos logit contributions
quet+0.007
comb+0.006
isy+0.005
ue+0.005
zie+0.005
Neg logit contributions
 asks-0.006
 meets-0.006
Jason-0.006
 writes-0.005
 pret-0.005
Token w
Token ID266
Feature activation-3.08e-02

Pos logit contributions
 asks+0.007
 meets+0.007
Jason+0.006
 writes+0.006
 pret+0.006
Neg logit contributions
quet-0.011
comb-0.009
isy-0.009
ue-0.008
zie-0.008
Tokenagged
Token ID14655
Feature activation+5.23e-02

Pos logit contributions
 asks+0.062
 meets+0.060
Jason+0.059
 writes+0.058
 pret+0.057
Neg logit contributions
quet-0.048
comb-0.039
isy-0.036
ue-0.032
zie-0.030
Token his
Token ID465
Feature activation-2.40e-02

Pos logit contributions
quet+0.150
comb+0.129
isy+0.127
immer+0.113
ue+0.112
Neg logit contributions
 asks-0.049
 writes-0.040
 yells-0.039
 pret-0.039
 shouts-0.038
Token tail
Token ID7894
Feature activation-1.66e-02

Pos logit contributions
 asks+0.036
 meets+0.034
Jason+0.033
 sees+0.033
 pret+0.033
Neg logit contributions
quet-0.051
comb-0.042
isy-0.039
ue-0.036
zie-0.036
Token.
Token ID13
Feature activation+8.19e-03

Pos logit contributions
 asks+0.023
 meets+0.022
 writes+0.021
Jason+0.020
 pret+0.020
Neg logit contributions
quet-0.036
comb-0.031
isy-0.029
ue-0.028
zie-0.028
Token He
Token ID679
Feature activation-7.80e-03

Pos logit contributions
quet+0.013
comb+0.011
ue+0.011
isy+0.010
 Sue+0.010
Neg logit contributions
 meets-0.013
Jason-0.013
 asks-0.013
 writes-0.013
Har-0.013
Token gave
Token ID2921
Feature activation-6.58e-03

Pos logit contributions
 asks+0.012
Jason+0.012
 meets+0.011
 writes+0.011
Ryan+0.011
Neg logit contributions
quet-0.015
comb-0.013
isy-0.013
ue-0.012
zie-0.011
Token,
Token ID11
Feature activation+4.49e-03

Pos logit contributions
quet+0.024
comb+0.021
isy+0.018
lights+0.018
imm+0.018
Neg logit contributions
 asks-0.018
 meets-0.017
Jason-0.017
 St-0.016
 sees-0.016
Token Tim
Token ID5045
Feature activation-2.56e-03

Pos logit contributions
quet+0.008
comb+0.007
lights+0.006
immer+0.006
isy+0.005
Neg logit contributions
 asks-0.009
 yells-0.008
 wants-0.008
 sees-0.008
 Hon-0.008
Token!"
Token ID2474
Feature activation-1.12e-02

Pos logit contributions
 asks+0.004
 meets+0.004
Jason+0.004
 writes+0.004
 pret+0.004
Neg logit contributions
quet-0.005
comb-0.004
isy-0.004
lights-0.004
ue-0.004
Token
Token ID198
Feature activation-7.30e-03

Pos logit contributions
 asks+0.012
 meets+0.011
 writes+0.010
 yells+0.010
Jason+0.010
Neg logit contributions
quet-0.028
comb-0.025
isy-0.024
lights-0.022
immer-0.022
Token
Token ID198
Feature activation+1.93e-03

Pos logit contributions
 asks+0.010
 meets+0.009
Jason+0.009
 writes+0.009
 pret+0.009
Neg logit contributions
quet-0.016
isy-0.014
comb-0.014
ue-0.013
zie-0.012
TokenFrom
Token ID4863
Feature activation+5.47e-02

Pos logit contributions
quet+0.004
comb+0.004
isy+0.003
lights+0.003
zie+0.003
Neg logit contributions
 asks-0.003
Jason-0.002
 meets-0.002
Ryan-0.002
Ready-0.002
Token that
Token ID326
Feature activation+3.87e-02

Pos logit contributions
quet+0.106
comb+0.093
isy+0.078
ue+0.073
zie+0.073
Neg logit contributions
 asks-0.092
 writes-0.083
 meets-0.083
Jason-0.082
 sees-0.081
Token day
Token ID1110
Feature activation+2.73e-02

Pos logit contributions
quet+0.064
comb+0.052
isy+0.048
lights+0.043
ue+0.043
Neg logit contributions
 asks-0.076
 meets-0.074
Jason-0.072
 writes-0.071
 pret-0.069
Token on
Token ID319
Feature activation+2.24e-02

Pos logit contributions
quet+0.075
comb+0.067
isy+0.065
lights+0.064
zie+0.061
Neg logit contributions
 asks-0.020
 meets-0.018
-0.018
Jes-0.017
 sees-0.016
Token,
Token ID11
Feature activation+2.33e-02

Pos logit contributions
quet+0.048
comb+0.040
isy+0.038
immer+0.035
lights+0.033
Neg logit contributions
 asks-0.034
 meets-0.031
 sees-0.031
-0.029
 yells-0.028
Token Tim
Token ID5045
Feature activation+4.57e-03

Pos logit contributions
quet+0.045
comb+0.038
immer+0.035
isy+0.034
lights+0.030
Neg logit contributions
 asks-0.041
 wants-0.038
 meets-0.037
 sees-0.037
-0.037
Token down
Token ID866
Feature activation-5.74e-03

Pos logit contributions
quet+0.024
isy+0.020
comb+0.020
ue+0.018
zie+0.017
Neg logit contributions
 asks-0.017
 meets-0.017
 sees-0.016
Jason-0.016
 writes-0.016
Token and
Token ID290
Feature activation+9.63e-03

Pos logit contributions
 asks+0.009
 meets+0.008
 writes+0.008
Jason+0.008
 pret+0.008
Neg logit contributions
quet-0.012
isy-0.010
comb-0.010
ue-0.009
zie-0.009
Token ate
Token ID15063
Feature activation+1.41e-02

Pos logit contributions
quet+0.019
comb+0.016
isy+0.016
ue+0.014
zie+0.014
Neg logit contributions
 asks-0.015
 meets-0.014
Jason-0.014
 writes-0.013
Ryan-0.013
Token the
Token ID262
Feature activation+2.55e-02

Pos logit contributions
quet+0.029
comb+0.025
isy+0.024
ue+0.022
zie+0.021
Neg logit contributions
 asks-0.021
 meets-0.020
 writes-0.020
Jason-0.019
 pret-0.019
Token y
Token ID331
Feature activation+3.47e-02

Pos logit contributions
quet+0.048
isy+0.042
comb+0.041
ue+0.035
zie+0.035
Neg logit contributions
 asks-0.042
 meets-0.038
Jason-0.037
Har-0.037
 writes-0.036
Tokenummy
Token ID13513
Feature activation+5.08e-02

Pos logit contributions
quet+0.050
comb+0.042
isy+0.040
zie+0.031
ue+0.029
Neg logit contributions
 asks-0.070
 writes-0.067
 meets-0.067
Jason-0.065
 sees-0.063
Token pasta
Token ID26296
Feature activation+1.24e-02

Pos logit contributions
quet+0.119
comb+0.104
isy+0.100
ue+0.093
zie+0.090
Neg logit contributions
 asks-0.062
 meets-0.059
Jason-0.057
 writes-0.057
 pret-0.055
Token together
Token ID1978
Feature activation+3.15e-02

Pos logit contributions
quet+0.026
isy+0.022
zie+0.022
comb+0.021
ue+0.021
Neg logit contributions
 pret-0.014
 writes-0.013
 asks-0.013
 meets-0.013
 sees-0.013
Token.
Token ID13
Feature activation-2.49e-03

Pos logit contributions
quet+0.071
isy+0.060
comb+0.060
zie+0.057
ue+0.057
Neg logit contributions
 asks-0.036
 meets-0.033
 writes-0.033
Jason-0.033
 pret-0.032
Token Lucy
Token ID22162
Feature activation+7.55e-03

Pos logit contributions
 asks+0.003
 meets+0.003
Jason+0.003
 writes+0.003
 pret+0.003
Neg logit contributions
quet-0.006
comb-0.005
isy-0.005
ue-0.004
zie-0.004
Token's
Token ID338
Feature activation-2.07e-02

Pos logit contributions
quet+0.014
comb+0.012
isy+0.012
ue+0.010
zie+0.010
Neg logit contributions
 asks-0.012
 meets-0.012
Jason-0.012
 writes-0.011
Ready-0.011
Token to
Token ID284
Feature activation+1.22e-02

Pos logit contributions
Jason+0.004
 asks+0.004
 meets+0.004
Ryan+0.004
 writes+0.004
Neg logit contributions
quet-0.004
comb-0.004
isy-0.004
 Betty-0.003
ue-0.003
Token do
Token ID466
Feature activation+6.35e-03

Pos logit contributions
quet+0.029
comb+0.025
isy+0.024
lights+0.024
zie+0.022
Neg logit contributions
 asks-0.015
 meets-0.013
 writes-0.013
 yells-0.013
 sees-0.013
Token.
Token ID13
Feature activation+3.53e-04

Pos logit contributions
quet+0.012
comb+0.010
isy+0.009
ue+0.008
zie+0.008
Neg logit contributions
 asks-0.011
 meets-0.011
Jason-0.010
 writes-0.010
 pret-0.010
Token
Token ID220
Feature activation-9.37e-03

Pos logit contributions
quet+0.000
comb+0.000
isy+0.000
ue+0.000
zie+0.000
Neg logit contributions
 meets-0.001
Jason-0.001
 asks-0.001
 pret-0.001
 writes-0.001
Token
Token ID198
Feature activation-3.04e-03

Pos logit contributions
 pret+0.014
 asks+0.013
 writes+0.013
 meets+0.013
Jason+0.013
Neg logit contributions
quet-0.018
ue-0.015
comb-0.015
isy-0.015
zie-0.014
Token
Token ID198
Feature activation+7.69e-03

Pos logit contributions
 pret+0.005
 writes+0.004
 meets+0.004
 asks+0.004
 wre+0.004
Neg logit contributions
quet-0.006
ue-0.005
isy-0.005
comb-0.005
 Betty-0.005
TokenShe
Token ID3347
Feature activation+2.03e-02

Pos logit contributions
quet+0.014
comb+0.012
isy+0.011
lights+0.010
zie+0.010
Neg logit contributions
 asks-0.014
Jason-0.013
 meets-0.013
 writes-0.012
Ryan-0.012
Token looked
Token ID3114
Feature activation+2.40e-03

Pos logit contributions
quet+0.036
isy+0.032
comb+0.031
ue+0.028
ie+0.028
Neg logit contributions
Jason-0.032
 meets-0.031
Ryan-0.030
 asks-0.030
Soc-0.029
Token up
Token ID510
Feature activation-1.44e-02

Pos logit contributions
quet+0.005
comb+0.004
isy+0.004
ue+0.004
zie+0.003
Neg logit contributions
 asks-0.004
 meets-0.004
 sees-0.004
Jason-0.003
 writes-0.003
Token and
Token ID290
Feature activation+1.00e-02

Pos logit contributions
 asks+0.023
 meets+0.021
Jason+0.020
 sees+0.020
 writes+0.020
Neg logit contributions
quet-0.030
comb-0.025
isy-0.024
ue-0.022
zie-0.021
Token saw
Token ID2497
Feature activation-1.59e-02

Pos logit contributions
quet+0.023
comb+0.021
isy+0.021
zie+0.020
ue+0.020
Neg logit contributions
 meets-0.010
Jason-0.010
 asks-0.010
 writes-0.009
 pret-0.009
Token excited
Token ID6568
Feature activation+2.20e-02

Pos logit contributions
quet+0.004
comb+0.004
isy+0.004
ue+0.003
 ray+0.003
Neg logit contributions
 meets-0.006
Jason-0.005
 asks-0.005
 writes-0.005
 pret-0.005
Token.
Token ID13
Feature activation-3.64e-03

Pos logit contributions
quet+0.032
isy+0.025
comb+0.024
ue+0.021
zie+0.020
Neg logit contributions
 asks-0.046
 meets-0.046
Jason-0.045
 writes-0.044
 pret-0.043
Token He
Token ID679
Feature activation-4.02e-03

Pos logit contributions
 pret+0.007
 meets+0.006
 writes+0.006
 loudspe+0.006
 risking+0.006
Neg logit contributions
quet-0.005
ue-0.005
 Betty-0.004
 Suz-0.004
 Sue-0.004
Token bent
Token ID17157
Feature activation-5.04e-03

Pos logit contributions
Jason+0.007
 meets+0.006
 asks+0.006
 writes+0.006
Ryan+0.006
Neg logit contributions
quet-0.007
isy-0.006
comb-0.006
ue-0.005
zie-0.005
Token over
Token ID625
Feature activation+7.96e-03

Pos logit contributions
 asks+0.008
 meets+0.008
Jason+0.007
 writes+0.007
 pret+0.007
Neg logit contributions
quet-0.010
comb-0.009
isy-0.008
ue-0.007
lights-0.007
Token and
Token ID290
Feature activation+9.59e-03

Pos logit contributions
quet+0.011
comb+0.009
isy+0.008
ue+0.008
zie+0.007
Neg logit contributions
 asks-0.016
 meets-0.016
Jason-0.016
 writes-0.015
 pret-0.015
Token picked
Token ID6497
Feature activation+1.17e-02

Pos logit contributions
quet+0.015
comb+0.013
isy+0.013
zie+0.011
 as+0.011
Neg logit contributions
Jason-0.016
 meets-0.016
 asks-0.016
 jury-0.015
 writes-0.015
Token it
Token ID340
Feature activation+3.38e-02

Pos logit contributions
quet+0.015
isy+0.013
comb+0.013
 as+0.011
ie+0.011
Neg logit contributions
Jason-0.023
 asks-0.023
 jury-0.023
 meets-0.022
 loudspe-0.022
Token up
Token ID510
Feature activation-7.81e-03

Pos logit contributions
quet+0.079
comb+0.067
isy+0.065
lights+0.061
ue+0.060
Neg logit contributions
 asks-0.041
 meets-0.037
 pret-0.036
 sees-0.036
 writes-0.036
Token,
Token ID11
Feature activation+2.37e-03

Pos logit contributions
 asks+0.014
 meets+0.014
Jason+0.013
 writes+0.013
 pret+0.013
Neg logit contributions
quet-0.014
comb-0.011
isy-0.011
ue-0.010
zie-0.009
Token then
Token ID788
Feature activation-3.16e-02

Pos logit contributions
quet+0.004
comb+0.003
isy+0.003
ue+0.002
zie+0.002
Neg logit contributions
 asks-0.005
 meets-0.004
Jason-0.004
 writes-0.004
Ryan-0.004
Token stretching
Token ID20880
Feature activation-3.18e-02

Pos logit contributions
quet+0.007
comb+0.006
isy+0.006
ue+0.005
zie+0.005
Neg logit contributions
 asks-0.006
 meets-0.006
 writes-0.006
Jason-0.006
 sees-0.006
Token across
Token ID1973
Feature activation-2.66e-02

Pos logit contributions
 asks+0.057
 meets+0.055
Jason+0.054
 writes+0.053
 pret+0.051
Neg logit contributions
quet-0.056
comb-0.047
isy-0.045
ue-0.040
zie-0.038
Token the
Token ID262
Feature activation-7.40e-04

Pos logit contributions
 asks+0.050
Jason+0.048
 meets+0.048
 writes+0.046
 pret+0.045
Neg logit contributions
quet-0.044
comb-0.035
isy-0.033
lights-0.031
ue-0.031
Token sky
Token ID6766
Feature activation+1.82e-03

Pos logit contributions
 asks+0.002
Jason+0.001
 pret+0.001
 meets+0.001
 writes+0.001
Neg logit contributions
quet-0.001
comb-0.001
isy-0.001
lights-0.001
zie-0.001
Token.
Token ID13
Feature activation-8.49e-03

Pos logit contributions
quet+0.004
comb+0.003
isy+0.003
ue+0.003
zie+0.003
Neg logit contributions
 asks-0.003
 meets-0.003
Jason-0.003
 writes-0.003
 pret-0.002
Token The
Token ID383
Feature activation+5.77e-03

Pos logit contributions
Jason+0.016
 pret+0.016
 meets+0.015
 risking+0.015
 asks+0.015
Neg logit contributions
quet-0.011
ue-0.010
 Suz-0.009
 Betty-0.009
zie-0.009
Token family
Token ID1641
Feature activation+1.53e-03

Pos logit contributions
quet+0.011
comb+0.009
isy+0.009
ue+0.008
zie+0.008
Neg logit contributions
 asks-0.010
 meets-0.009
Jason-0.009
 writes-0.009
 pret-0.009
Token was
Token ID373
Feature activation+1.41e-02

Pos logit contributions
quet+0.003
comb+0.003
isy+0.003
ue+0.002
zie+0.002
Neg logit contributions
 asks-0.002
 meets-0.002
Jason-0.002
 writes-0.002
 pret-0.002
Token absolutely
Token ID5543
Feature activation+7.76e-03

Pos logit contributions
quet+0.025
comb+0.020
isy+0.020
ue+0.018
zie+0.017
Neg logit contributions
 asks-0.026
 meets-0.025
Jason-0.024
 writes-0.024
 pret-0.023
Token amazed
Token ID24562
Feature activation+4.09e-03

Pos logit contributions
quet+0.015
comb+0.012
isy+0.012
ue+0.010
zie+0.010
Neg logit contributions
 asks-0.013
 meets-0.013
Jason-0.012
 writes-0.012
 pret-0.012
Token by
Token ID416
Feature activation+3.20e-03

Pos logit contributions
quet+0.007
comb+0.006
isy+0.006
ue+0.005
lights+0.005
Neg logit contributions
 asks-0.007
 meets-0.007
Jason-0.007
 writes-0.007
 pret-0.007
Token there
Token ID612
Feature activation+3.04e-03

Pos logit contributions
quet+0.042
comb+0.036
isy+0.035
ue+0.032
zie+0.031
Neg logit contributions
 asks-0.027
 meets-0.025
Jason-0.025
 writes-0.024
 pret-0.023
Token was
Token ID373
Feature activation+1.13e-02

Pos logit contributions
quet+0.006
comb+0.005
isy+0.005
ue+0.005
zie+0.005
Neg logit contributions
 asks-0.005
 meets-0.004
Jason-0.004
 writes-0.004
 pret-0.004
Token a
Token ID257
Feature activation-2.26e-02

Pos logit contributions
quet+0.024
comb+0.021
isy+0.020
ue+0.018
zie+0.018
Neg logit contributions
 asks-0.016
 meets-0.015
Jason-0.015
 writes-0.015
 pret-0.014
Token little
Token ID1310
Feature activation+1.79e-02

Pos logit contributions
 asks+0.036
 meets+0.035
Jason+0.033
 writes+0.033
 yells+0.032
Neg logit contributions
quet-0.044
comb-0.037
isy-0.037
ue-0.033
zie-0.031
Token girl
Token ID2576
Feature activation+1.20e-02

Pos logit contributions
quet+0.043
comb+0.038
isy+0.036
ue+0.034
zie+0.034
Neg logit contributions
 asks-0.021
Jason-0.019
 meets-0.018
 pret-0.018
 writes-0.018
Token named
Token ID3706
Feature activation+7.19e-03

Pos logit contributions
quet+0.025
comb+0.021
isy+0.020
ue+0.019
zie+0.018
Neg logit contributions
 asks-0.018
 meets-0.017
 writes-0.017
Jason-0.017
 pret-0.016
Token Lily
Token ID20037
Feature activation+9.73e-03

Pos logit contributions
quet+0.018
comb+0.015
lights+0.014
isy+0.014
immer+0.013
Neg logit contributions
 asks-0.009
 meets-0.008
 sees-0.007
 met-0.007
Jason-0.007
Token.
Token ID13
Feature activation+4.54e-03

Pos logit contributions
quet+0.016
comb+0.014
isy+0.013
ue+0.012
ie+0.012
Neg logit contributions
 asks-0.017
 meets-0.017
Jason-0.017
 pret-0.016
Ryan-0.016
Token She
Token ID1375
Feature activation+7.37e-03

Pos logit contributions
quet+0.011
comb+0.009
isy+0.009
immer+0.008
lights+0.008
Neg logit contributions
 asks-0.006
 meets-0.005
 writes-0.005
 Whe-0.005
 sees-0.005
Token loved
Token ID6151
Feature activation-3.74e-03

Pos logit contributions
quet+0.014
isy+0.013
comb+0.012
ue+0.011
ie+0.011
Neg logit contributions
 asks-0.011
Jason-0.011
 meets-0.010
 yells-0.010
Ryan-0.010
Token to
Token ID284
Feature activation+3.66e-03

Pos logit contributions
Jason+0.006
 asks+0.006
 meets+0.005
Ryan+0.005
 writes+0.005
Neg logit contributions
quet-0.007
comb-0.006
isy-0.006
 shade-0.005
ue-0.005
Token light
Token ID1657
Feature activation-1.59e-02

Pos logit contributions
quet+0.027
comb+0.021
isy+0.020
lights+0.020
 ray+0.019
Neg logit contributions
 asks-0.034
 meets-0.034
Jason-0.033
Har-0.031
Ryan-0.031
Token.
Token ID13
Feature activation-4.83e-03

Pos logit contributions
 asks+0.028
 meets+0.028
Jason+0.027
 writes+0.025
Har+0.025
Neg logit contributions
quet-0.028
comb-0.023
isy-0.022
lights-0.020
ue-0.020
Token
Token ID198
Feature activation-9.92e-03

Pos logit contributions
 meets+0.008
Har+0.008
 asks+0.008
use+0.008
Jason+0.008
Neg logit contributions
quet-0.007
ue-0.006
 Sue-0.006
 Betty-0.006
 Suz-0.006
Token
Token ID198
Feature activation+9.41e-04

Pos logit contributions
 pret+0.016
 asks+0.016
 writes+0.016
 meets+0.016
 jury+0.015
Neg logit contributions
quet-0.016
ue-0.015
isy-0.014
 Suz-0.013
comb-0.013
Token"
Token ID1
Feature activation+8.39e-03

Pos logit contributions
quet+0.001
ue+0.001
isy+0.001
comb+0.001
zie+0.001
Neg logit contributions
 asks-0.002
 meets-0.002
 pret-0.002
 writes-0.002
Jason-0.002
TokenWow
Token ID22017
Feature activation+3.31e-02

Pos logit contributions
quet+0.018
comb+0.016
isy+0.015
ue+0.014
lights+0.013
Neg logit contributions
 asks-0.011
 meets-0.011
 writes-0.010
Jason-0.010
 yells-0.010
Token,
Token ID11
Feature activation+7.38e-04

Pos logit contributions
quet+0.050
comb+0.040
isy+0.038
ue+0.033
zie+0.032
Neg logit contributions
 asks-0.067
 meets-0.065
Jason-0.064
 writes-0.063
 pret-0.061
Token what
Token ID644
Feature activation-4.82e-03

Pos logit contributions
quet+0.001
comb+0.001
isy+0.001
ue+0.001
zie+0.001
Neg logit contributions
 asks-0.001
 meets-0.001
Jason-0.001
 writes-0.001
 pret-0.001
Token was
Token ID373
Feature activation+1.90e-02

Pos logit contributions
Har+0.008
Jason+0.008
Ryan+0.008
 asks+0.008
 meets+0.007
Neg logit contributions
quet-0.007
comb-0.007
isy-0.006
 of-0.006
 ray-0.006
Token that
Token ID326
Feature activation+1.96e-02

Pos logit contributions
quet+0.023
isy+0.017
comb+0.016
ue+0.012
 as+0.012
Neg logit contributions
 asks-0.044
Jason-0.044
 meets-0.044
 writes-0.041
Har-0.040
Token,
Token ID11
Feature activation-1.94e-03

Pos logit contributions
quet+0.035
isy+0.030
comb+0.030
ue+0.027
 ray+0.026
Neg logit contributions
 meets-0.031
 asks-0.030
Jason-0.030
Har-0.029
bers-0.029
Token what
Token ID644
Feature activation-3.56e-03

Pos logit contributions
 asks+0.047
Jason+0.046
 meets+0.045
Har+0.045
 writes+0.044
Neg logit contributions
quet-0.044
comb-0.039
isy-0.038
ue-0.033
zie-0.032
Token did
Token ID750
Feature activation+3.14e-02

Pos logit contributions
Har+0.007
Jason+0.007
Ryan+0.007
 asks+0.006
 Ethan+0.006
Neg logit contributions
quet-0.004
comb-0.004
 of-0.004
isy-0.004
 shade-0.003
Token you
Token ID345
Feature activation-9.60e-03

Pos logit contributions
quet+0.057
isy+0.047
comb+0.046
ue+0.045
 as+0.042
Neg logit contributions
 asks-0.051
Jason-0.049
 meets-0.049
 writes-0.046
Har-0.046
Token do
Token ID466
Feature activation+8.39e-03

Pos logit contributions
 asks+0.017
 meets+0.016
Jason+0.016
 writes+0.015
 pret+0.015
Neg logit contributions
quet-0.017
comb-0.014
isy-0.014
ue-0.012
zie-0.012
Token?
Token ID30
Feature activation-1.43e-02

Pos logit contributions
quet+0.016
comb+0.013
isy+0.013
ue+0.011
ie+0.011
Neg logit contributions
 asks-0.014
 meets-0.013
Jason-0.013
Har-0.012
Ready-0.012
Token You
Token ID921
Feature activation-7.53e-03

Pos logit contributions
 meets+0.020
Jason+0.020
Har+0.019
Jes+0.019
 asks+0.018
Neg logit contributions
quet-0.026
comb-0.022
 Suz-0.020
house-0.020
ue-0.020
Token should
Token ID815
Feature activation+5.61e-03

Pos logit contributions
 asks+0.012
 meets+0.011
Jason+0.011
 writes+0.011
Ryan+0.011
Neg logit contributions
quet-0.014
comb-0.012
isy-0.012
ue-0.011
zie-0.010
Token never
Token ID1239
Feature activation+1.51e-02

Pos logit contributions
quet+0.010
comb+0.008
isy+0.008
ue+0.007
zie+0.007
Neg logit contributions
 asks-0.010
 meets-0.010
Jason-0.009
 writes-0.009
 pret-0.009
Token touch
Token ID3638
Feature activation-1.45e-02

Pos logit contributions
quet+0.024
comb+0.020
isy+0.020
ue+0.018
zie+0.016
Neg logit contributions
Jason-0.028
 asks-0.028
 meets-0.027
 writes-0.026
Ryan-0.026
Token the
Token ID262
Feature activation-7.85e-03

Pos logit contributions
Jason+0.026
 asks+0.025
 meets+0.025
Ryan+0.024
Jes+0.024
Neg logit contributions
quet-0.023
isy-0.019
comb-0.018
ie-0.018
lights-0.018
Token razor
Token ID26811
Feature activation-4.61e-03

Pos logit contributions
 asks+0.015
Jason+0.015
 meets+0.015
Ryan+0.014
Har+0.014
Neg logit contributions
quet-0.012
comb-0.010
isy-0.010
 cushion-0.009
 shade-0.009
Token made
Token ID925
Feature activation+6.03e-03

Pos logit contributions
quet+0.016
comb+0.013
isy+0.013
ue+0.012
lights+0.011
Neg logit contributions
 asks-0.016
 meets-0.015
 writes-0.015
Jason-0.014
 pret-0.014
Token her
Token ID607
Feature activation+1.26e-02

Pos logit contributions
quet+0.012
comb+0.011
isy+0.009
ue+0.009
zie+0.008
Neg logit contributions
 asks-0.009
 meets-0.009
 writes-0.009
Jason-0.009
 Daniel-0.008
Token feel
Token ID1254
Feature activation-1.90e-03

Pos logit contributions
quet+0.026
comb+0.021
isy+0.020
ue+0.020
zie+0.018
Neg logit contributions
 asks-0.020
 meets-0.019
 pret-0.019
 writes-0.019
 sees-0.018
Token very
Token ID845
Feature activation-6.20e-03

Pos logit contributions
 asks+0.004
 meets+0.004
Jason+0.004
 writes+0.003
 pret+0.003
Neg logit contributions
quet-0.003
comb-0.002
isy-0.002
ue-0.002
zie-0.002
Token special
Token ID2041
Feature activation-2.11e-02

Pos logit contributions
 asks+0.012
 meets+0.012
Jason+0.011
 writes+0.011
 pret+0.011
Neg logit contributions
quet-0.010
comb-0.008
isy-0.008
lights-0.007
ue-0.006
Token.
Token ID13
Feature activation-4.76e-03

Pos logit contributions
 asks+0.032
 meets+0.030
Jason+0.029
 writes+0.029
 pret+0.028
Neg logit contributions
quet-0.044
comb-0.037
isy-0.036
ue-0.034
zie-0.032
Token
Token ID198
Feature activation-1.53e-03

Pos logit contributions
 asks+0.006
 meets+0.006
Jason+0.006
 writes+0.005
 pret+0.005
Neg logit contributions
quet-0.011
comb-0.009
isy-0.009
ue-0.009
zie-0.008
Token
Token ID198
Feature activation+1.15e-02

Pos logit contributions
 asks+0.002
 meets+0.002
 pret+0.002
Jason+0.002
 writes+0.002
Neg logit contributions
quet-0.003
isy-0.003
comb-0.003
ue-0.003
zie-0.003
TokenEvery
Token ID6109
Feature activation+1.84e-03

Pos logit contributions
quet+0.026
comb+0.024
isy+0.022
ue+0.020
zie+0.019
Neg logit contributions
 asks-0.015
 meets-0.014
Jason-0.014
 writes-0.013
 sees-0.013
Token day
Token ID1110
Feature activation+6.90e-03

Pos logit contributions
quet+0.003
comb+0.003
isy+0.003
lights+0.002
ue+0.002
Neg logit contributions
 asks-0.003
 meets-0.003
Jason-0.003
 writes-0.003
 sees-0.003
Token,
Token ID11
Feature activation+1.99e-02

Pos logit contributions
quet+0.014
comb+0.012
isy+0.011
ue+0.010
zie+0.010
Neg logit contributions
 asks-0.011
 writes-0.010
 meets-0.010
 sees-0.010
 pret-0.010
Token,
Token ID11
Feature activation+1.03e-02

Pos logit contributions
quet+0.030
comb+0.024
isy+0.023
ue+0.020
zie+0.019
Neg logit contributions
 asks-0.042
 meets-0.041
Jason-0.040
 writes-0.039
 pret-0.038
Token I
Token ID314
Feature activation-2.27e-02

Pos logit contributions
quet+0.019
comb+0.015
isy+0.015
ue+0.013
zie+0.013
Neg logit contributions
 asks-0.018
 meets-0.017
Jason-0.017
 writes-0.017
 pret-0.016
Tokenâ
Token ID22940
Feature activation-3.80e-04

Pos logit contributions
 asks+0.034
Jason+0.034
 motorcycles+0.033
 meets+0.033
 writes+0.032
Neg logit contributions
quet-0.041
comb-0.038
isy-0.036
ue-0.032
 surely-0.032
Token€
Token ID26391
Feature activation+9.81e-03

Pos logit contributions
 asks+0.001
 meets+0.001
Jason+0.001
 writes+0.000
 pret+0.000
Neg logit contributions
quet-0.001
comb-0.001
isy-0.001
ue-0.001
zie-0.001
Tokenâ„¢
Token ID8151
Feature activation+1.40e-02

Pos logit contributions
quet+0.020
comb+0.017
ue+0.016
isy+0.015
zie+0.014
Neg logit contributions
 asks-0.015
 writes-0.014
Jason-0.014
 meets-0.014
 pret-0.013
Tokend
Token ID67
Feature activation-2.43e-02

Pos logit contributions
quet+0.025
comb+0.020
isy+0.020
ue+0.019
zie+0.017
Neg logit contributions
 asks-0.025
 meets-0.024
Jason-0.024
 writes-0.024
 pret-0.023
Token love
Token ID1842
Feature activation+1.17e-02

Pos logit contributions
 asks+0.041
Jason+0.040
 meets+0.040
 writes+0.038
 pret+0.037
Neg logit contributions
quet-0.044
isy-0.036
comb-0.036
ue-0.032
zie-0.031
Token to
Token ID284
Feature activation+8.11e-03

Pos logit contributions
quet+0.019
isy+0.015
comb+0.013
ie+0.013
 as+0.013
Neg logit contributions
Jason-0.022
 asks-0.021
 meets-0.020
 cheated-0.020
Jes-0.019
Token play
Token ID711
Feature activation+6.31e-03

Pos logit contributions
quet+0.014
comb+0.011
isy+0.011
ue+0.010
zie+0.009
Neg logit contributions
 asks-0.015
 meets-0.015
Jason-0.014
 writes-0.014
 pret-0.014
Token with
Token ID351
Feature activation+1.64e-02

Pos logit contributions
quet+0.011
isy+0.008
comb+0.008
 cushion+0.007
ue+0.007
Neg logit contributions
 asks-0.012
Jason-0.012
 meets-0.012
 writes-0.011
 yells-0.011
Token you
Token ID345
Feature activation-1.19e-02

Pos logit contributions
quet+0.030
isy+0.025
comb+0.022
ie+0.022
 as+0.021
Neg logit contributions
 asks-0.027
Jason-0.026
 meets-0.026
 writes-0.026
 pret-0.025
Token're
Token ID821
Feature activation-1.19e-03

Pos logit contributions
 asks+0.027
 meets+0.025
Jason+0.024
 writes+0.024
 pret+0.023
Neg logit contributions
quet-0.043
comb-0.037
isy-0.036
ue-0.033
zie-0.032
Token going
Token ID1016
Feature activation-3.10e-02

Pos logit contributions
 asks+0.002
 meets+0.002
Jason+0.002
 writes+0.002
 pret+0.002
Neg logit contributions
quet-0.002
comb-0.002
isy-0.002
ue-0.002
lights-0.002
Token to
Token ID284
Feature activation+1.96e-02

Pos logit contributions
Jason+0.053
 asks+0.053
 yells+0.049
 writes+0.049
 pret+0.049
Neg logit contributions
quet-0.053
comb-0.041
 as-0.039
isy-0.038
 surely-0.036
Token fix
Token ID4259
Feature activation-8.37e-04

Pos logit contributions
quet+0.031
comb+0.025
isy+0.024
ue+0.022
 shade+0.021
Neg logit contributions
 asks-0.036
Jason-0.036
 meets-0.035
bers-0.035
rev-0.034
Token them
Token ID606
Feature activation+1.30e-02

Pos logit contributions
 asks+0.001
 meets+0.001
Jason+0.001
Check+0.001
Ready+0.001
Neg logit contributions
quet-0.001
isy-0.001
ie-0.001
comb-0.001
ue-0.001
Token."
Token ID526
Feature activation-6.88e-03

Pos logit contributions
quet+0.024
comb+0.020
isy+0.019
ue+0.018
zie+0.017
Neg logit contributions
 asks-0.022
 meets-0.021
Jason-0.021
 writes-0.020
 pret-0.020
Token When
Token ID1649
Feature activation+2.26e-02

Pos logit contributions
 asks+0.010
 meets+0.010
Jason+0.010
Check+0.009
 pret+0.009
Neg logit contributions
quet-0.014
comb-0.012
ue-0.011
isy-0.011
zie-0.010
Token they
Token ID484
Feature activation+8.05e-03

Pos logit contributions
quet+0.045
comb+0.038
isy+0.037
ue+0.033
zie+0.032
Neg logit contributions
 asks-0.036
 meets-0.034
Jason-0.033
 writes-0.032
 pret-0.031
Token got
Token ID1392
Feature activation+1.33e-02

Pos logit contributions
quet+0.019
comb+0.017
isy+0.016
lights+0.015
zie+0.014
Neg logit contributions
 asks-0.011
 meets-0.009
Jason-0.009
 met-0.009
 writes-0.009
Token home
Token ID1363
Feature activation+6.60e-03

Pos logit contributions
quet+0.029
isy+0.026
comb+0.026
ue+0.022
zie+0.022
Neg logit contributions
 asks-0.020
 meets-0.018
Jason-0.017
 sees-0.017
 writes-0.016
Token,
Token ID11
Feature activation+1.86e-02

Pos logit contributions
quet+0.012
comb+0.010
isy+0.010
ue+0.008
zie+0.008
Neg logit contributions
 asks-0.012
 meets-0.011
 sees-0.011
Jason-0.011
 yells-0.010
Token room
Token ID2119
Feature activation+1.69e-02

Pos logit contributions
quet+0.002
comb+0.001
isy+0.001
ue+0.001
zie+0.001
Neg logit contributions
 asks-0.001
 meets-0.001
Jason-0.001
 writes-0.001
 pret-0.001
Token and
Token ID290
Feature activation-1.50e-02

Pos logit contributions
quet+0.029
comb+0.025
isy+0.023
ue+0.020
lights+0.020
Neg logit contributions
 asks-0.030
Jason-0.029
 meets-0.029
 writes-0.028
Ryan-0.027
Token have
Token ID423
Feature activation+3.75e-03

Pos logit contributions
 asks+0.026
 meets+0.025
Jason+0.025
 writes+0.024
Ryan+0.023
Neg logit contributions
quet-0.027
comb-0.023
isy-0.022
ue-0.020
zie-0.019
Token a
Token ID257
Feature activation-2.81e-02

Pos logit contributions
quet+0.005
comb+0.004
isy+0.004
 shade+0.004
ue+0.004
Neg logit contributions
 asks-0.008
Jason-0.007
Ryan-0.007
 meets-0.007
 jury-0.007
Token snack
Token ID26906
Feature activation+7.67e-03

Pos logit contributions
 asks+0.059
 meets+0.057
Jason+0.056
 writes+0.055
 yells+0.054
Neg logit contributions
quet-0.041
comb-0.033
isy-0.031
ue-0.027
zie-0.024
Token."
Token ID526
Feature activation-1.17e-02

Pos logit contributions
quet+0.016
comb+0.014
isy+0.013
ue+0.012
zie+0.012
Neg logit contributions
 asks-0.011
 meets-0.011
Jason-0.010
 writes-0.010
 pret-0.010
Token
Token ID198
Feature activation-5.18e-03

Pos logit contributions
 meets+0.018
 wre+0.018
 pret+0.018
Check+0.018
 writes+0.018
Neg logit contributions
quet-0.019
comb-0.016
ue-0.016
 Sue-0.015
 Betty-0.015
Token
Token ID198
Feature activation+4.09e-03

Pos logit contributions
 meets+0.008
 asks+0.008
 pret+0.007
Jason+0.007
 cheated+0.007
Neg logit contributions
quet-0.010
isy-0.008
ue-0.008
comb-0.008
 shade-0.007
TokenAnna
Token ID31160
Feature activation+9.48e-03

Pos logit contributions
quet+0.010
comb+0.008
isy+0.008
ue+0.008
lights+0.007
Neg logit contributions
 asks-0.005
 meets-0.005
 writes-0.005
Jason-0.005
 pret-0.004
Token and
Token ID290
Feature activation-1.45e-02

Pos logit contributions
quet+0.011
comb+0.009
isy+0.009
ue+0.008
zie+0.007
Neg logit contributions
Jason-0.020
 meets-0.019
 asks-0.019
Ryan-0.019
Har-0.019
Token Ben
Token ID3932
Feature activation-2.70e-02

Pos logit contributions
 meets+0.013
 asks+0.013
Jason+0.012
 writes+0.011
 pret+0.010
Neg logit contributions
quet-0.037
comb-0.033
isy-0.032
ue-0.031
zie-0.030
Token with
Token ID351
Feature activation-4.23e-03

Pos logit contributions
 asks+0.010
 meets+0.009
Jason+0.009
 writes+0.009
 pret+0.008
Neg logit contributions
quet-0.011
comb-0.009
isy-0.008
ue-0.008
zie-0.007
Token things
Token ID1243
Feature activation-1.55e-03

Pos logit contributions
 meets+0.007
 asks+0.007
Jason+0.007
Ready+0.006
 writes+0.006
Neg logit contributions
quet-0.008
isy-0.007
comb-0.006
ie-0.006
zie-0.006
Token that
Token ID326
Feature activation+1.72e-03

Pos logit contributions
 asks+0.003
 meets+0.003
Jason+0.003
 writes+0.003
 pret+0.003
Neg logit contributions
quet-0.002
comb-0.002
isy-0.002
ue-0.002
lights-0.002
Token are
Token ID389
Feature activation+2.26e-02

Pos logit contributions
quet+0.003
comb+0.003
isy+0.003
ue+0.002
zie+0.002
Neg logit contributions
 asks-0.003
Jason-0.003
 meets-0.003
 writes-0.003
Ryan-0.003
Token not
Token ID407
Feature activation+2.65e-02

Pos logit contributions
quet+0.042
comb+0.034
isy+0.032
ue+0.029
zie+0.028
Neg logit contributions
 asks-0.040
 meets-0.038
 writes-0.037
Jason-0.037
 pret-0.036
Token yours
Token ID12431
Feature activation-7.16e-02

Pos logit contributions
quet+0.053
comb+0.045
isy+0.043
ue+0.039
zie+0.038
Neg logit contributions
 asks-0.042
 meets-0.040
Jason-0.039
 writes-0.038
 pret-0.037
Token.
Token ID13
Feature activation+5.25e-03

Pos logit contributions
 asks+0.132
Jason+0.131
 meets+0.127
 writes+0.124
Har+0.121
Neg logit contributions
quet-0.118
comb-0.100
isy-0.094
ue-0.083
zie-0.078
Token And
Token ID843
Feature activation+2.25e-02

Pos logit contributions
quet+0.012
comb+0.010
isy+0.010
ue+0.009
zie+0.009
Neg logit contributions
 asks-0.006
 meets-0.006
Jason-0.006
 writes-0.006
 pret-0.006
Token you
Token ID345
Feature activation-3.07e-02

Pos logit contributions
quet+0.050
comb+0.043
isy+0.042
ue+0.038
zie+0.037
Neg logit contributions
 asks-0.030
 meets-0.029
Jason-0.028
 writes-0.027
 pret-0.026
Token have
Token ID423
Feature activation-5.45e-03

Pos logit contributions
 asks+0.049
 meets+0.047
Jason+0.045
 writes+0.044
 pret+0.043
Neg logit contributions
quet-0.062
comb-0.053
isy-0.051
ue-0.046
zie-0.045
Token to
Token ID284
Feature activation-1.10e-02

Pos logit contributions
Jason+0.011
rob+0.010
 pret+0.010
rev+0.010
Ready+0.010
Neg logit contributions
quet-0.007
 too-0.006
 shade-0.005
 as-0.005
 of-0.005
Token eating
Token ID6600
Feature activation-1.12e-02

Pos logit contributions
quet+0.004
isy+0.004
comb+0.004
 as+0.003
zie+0.003
Neg logit contributions
 meets-0.005
Jason-0.005
 asks-0.005
 writes-0.005
Ready-0.005
Token her
Token ID607
Feature activation+1.59e-02

Pos logit contributions
 asks+0.018
 meets+0.017
Jason+0.017
 writes+0.016
 pret+0.016
Neg logit contributions
quet-0.022
comb-0.018
isy-0.018
ue-0.016
zie-0.015
Token soup
Token ID17141
Feature activation-1.47e-02

Pos logit contributions
quet+0.026
comb+0.023
isy+0.021
ue+0.018
zie+0.018
Neg logit contributions
 asks-0.029
 meets-0.028
Jason-0.028
 writes-0.027
Ryan-0.027
Token quietly
Token ID12703
Feature activation-2.07e-02

Pos logit contributions
 asks+0.022
 meets+0.021
 writes+0.020
Jason+0.020
 pret+0.020
Neg logit contributions
quet-0.030
comb-0.024
isy-0.024
ue-0.022
zie-0.022
Token and
Token ID290
Feature activation-2.51e-02

Pos logit contributions
 asks+0.038
 meets+0.037
Jason+0.037
 writes+0.035
Ryan+0.035
Neg logit contributions
quet-0.035
comb-0.030
isy-0.028
ue-0.025
zie-0.024
Token politely
Token ID34313
Feature activation-6.01e-02

Pos logit contributions
Jason+0.042
 asks+0.041
 meets+0.041
Har+0.040
Ryan+0.039
Neg logit contributions
quet-0.044
comb-0.039
isy-0.036
ue-0.031
lights-0.031
Token.
Token ID13
Feature activation-3.07e-03

Pos logit contributions
Jason+0.115
Har+0.110
Ryan+0.110
rev+0.107
Ready+0.107
Neg logit contributions
quet-0.087
comb-0.079
 as-0.072
isy-0.070
flower-0.061
Token She
Token ID1375
Feature activation+9.63e-03

Pos logit contributions
 meets+0.006
 asks+0.006
 pret+0.006
Jason+0.006
 writes+0.006
Neg logit contributions
quet-0.004
comb-0.003
ue-0.003
isy-0.003
 Betty-0.003
Token wished
Token ID16555
Feature activation+2.03e-03

Pos logit contributions
quet+0.018
comb+0.016
isy+0.016
ue+0.015
zie+0.014
Neg logit contributions
 meets-0.014
Jason-0.014
 asks-0.014
Ryan-0.013
Soc-0.013
Token Sam
Token ID3409
Feature activation+1.70e-02

Pos logit contributions
quet+0.004
comb+0.003
isy+0.003
ue+0.003
zie+0.002
Neg logit contributions
 asks-0.004
 meets-0.004
Jason-0.003
 writes-0.003
 pret-0.003
Token would
Token ID561
Feature activation-1.08e-02

Pos logit contributions
quet+0.032
comb+0.028
isy+0.027
ue+0.024
zie+0.023
Neg logit contributions
 asks-0.027
Jason-0.026
 meets-0.026
 writes-0.025
 pret-0.024
Token a
Token ID257
Feature activation-4.20e-02

Pos logit contributions
 asks+0.020
 meets+0.020
Jason+0.020
 writes+0.019
Har+0.018
Neg logit contributions
quet-0.020
comb-0.017
isy-0.015
 shade-0.014
ue-0.014
Token delicious
Token ID12625
Feature activation+3.41e-03

Pos logit contributions
 asks+0.080
 meets+0.077
Jason+0.074
 writes+0.073
Ryan+0.070
Neg logit contributions
quet-0.069
comb-0.059
isy-0.057
ue-0.047
 cushion-0.047
Token carrot
Token ID40562
Feature activation-1.34e-02

Pos logit contributions
quet+0.006
comb+0.004
isy+0.004
lights+0.004
ue+0.004
Neg logit contributions
 asks-0.006
 meets-0.006
Jason-0.006
 writes-0.006
 pret-0.006
Token -
Token ID532
Feature activation-1.14e-02

Pos logit contributions
 asks+0.024
 meets+0.023
Jason+0.023
 writes+0.023
 pret+0.022
Neg logit contributions
quet-0.023
comb-0.019
isy-0.018
ue-0.016
zie-0.015
Token but
Token ID475
Feature activation+5.34e-03

Pos logit contributions
 asks+0.020
 meets+0.020
Jason+0.020
 writes+0.019
Ryan+0.018
Neg logit contributions
quet-0.020
comb-0.017
isy-0.016
ue-0.014
 shade-0.013
Token he
Token ID339
Feature activation-5.62e-02

Pos logit contributions
quet+0.009
comb+0.008
isy+0.008
ue+0.007
zie+0.007
Neg logit contributions
 asks-0.009
 meets-0.009
Jason-0.009
 writes-0.009
Har-0.008
Token decided
Token ID3066
Feature activation-1.35e-02

Pos logit contributions
 asks+0.086
Jason+0.085
 meets+0.084
 writes+0.079
Ryan+0.078
Neg logit contributions
quet-0.107
comb-0.095
isy-0.092
ue-0.081
zie-0.079
Token not
Token ID407
Feature activation+1.75e-02

Pos logit contributions
Jason+0.026
 asks+0.026
 pret+0.025
 meets+0.025
Check+0.025
Neg logit contributions
quet-0.019
 as-0.015
isy-0.015
comb-0.015
 too-0.013
Token to
Token ID284
Feature activation-4.25e-03

Pos logit contributions
quet+0.034
comb+0.029
isy+0.028
ue+0.025
zie+0.024
Neg logit contributions
Jason-0.027
 asks-0.026
 meets-0.025
 writes-0.025
Ryan-0.025
Token share
Token ID2648
Feature activation-1.18e-02

Pos logit contributions
 asks+0.008
 meets+0.007
Jason+0.007
 writes+0.007
 pret+0.007
Neg logit contributions
quet-0.007
comb-0.006
isy-0.006
ue-0.005
zie-0.005
Token it
Token ID340
Feature activation+2.80e-02

Pos logit contributions
 asks+0.021
 meets+0.020
Jason+0.020
 writes+0.019
Ready+0.018
Neg logit contributions
quet-0.021
comb-0.017
isy-0.017
ue-0.015
ie-0.014
Token a
Token ID257
Feature activation-1.26e-02

Pos logit contributions
quet+0.009
isy+0.006
 as+0.006
 shade+0.006
ie+0.005
Neg logit contributions
use-0.012
 meets-0.012
 asks-0.012
Jason-0.011
bers-0.011
Token new
Token ID649
Feature activation+1.12e-02

Pos logit contributions
 asks+0.022
 meets+0.021
Jason+0.021
 writes+0.020
 pret+0.020
Neg logit contributions
quet-0.023
comb-0.019
isy-0.018
ue-0.016
zie-0.015
Token dress
Token ID6576
Feature activation+3.97e-02

Pos logit contributions
quet+0.021
comb+0.018
isy+0.017
ue+0.015
zie+0.015
Neg logit contributions
 asks-0.019
 meets-0.018
Jason-0.018
 writes-0.017
 pret-0.017
Token,
Token ID11
Feature activation-4.96e-04

Pos logit contributions
quet+0.074
comb+0.066
isy+0.062
ue+0.061
zie+0.059
Neg logit contributions
 asks-0.060
 writes-0.059
 meets-0.057
Jason-0.056
 pret-0.056
Token but
Token ID475
Feature activation-6.12e-04

Pos logit contributions
 asks+0.001
 meets+0.001
Jason+0.001
 writes+0.001
 pret+0.001
Neg logit contributions
quet-0.001
comb-0.001
isy-0.001
ue-0.001
zie-0.000
Token he
Token ID339
Feature activation-5.81e-02

Pos logit contributions
 asks+0.001
 meets+0.001
Jason+0.001
 writes+0.001
 pret+0.001
Neg logit contributions
quet-0.001
comb-0.001
isy-0.001
ue-0.001
zie-0.001
Token didn
Token ID1422
Feature activation+5.67e-03

Pos logit contributions
 asks+0.085
 meets+0.082
Jason+0.079
 writes+0.077
 pret+0.075
Neg logit contributions
quet-0.123
comb-0.105
isy-0.101
ue-0.092
zie-0.089
Token't
Token ID470
Feature activation+2.17e-02

Pos logit contributions
quet+0.010
comb+0.009
isy+0.008
ue+0.007
zie+0.007
Neg logit contributions
 asks-0.010
 meets-0.010
Jason-0.010
 writes-0.009
Ryan-0.009
Token know
Token ID760
Feature activation-1.18e-03

Pos logit contributions
quet+0.052
comb+0.045
isy+0.043
lights+0.042
ue+0.042
Neg logit contributions
 asks-0.029
 meets-0.026
 writes-0.025
 pret-0.024
Jason-0.023
Token what
Token ID644
Feature activation-7.31e-04

Pos logit contributions
 asks+0.003
 meets+0.003
Jason+0.003
 writes+0.002
 pret+0.002
Neg logit contributions
quet-0.002
comb-0.001
isy-0.001
ue-0.001
lights-0.001
Token to
Token ID284
Feature activation+1.13e-02

Pos logit contributions
 meets+0.001
Jason+0.001
 asks+0.001
 yells+0.001
Har+0.001
Neg logit contributions
quet-0.001
isy-0.001
comb-0.001
 shade-0.001
 cushion-0.001
Token had
Token ID550
Feature activation+8.96e-03

Pos logit contributions
Jason+0.014
 asks+0.013
Ryan+0.013
 Daniel+0.012
 yells+0.012
Neg logit contributions
quet-0.011
isy-0.011
comb-0.010
ie-0.010
zie-0.009
Token a
Token ID257
Feature activation-1.08e-02

Pos logit contributions
quet+0.014
isy+0.011
comb+0.010
 shade+0.010
ue+0.009
Neg logit contributions
 asks-0.017
Jason-0.016
 meets-0.016
bers-0.016
 pret-0.015
Token toy
Token ID13373
Feature activation+2.34e-02

Pos logit contributions
 asks+0.018
 meets+0.018
Jason+0.018
 writes+0.017
 yells+0.017
Neg logit contributions
quet-0.019
comb-0.016
isy-0.016
ue-0.014
lights-0.013
Token helicopter
Token ID15392
Feature activation+1.58e-02

Pos logit contributions
quet+0.043
comb+0.036
isy+0.035
ue+0.031
lights+0.029
Neg logit contributions
 asks-0.040
 meets-0.039
Jason-0.038
 writes-0.037
 pret-0.036
Token that
Token ID326
Feature activation+8.23e-03

Pos logit contributions
quet+0.027
comb+0.022
isy+0.021
ue+0.020
zie+0.019
Neg logit contributions
 asks-0.029
 meets-0.028
 writes-0.027
Jason-0.027
 pret-0.026
Token he
Token ID339
Feature activation-5.77e-02

Pos logit contributions
quet+0.017
comb+0.014
isy+0.014
ue+0.013
zie+0.013
Neg logit contributions
 asks-0.012
Jason-0.012
 meets-0.011
 writes-0.011
 yells-0.011
Token played
Token ID2826
Feature activation+9.76e-03

Pos logit contributions
Jason+0.090
 asks+0.088
 meets+0.083
 yells+0.082
Ryan+0.080
Neg logit contributions
quet-0.108
isy-0.095
comb-0.091
ie-0.083
ue-0.077
Token with
Token ID351
Feature activation+1.95e-02

Pos logit contributions
quet+0.017
comb+0.015
isy+0.014
ue+0.012
zie+0.012
Neg logit contributions
 asks-0.017
 meets-0.017
Jason-0.016
 writes-0.016
 pret-0.016
Token every
Token ID790
Feature activation-1.22e-02

Pos logit contributions
quet+0.025
isy+0.020
comb+0.019
ie+0.016
ue+0.015
Neg logit contributions
 asks-0.043
Jason-0.043
 meets-0.041
 writes-0.040
Ryan-0.039
Token day
Token ID1110
Feature activation+4.31e-03

Pos logit contributions
 asks+0.025
 meets+0.025
Jason+0.024
 writes+0.023
 pret+0.023
Neg logit contributions
quet-0.018
comb-0.015
isy-0.014
ue-0.012
zie-0.012
Token.
Token ID13
Feature activation+6.71e-05

Pos logit contributions
quet+0.007
comb+0.006
isy+0.006
lights+0.005
ue+0.005
Neg logit contributions
 asks-0.008
 meets-0.008
Jason-0.008
 writes-0.008
 pret-0.007