TOP ACTIVATIONS
MAX = 7.950

twenty - eight , twenty - nine , thirty , thirty
. He looked through the ey ep iece and saw the
slide and looked through the ey ep iece . He saw
nine , thirty , thirty - one , thirty - two
and carefully picked up the pe b ble for the bunny
thirty - one , thirty - two , thirty - three
M ummy pe ered down at the ground
Mary carefully placed the pe b ble inside her dough
children agreed and let the pe b ble help measure the
'm glad you enjoyed the pe aches . Have a nice
, she accidentally threw a pe b ble at her friend
spoon . She put the pe aches in the bowl and
, Anna picked up a pe b ble that was different
day , she found a pe b ble that was very
me ?" An ch or said , " Yes
ed up some of the pe b bles and the sticks
his phone and threw the pe b ble as hard as
He picked up a round pe b ble and threw it
saw something strange ! A pe b ble next to him
So , Lily gave the pe b ble to Jack and

MIN ACTIVATIONS
MIN = -5.251

lonely clock on his bed side table and he made sure
toys and clothes in their bags . They got in the
packed many toys in their bags . Mom was
v ase on her bed side table . She remembered why
clothes and toys into big bags . When
throwing the corn in their baskets . Soon ,
, which are like big bags inside us . We breathe
put their things in their bags and zip them up .
s and paper in their bags . They go to the
the last things into their bags and they stepped outside with
and stuff it in the bags . Molly helps too .
saw Sammy leaving with his bags . Benny felt en vious
they had unp acked their bags . Tom put the card
again and saved it in bags for the next day .
and put them in their baskets . " Look
She writes " To Ben " on the heart .
go back to the pool side , Mia . Maybe we
, they checked in their bags and got their tickets .
pack some gems in their bags . They do not see
coats and put away their bags . They c uddled with

INTERVAL 4.650 - 7.950
CONTAINS 0.017%

said goodbye to the se ag ull s and put his
. The more , the mer rier . Come to my
The big do ggy got sick er and
morning , he found a pe b ble sitting on the
. He showed Lily his pe b ble . It was

INTERVAL 1.349 - 4.650
CONTAINS 8.263%

" We didn 't know it was your plane ,"
. They knocked again , louder , but still no one
were glad that the z ebra had changed his ways .
Max are twins . They like to play together , but
her mom my told her it was fake . Lily was

INTERVAL -1.951 - 1.349
CONTAINS 89.163%

was the best day ever ! When it
mom . But when she went back inside to get her
put them on her desk . She named each color out
said , " I want something else that 's delicious !"
Pam says . " Rot ? What is rot

INTERVAL -5.251 - -1.951
CONTAINS 2.556%

and slides down . " Y ay !" They
my decided to cook something y ummy to eat . They
He blew on the sticks until the sun got hot and
might find next ? <|endoftext|> Once upon a time , there
Ben were playing with their toys in the garden . Lily
Token twenty
Token ID8208
Feature activation+5.81e+00

Pos logit contributions
 dives+0.150
eway+0.140
 villains+0.129
 mer+0.129
 films+0.129
Neg logit contributions
 Em-0.090
 Gem-0.087
ama-0.084
 expensive-0.082
 checkout-0.080
Token-
Token ID12
Feature activation+7.95e+00

Pos logit contributions
 dives+0.134
eway+0.118
 tricks+0.115
 films+0.111
 mer+0.110
Neg logit contributions
 Em-0.150
ama-0.147
 Gem-0.146
 Johnson-0.143
 groceries-0.143
Tokeneight
Token ID26022
Feature activation+3.34e+00

Pos logit contributions
 dives+0.190
eway+0.166
 films+0.159
 mer+0.157
 tricks+0.157
Neg logit contributions
 Em-0.201
ama-0.197
 Gem-0.196
 checkout-0.188
 Johnson-0.188
Token,
Token ID11
Feature activation+4.55e+00

Pos logit contributions
 dives+0.088
 tricks+0.082
 poses+0.078
eway+0.078
 dances+0.077
Neg logit contributions
 groceries-0.068
 infected-0.067
 Em-0.066
 severe-0.066
 Gem-0.066
Token twenty
Token ID8208
Feature activation+5.70e+00

Pos logit contributions
 dives+0.136
eway+0.123
 tricks+0.119
 films+0.119
 mer+0.118
Neg logit contributions
 Em-0.085
ama-0.085
 Gem-0.082
 groceries-0.080
 Johnson-0.080
Token-
Token ID12
Feature activation+7.65e+00

Pos logit contributions
 dives+0.127
eway+0.111
 tricks+0.108
 films+0.104
 dances+0.102
Neg logit contributions
 Em-0.151
ama-0.149
 Gem-0.148
 Johnson-0.145
 groceries-0.145
Tokennine
Token ID30888
Feature activation+4.21e+00

Pos logit contributions
 dives+0.177
eway+0.157
 tricks+0.149
 films+0.148
 mer+0.147
Neg logit contributions
 Em-0.195
ama-0.194
 Gem-0.190
 Johnson-0.185
 groceries-0.185
Token,
Token ID11
Feature activation+4.34e+00

Pos logit contributions
 dives+0.124
 tricks+0.110
eway+0.107
 dances+0.107
 hops+0.106
Neg logit contributions
ama-0.078
 groceries-0.076
 Em-0.076
 Gem-0.076
 checkout-0.074
Token thirty
Token ID12277
Feature activation+4.31e+00

Pos logit contributions
 dives+0.126
eway+0.112
 films+0.112
 tricks+0.111
 mer+0.111
Neg logit contributions
ama-0.082
 Em-0.080
 groceries-0.078
 Gem-0.078
 Johnson-0.077
Token,
Token ID11
Feature activation+4.34e+00

Pos logit contributions
 dives+0.086
eway+0.074
 tricks+0.071
 films+0.068
 mer+0.068
Neg logit contributions
 Em-0.125
ama-0.123
 Gem-0.122
 groceries-0.120
 Johnson-0.119
Token thirty
Token ID12277
Feature activation+4.07e+00

Pos logit contributions
 dives+0.127
eway+0.113
 films+0.113
 mer+0.112
 tricks+0.112
Neg logit contributions
ama-0.081
 Em-0.079
 groceries-0.078
 Gem-0.077
 Johnson-0.077
Token.
Token ID13
Feature activation+4.75e-01

Pos logit contributions
 dives+0.024
eway+0.022
RO+0.021
 films+0.021
 Fly+0.021
Neg logit contributions
 Em-0.011
ama-0.010
 groceries-0.010
 checkout-0.010
 expensive-0.010
Token He
Token ID679
Feature activation+3.41e-01

Pos logit contributions
eway+0.015
 dives+0.015
 mer+0.014
ile+0.014
ull+0.014
Neg logit contributions
 Em-0.007
ama-0.007
 grandma-0.007
 checkout-0.007
 Johnson-0.007
Token looked
Token ID3114
Feature activation+1.25e+00

Pos logit contributions
eway+0.010
 dives+0.010
 films+0.010
 tricks+0.009
 mer+0.009
Neg logit contributions
 Em-0.006
 expensive-0.006
 already-0.006
 checkout-0.006
 Gem-0.006
Token through
Token ID832
Feature activation+1.87e+00

Pos logit contributions
eway+0.033
 dives+0.032
 villains+0.030
 films+0.030
 Fly+0.029
Neg logit contributions
 Em-0.027
 expensive-0.026
 Gem-0.026
 groceries-0.025
 tired-0.025
Token the
Token ID262
Feature activation-3.08e-01

Pos logit contributions
 dives+0.061
eway+0.057
igators+0.054
 films+0.054
RO+0.054
Neg logit contributions
 Em-0.030
 groceries-0.028
 Gem-0.028
 expensive-0.028
 Johnson-0.027
Token ey
Token ID1926
Feature activation+7.30e+00

Pos logit contributions
 Em+0.006
ama+0.006
 Gem+0.006
 Johnson+0.006
 groceries+0.006
Neg logit contributions
 dives-0.009
eway-0.008
 tricks-0.008
 films-0.008
 mer-0.008
Tokenep
Token ID538
Feature activation+6.86e-01

Pos logit contributions
 dives+0.185
 villains+0.163
 films+0.162
 dances+0.155
 warriors+0.154
Neg logit contributions
ama-0.171
 infected-0.165
 expensive-0.160
 already-0.160
bur-0.160
Tokeniece
Token ID8535
Feature activation+5.89e-01

Pos logit contributions
 dives+0.018
eway+0.016
 films+0.016
igators+0.016
RO+0.015
Neg logit contributions
ama-0.015
 Em-0.015
 Gem-0.014
 first-0.014
 checkout-0.014
Token and
Token ID290
Feature activation+2.53e-01

Pos logit contributions
 dives+0.021
RO+0.019
igators+0.019
 films+0.018
 Fly+0.018
Neg logit contributions
ama-0.009
 already-0.008
 first-0.008
 no-0.007
 Gem-0.007
Token saw
Token ID2497
Feature activation+6.04e-01

Pos logit contributions
eway+0.008
 dives+0.008
 films+0.008
igators+0.008
 villains+0.007
Neg logit contributions
 Em-0.004
 Gem-0.004
 first-0.004
 grandma-0.004
 tired-0.004
Token the
Token ID262
Feature activation-1.50e-02

Pos logit contributions
 dives+0.022
eway+0.021
RO+0.020
 films+0.019
 villains+0.019
Neg logit contributions
 Em-0.008
 expensive-0.007
 grandma-0.007
 Gem-0.007
 groceries-0.007
Token slide
Token ID10649
Feature activation-7.19e-01

Pos logit contributions
 dives+0.025
eway+0.023
 films+0.022
 tricks+0.022
 mer+0.022
Neg logit contributions
 Em-0.017
ama-0.017
 Gem-0.016
 groceries-0.016
 checkout-0.016
Token and
Token ID290
Feature activation-1.63e-01

Pos logit contributions
 Em+0.015
ama+0.015
 Gem+0.015
 groceries+0.014
 Johnson+0.014
Neg logit contributions
 dives-0.020
eway-0.018
 tricks-0.017
 mer-0.017
 films-0.017
Token looked
Token ID3114
Feature activation+9.74e-01

Pos logit contributions
 Em+0.003
 checkout+0.003
 Gem+0.003
 grandma+0.003
 groceries+0.003
Neg logit contributions
eway-0.005
 dives-0.005
ile-0.005
 films-0.005
ag-0.005
Token through
Token ID832
Feature activation+1.52e+00

Pos logit contributions
 dives+0.025
eway+0.025
 villains+0.023
 films+0.023
 Fly+0.022
Neg logit contributions
 Em-0.022
 expensive-0.021
 Gem-0.021
 groceries-0.021
ama-0.020
Token the
Token ID262
Feature activation-6.36e-01

Pos logit contributions
 dives+0.048
eway+0.045
 films+0.042
RO+0.042
 tricks+0.042
Neg logit contributions
 Em-0.026
 Gem-0.025
 groceries-0.024
 expensive-0.024
ama-0.024
Token ey
Token ID1926
Feature activation+7.25e+00

Pos logit contributions
 groceries+0.010
 Em+0.010
ama+0.010
 checkout+0.010
 Gem+0.010
Neg logit contributions
 dives-0.020
eway-0.019
 Fly-0.018
 villains-0.018
 films-0.018
Tokenep
Token ID538
Feature activation+1.88e-01

Pos logit contributions
 dives+0.192
 villains+0.170
 films+0.170
 dances+0.163
 Fly+0.162
Neg logit contributions
ama-0.158
 infected-0.157
bur-0.151
 expensive-0.151
 already-0.149
Tokeniece
Token ID8535
Feature activation+2.22e-01

Pos logit contributions
 dives+0.006
eway+0.005
 films+0.005
igators+0.005
RO+0.005
Neg logit contributions
ama-0.003
 Em-0.003
 first-0.003
 Gem-0.003
 groceries-0.003
Token.
Token ID13
Feature activation+1.33e-02

Pos logit contributions
 dives+0.008
RO+0.008
igators+0.007
 Fly+0.007
 films+0.007
Neg logit contributions
ama-0.003
 already-0.002
 first-0.002
 Gem-0.002
 no-0.002
Token He
Token ID679
Feature activation-1.48e-01

Pos logit contributions
 dives+0.000
eway+0.000
igators+0.000
 films+0.000
 mer+0.000
Neg logit contributions
 Em-0.000
 Gem-0.000
ama-0.000
 Johnson-0.000
 checkout-0.000
Token saw
Token ID2497
Feature activation+6.56e-01

Pos logit contributions
 Em+0.003
ama+0.003
 Gem+0.003
 checkout+0.003
 expensive+0.003
Neg logit contributions
 dives-0.004
eway-0.004
 films-0.004
 tricks-0.004
 mer-0.004
Tokennine
Token ID30888
Feature activation+4.21e+00

Pos logit contributions
 dives+0.177
eway+0.157
 tricks+0.149
 films+0.148
 mer+0.147
Neg logit contributions
 Em-0.195
ama-0.194
 Gem-0.190
 Johnson-0.185
 groceries-0.185
Token,
Token ID11
Feature activation+4.34e+00

Pos logit contributions
 dives+0.124
 tricks+0.110
eway+0.107
 dances+0.107
 hops+0.106
Neg logit contributions
ama-0.078
 groceries-0.076
 Em-0.076
 Gem-0.076
 checkout-0.074
Token thirty
Token ID12277
Feature activation+4.31e+00

Pos logit contributions
 dives+0.126
eway+0.112
 films+0.112
 tricks+0.111
 mer+0.111
Neg logit contributions
ama-0.082
 Em-0.080
 groceries-0.078
 Gem-0.078
 Johnson-0.077
Token,
Token ID11
Feature activation+4.34e+00

Pos logit contributions
 dives+0.086
eway+0.074
 tricks+0.071
 films+0.068
 mer+0.068
Neg logit contributions
 Em-0.125
ama-0.123
 Gem-0.122
 groceries-0.120
 Johnson-0.119
Token thirty
Token ID12277
Feature activation+4.07e+00

Pos logit contributions
 dives+0.127
eway+0.113
 films+0.113
 mer+0.112
 tricks+0.112
Neg logit contributions
ama-0.081
 Em-0.079
 groceries-0.078
 Gem-0.077
 Johnson-0.077
Token-
Token ID12
Feature activation+7.05e+00

Pos logit contributions
 dives+0.081
eway+0.069
 tricks+0.066
 films+0.064
 mer+0.064
Neg logit contributions
 Em-0.118
ama-0.117
 Gem-0.115
 groceries-0.113
 Johnson-0.113
Tokenone
Token ID505
Feature activation+2.45e+00

Pos logit contributions
 dives+0.166
eway+0.146
 tricks+0.139
 films+0.139
 mer+0.138
Neg logit contributions
 Em-0.178
ama-0.177
 Gem-0.174
 Johnson-0.168
 groceries-0.168
Token,
Token ID11
Feature activation+4.22e+00

Pos logit contributions
 dives+0.068
eway+0.061
 tricks+0.060
 films+0.058
 dances+0.057
Neg logit contributions
 Em-0.051
ama-0.050
 Gem-0.050
 groceries-0.049
 checkout-0.048
Token thirty
Token ID12277
Feature activation+3.62e+00

Pos logit contributions
 dives+0.123
 films+0.109
eway+0.109
 mer+0.108
 tricks+0.108
Neg logit contributions
ama-0.080
 Em-0.077
 groceries-0.076
 Johnson-0.075
 Gem-0.075
Token-
Token ID12
Feature activation+6.47e+00

Pos logit contributions
 dives+0.070
eway+0.060
 tricks+0.057
 films+0.055
 mer+0.054
Neg logit contributions
 Em-0.107
ama-0.105
 Gem-0.105
 groceries-0.103
 Johnson-0.103
Tokentwo
Token ID11545
Feature activation+2.34e+00

Pos logit contributions
 dives+0.150
eway+0.133
 tricks+0.126
 films+0.125
 mer+0.125
Neg logit contributions
 Em-0.164
ama-0.164
 Gem-0.160
 Johnson-0.156
 groceries-0.156
Token and
Token ID290
Feature activation+1.45e+00

Pos logit contributions
 dives+0.041
eway+0.037
 mer+0.036
 tricks+0.036
 films+0.035
Neg logit contributions
 Em-0.024
ama-0.024
 Gem-0.023
 groceries-0.022
 Johnson-0.022
Token carefully
Token ID7773
Feature activation+2.03e+00

Pos logit contributions
 dives+0.049
eway+0.047
 films+0.046
RO+0.045
ile+0.044
Neg logit contributions
 Em-0.020
 buy-0.020
 Gem-0.020
 groceries-0.019
 expensive-0.019
Token picked
Token ID6497
Feature activation+8.63e-01

Pos logit contributions
 dives+0.061
eway+0.057
 films+0.055
 mer+0.054
 tricks+0.054
Neg logit contributions
 Em-0.037
 Gem-0.036
ama-0.036
 checkout-0.034
 groceries-0.034
Token up
Token ID510
Feature activation+3.82e+00

Pos logit contributions
 dives+0.024
eway+0.022
 films+0.021
 tricks+0.021
 mer+0.021
Neg logit contributions
 Em-0.018
ama-0.017
 Gem-0.017
 groceries-0.017
 Johnson-0.017
Token the
Token ID262
Feature activation+2.12e+00

Pos logit contributions
 dives+0.116
eway+0.106
 tricks+0.101
 films+0.101
 mer+0.101
Neg logit contributions
 Em-0.070
ama-0.069
 Gem-0.068
 groceries-0.066
 Johnson-0.065
Token pe
Token ID613
Feature activation+6.55e+00

Pos logit contributions
 dives+0.062
eway+0.057
 tricks+0.055
 mer+0.054
 films+0.054
Neg logit contributions
 Em-0.041
ama-0.040
 Gem-0.039
 Johnson-0.038
 groceries-0.037
Tokenb
Token ID65
Feature activation+3.83e+00

Pos logit contributions
 dives+0.157
eway+0.140
 films+0.138
 mer+0.134
 Fly+0.131
Neg logit contributions
ama-0.160
 Em-0.158
 Gem-0.157
 groceries-0.152
 expensive-0.150
Tokenble
Token ID903
Feature activation+2.37e+00

Pos logit contributions
 dives+0.118
eway+0.107
 films+0.106
 mer+0.103
 tricks+0.102
Neg logit contributions
ama-0.069
 Em-0.068
 Gem-0.067
 groceries-0.063
 Johnson-0.062
Token for
Token ID329
Feature activation+1.33e+00

Pos logit contributions
 dives+0.067
eway+0.061
 films+0.059
 tricks+0.058
 mer+0.058
Neg logit contributions
ama-0.048
 Em-0.048
 Gem-0.047
 groceries-0.046
 Johnson-0.045
Token the
Token ID262
Feature activation+9.48e-01

Pos logit contributions
 dives+0.039
eway+0.035
 films+0.033
 tricks+0.033
 mer+0.033
Neg logit contributions
 Em-0.027
ama-0.026
 Gem-0.026
 groceries-0.025
 Johnson-0.025
Token bunny
Token ID44915
Feature activation+1.16e+00

Pos logit contributions
 dives+0.029
eway+0.026
 tricks+0.025
 mer+0.025
 films+0.025
Neg logit contributions
 Em-0.017
ama-0.017
 Gem-0.017
 Johnson-0.016
 groceries-0.016
Token thirty
Token ID12277
Feature activation+4.07e+00

Pos logit contributions
 dives+0.127
eway+0.113
 films+0.113
 mer+0.112
 tricks+0.112
Neg logit contributions
ama-0.081
 Em-0.079
 groceries-0.078
 Gem-0.077
 Johnson-0.077
Token-
Token ID12
Feature activation+7.05e+00

Pos logit contributions
 dives+0.081
eway+0.069
 tricks+0.066
 films+0.064
 mer+0.064
Neg logit contributions
 Em-0.118
ama-0.117
 Gem-0.115
 groceries-0.113
 Johnson-0.113
Tokenone
Token ID505
Feature activation+2.45e+00

Pos logit contributions
 dives+0.166
eway+0.146
 tricks+0.139
 films+0.139
 mer+0.138
Neg logit contributions
 Em-0.178
ama-0.177
 Gem-0.174
 Johnson-0.168
 groceries-0.168
Token,
Token ID11
Feature activation+4.22e+00

Pos logit contributions
 dives+0.068
eway+0.061
 tricks+0.060
 films+0.058
 dances+0.057
Neg logit contributions
 Em-0.051
ama-0.050
 Gem-0.050
 groceries-0.049
 checkout-0.048
Token thirty
Token ID12277
Feature activation+3.62e+00

Pos logit contributions
 dives+0.123
 films+0.109
eway+0.109
 mer+0.108
 tricks+0.108
Neg logit contributions
ama-0.080
 Em-0.077
 groceries-0.076
 Johnson-0.075
 Gem-0.075
Token-
Token ID12
Feature activation+6.47e+00

Pos logit contributions
 dives+0.070
eway+0.060
 tricks+0.057
 films+0.055
 mer+0.054
Neg logit contributions
 Em-0.107
ama-0.105
 Gem-0.105
 groceries-0.103
 Johnson-0.103
Tokentwo
Token ID11545
Feature activation+2.34e+00

Pos logit contributions
 dives+0.150
eway+0.133
 tricks+0.126
 films+0.125
 mer+0.125
Neg logit contributions
 Em-0.164
ama-0.164
 Gem-0.160
 Johnson-0.156
 groceries-0.156
Token,
Token ID11
Feature activation+3.65e+00

Pos logit contributions
 dives+0.066
 tricks+0.060
eway+0.057
 dances+0.056
 hops+0.055
Neg logit contributions
 Em-0.049
 groceries-0.048
 Johnson-0.048
 Gem-0.047
ama-0.047
Token thirty
Token ID12277
Feature activation+2.86e+00

Pos logit contributions
 dives+0.110
eway+0.098
 films+0.097
 mer+0.097
 tricks+0.097
Neg logit contributions
ama-0.066
 Em-0.064
 groceries-0.063
 Gem-0.062
 Johnson-0.062
Token-
Token ID12
Feature activation+5.33e+00

Pos logit contributions
 dives+0.053
eway+0.045
 tricks+0.044
 films+0.041
 mer+0.041
Neg logit contributions
 Em-0.086
ama-0.085
 Gem-0.084
 Johnson-0.083
 groceries-0.083
Tokenthree
Token ID15542
Feature activation+1.09e+00

Pos logit contributions
 dives+0.127
eway+0.113
 tricks+0.108
 mer+0.106
 films+0.106
Neg logit contributions
ama-0.131
 Em-0.131
 Gem-0.128
 Johnson-0.125
 groceries-0.125
Token
Token ID220
Feature activation-1.67e+00

Pos logit contributions
ama+0.003
 Em+0.003
 Gem+0.003
 Johnson+0.003
 checkout+0.003
Neg logit contributions
 dives-0.005
eway-0.004
 tricks-0.004
 films-0.004
 mer-0.004
Token
Token ID198
Feature activation+6.23e-02

Pos logit contributions
 checkout+0.035
 Em+0.035
 infected+0.034
 Gem+0.034
 groceries+0.034
Neg logit contributions
 dives-0.044
eway-0.043
 films-0.038
 tricks-0.038
ull-0.038
Token
Token ID198
Feature activation-6.95e-01

Pos logit contributions
 dives+0.002
eway+0.002
 tricks+0.002
 mer+0.002
 films+0.002
Neg logit contributions
 Em-0.001
ama-0.001
 Gem-0.001
 groceries-0.001
 Johnson-0.001
TokenM
Token ID44
Feature activation-1.49e+00

Pos logit contributions
ama+0.013
 Em+0.012
 Gem+0.012
 Johnson+0.012
 checkout+0.011
Neg logit contributions
 dives-0.021
eway-0.019
 tricks-0.019
 films-0.019
 mer-0.018
Tokenummy
Token ID13513
Feature activation+2.03e+00

Pos logit contributions
 Em+0.019
 Gem+0.017
 infected+0.017
 checkout+0.017
 Johnson+0.017
Neg logit contributions
 dives-0.054
eway-0.050
 tricks-0.049
 mer-0.048
 films-0.048
Token pe
Token ID613
Feature activation+6.36e+00

Pos logit contributions
 dives+0.069
eway+0.068
 tricks+0.065
 villains+0.064
 poses+0.063
Neg logit contributions
ama-0.031
 Em-0.031
 Gem-0.030
 Johnson-0.029
 checkout-0.026
Tokenered
Token ID1068
Feature activation+1.92e+00

Pos logit contributions
 dives+0.158
eway+0.138
 films+0.136
 mer+0.133
 tricks+0.132
Neg logit contributions
ama-0.157
 Em-0.151
 Gem-0.149
 infected-0.143
 checkout-0.142
Token down
Token ID866
Feature activation+7.20e-01

Pos logit contributions
 dives+0.052
 villains+0.049
eway+0.048
 tricks+0.047
RO+0.045
Neg logit contributions
 Em-0.042
 Gem-0.042
 groceries-0.041
ama-0.040
 expensive-0.039
Token at
Token ID379
Feature activation-2.63e-01

Pos logit contributions
 dives+0.020
eway+0.018
 tricks+0.018
 films+0.018
 mer+0.018
Neg logit contributions
 Em-0.015
ama-0.015
 Gem-0.014
 Johnson-0.014
 groceries-0.014
Token the
Token ID262
Feature activation+6.71e-01

Pos logit contributions
ama+0.006
 Em+0.006
 infected+0.006
 Gem+0.006
 Johnson+0.005
Neg logit contributions
 dives-0.007
eway-0.006
 films-0.006
 mer-0.006
 tricks-0.006
Token ground
Token ID2323
Feature activation+3.21e-03

Pos logit contributions
 dives+0.019
eway+0.016
 mer+0.016
 tricks+0.016
 films+0.016
Neg logit contributions
ama-0.014
 Em-0.014
 Gem-0.014
 infected-0.013
 Johnson-0.013
Token
Token ID198
Feature activation-7.96e-01

Pos logit contributions
 dives+0.004
eway+0.004
 Fly+0.004
 tricks+0.004
 films+0.004
Neg logit contributions
 checkout-0.004
 Em-0.004
 groceries-0.003
 infected-0.003
 Gem-0.003
TokenMary
Token ID24119
Feature activation+1.16e+00

Pos logit contributions
 Em+0.016
ama+0.016
 Gem+0.016
 groceries+0.015
 Johnson+0.015
Neg logit contributions
 dives-0.023
eway-0.021
 tricks-0.020
 films-0.020
 mer-0.020
Token carefully
Token ID7773
Feature activation+1.78e+00

Pos logit contributions
 dives+0.033
eway+0.030
 tricks+0.029
 films+0.029
 mer+0.029
Neg logit contributions
 Em-0.023
ama-0.023
 Gem-0.023
 Johnson-0.022
 groceries-0.022
Token placed
Token ID4624
Feature activation+4.81e-01

Pos logit contributions
 dives+0.050
eway+0.045
 tricks+0.043
 films+0.043
 mer+0.043
Neg logit contributions
 Em-0.037
ama-0.037
 Gem-0.036
 Johnson-0.035
 groceries-0.035
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
 dives+0.012
 films+0.011
eway+0.011
 tricks+0.011
 mer+0.010
Neg logit contributions
ama-0.011
 Em-0.010
 Gem-0.010
 Johnson-0.010
 infected-0.010
Token pe
Token ID613
Feature activation+6.30e+00

Pos logit contributions
 dives+0.028
 tricks+0.025
eway+0.025
 films+0.024
 mer+0.024
Neg logit contributions
 Em-0.022
ama-0.022
 Gem-0.021
 Johnson-0.021
 checkout-0.020
Tokenb
Token ID65
Feature activation+3.73e+00

Pos logit contributions
 dives+0.151
eway+0.136
 films+0.130
 mer+0.130
 villains+0.127
Neg logit contributions
ama-0.155
 Em-0.151
 Gem-0.150
 groceries-0.147
 infected-0.145
Tokenble
Token ID903
Feature activation+2.39e+00

Pos logit contributions
 dives+0.113
eway+0.104
 tricks+0.100
 mer+0.098
 films+0.097
Neg logit contributions
 Em-0.070
ama-0.067
 Gem-0.066
 checkout-0.065
 Johnson-0.065
Token inside
Token ID2641
Feature activation-3.07e-01

Pos logit contributions
 dives+0.058
eway+0.052
 films+0.050
 tricks+0.050
 mer+0.049
Neg logit contributions
ama-0.057
 Em-0.057
 Gem-0.056
 groceries-0.055
 Johnson-0.054
Token her
Token ID607
Feature activation+1.56e-01

Pos logit contributions
ama+0.007
 Em+0.007
 Gem+0.007
 Johnson+0.007
 infected+0.007
Neg logit contributions
 dives-0.008
eway-0.007
 films-0.007
 tricks-0.007
 mer-0.007
Token dough
Token ID15756
Feature activation+8.37e-01

Pos logit contributions
 dives+0.005
 tricks+0.004
 films+0.004
eway+0.004
 mer+0.004
Neg logit contributions
 Em-0.003
 Gem-0.003
ama-0.003
 Johnson-0.003
 infected-0.003
Token children
Token ID1751
Feature activation+1.82e+00

Pos logit contributions
 dives+0.036
eway+0.033
RO+0.031
 films+0.030
 tricks+0.030
Neg logit contributions
 Em-0.025
ama-0.025
 groceries-0.024
 checkout-0.024
 Gem-0.024
Token agreed
Token ID4987
Feature activation-1.23e+00

Pos logit contributions
 dives+0.055
eway+0.052
 films+0.049
 tricks+0.049
 mer+0.048
Neg logit contributions
 Em-0.033
ama-0.032
 Gem-0.031
 checkout-0.030
 Johnson-0.030
Token and
Token ID290
Feature activation+1.21e+00

Pos logit contributions
 Em+0.022
ama+0.021
 Gem+0.021
 Johnson+0.020
 groceries+0.020
Neg logit contributions
 dives-0.038
eway-0.035
RO-0.034
 films-0.034
 mer-0.033
Token let
Token ID1309
Feature activation-3.15e-01

Pos logit contributions
eway+0.036
 dives+0.035
 films+0.034
RO+0.033
 tricks+0.033
Neg logit contributions
 Em-0.022
 Gem-0.022
 checkout-0.021
 already-0.021
 buy-0.020
Token the
Token ID262
Feature activation+1.18e+00

Pos logit contributions
 Em+0.007
ama+0.007
 Gem+0.007
 groceries+0.007
 Johnson+0.007
Neg logit contributions
 dives-0.008
eway-0.008
 tricks-0.007
 mer-0.007
 films-0.007
Token pe
Token ID613
Feature activation+6.24e+00

Pos logit contributions
 dives+0.038
eway+0.036
RO+0.033
 mer+0.033
 Fly+0.033
Neg logit contributions
ama-0.019
 Em-0.019
 Gem-0.018
 groceries-0.018
 expensive-0.018
Tokenb
Token ID65
Feature activation+3.52e+00

Pos logit contributions
 dives+0.182
 films+0.175
 villains+0.170
eway+0.169
 mer+0.167
Neg logit contributions
ama-0.115
 Gem-0.107
 infected-0.105
 Em-0.104
 groceries-0.103
Tokenble
Token ID903
Feature activation+3.16e+00

Pos logit contributions
 dives+0.098
eway+0.088
 films+0.085
 tricks+0.084
 mer+0.084
Neg logit contributions
ama-0.073
 Em-0.073
 Gem-0.071
 groceries-0.069
 Johnson-0.068
Token help
Token ID1037
Feature activation-1.13e-01

Pos logit contributions
 dives+0.091
eway+0.087
 villains+0.086
 films+0.085
RO+0.083
Neg logit contributions
 Gem-0.056
 buy-0.056
 Em-0.055
 groceries-0.055
ama-0.055
Token measure
Token ID3953
Feature activation+1.56e+00

Pos logit contributions
 Em+0.002
 Gem+0.002
ama+0.002
 Johnson+0.002
 groceries+0.002
Neg logit contributions
 dives-0.003
eway-0.003
 films-0.003
 mer-0.003
 tricks-0.003
Token the
Token ID262
Feature activation+1.18e+00

Pos logit contributions
 dives+0.044
eway+0.040
 tricks+0.038
 films+0.038
 mer+0.038
Neg logit contributions
 Em-0.032
ama-0.032
 Gem-0.031
 Johnson-0.030
 groceries-0.030
Token'm
Token ID1101
Feature activation+2.22e+00

Pos logit contributions
 dives+0.103
eway+0.096
 films+0.093
 tricks+0.091
 mer+0.090
Neg logit contributions
 Em-0.054
ama-0.052
 Gem-0.051
 infected-0.049
 checkout-0.049
Token glad
Token ID9675
Feature activation+7.99e-01

Pos logit contributions
 dives+0.073
eway+0.069
 films+0.065
 tricks+0.064
 villains+0.064
Neg logit contributions
 Em-0.036
 Gem-0.034
ama-0.034
 expensive-0.032
 infected-0.032
Token you
Token ID345
Feature activation+2.34e+00

Pos logit contributions
 dives+0.028
eway+0.028
RO+0.026
 films+0.026
 mer+0.025
Neg logit contributions
 Em-0.010
ama-0.010
 grandma-0.009
 Gem-0.009
 Johnson-0.009
Token enjoyed
Token ID8359
Feature activation+2.18e-01

Pos logit contributions
 dives+0.065
 mer+0.058
 dances+0.058
 tricks+0.055
RO+0.055
Neg logit contributions
ama-0.054
 groceries-0.051
 Gem-0.049
 Johnson-0.048
 checkout-0.048
Token the
Token ID262
Feature activation+2.22e+00

Pos logit contributions
 dives+0.006
 tricks+0.006
eway+0.006
 films+0.006
 mer+0.006
Neg logit contributions
ama-0.004
 Em-0.004
 Gem-0.004
 Johnson-0.004
 checkout-0.004
Token pe
Token ID613
Feature activation+6.17e+00

Pos logit contributions
 dives+0.066
eway+0.061
 films+0.057
 tricks+0.057
 mer+0.057
Neg logit contributions
 Em-0.041
ama-0.041
 Gem-0.040
 groceries-0.040
 Johnson-0.039
Tokenaches
Token ID3694
Feature activation+2.36e-01

Pos logit contributions
 dives+0.146
eway+0.129
 films+0.125
 mer+0.123
 tricks+0.122
Neg logit contributions
ama-0.154
 Em-0.152
 Gem-0.150
 groceries-0.145
 expensive-0.143
Token.
Token ID13
Feature activation+1.21e+00

Pos logit contributions
 dives+0.006
eway+0.005
fish+0.005
 tricks+0.005
igators+0.005
Neg logit contributions
 Em-0.005
ama-0.005
 Gem-0.005
 infected-0.005
 checkout-0.005
Token Have
Token ID8192
Feature activation+2.50e+00

Pos logit contributions
 dives+0.030
eway+0.027
 Fly+0.026
 films+0.026
 mer+0.026
Neg logit contributions
 groceries-0.028
ama-0.028
 Em-0.027
 infected-0.027
 Gem-0.027
Token a
Token ID257
Feature activation-2.52e-01

Pos logit contributions
 dives+0.080
eway+0.074
 films+0.071
 tricks+0.070
 mer+0.070
Neg logit contributions
 Em-0.042
ama-0.041
 Gem-0.041
 groceries-0.039
 Johnson-0.038
Token nice
Token ID3621
Feature activation+3.34e-01

Pos logit contributions
 Em+0.004
ama+0.004
 Gem+0.003
 groceries+0.003
 checkout+0.003
Neg logit contributions
 dives-0.009
eway-0.008
 films-0.008
 tricks-0.008
 mer-0.008
Token,
Token ID11
Feature activation-1.74e+00

Pos logit contributions
 dives+0.010
 aids+0.010
zo+0.010
 fins+0.010
ull+0.010
Neg logit contributions
 first-0.002
 groceries-0.001
 buy-0.001
 Johnson-0.001
 Em-0.001
Token she
Token ID673
Feature activation-5.85e-01

Pos logit contributions
 Em+0.029
ama+0.029
 Gem+0.028
 Johnson+0.027
 groceries+0.027
Neg logit contributions
 dives-0.056
eway-0.051
 tricks-0.049
 films-0.049
 mer-0.049
Token accidentally
Token ID14716
Feature activation+1.81e+00

Pos logit contributions
 Em+0.013
ama+0.013
 Gem+0.013
 groceries+0.012
 Johnson+0.012
Neg logit contributions
 dives-0.015
eway-0.014
 tricks-0.013
 mer-0.013
 films-0.013
Token threw
Token ID9617
Feature activation+3.85e-01

Pos logit contributions
 dives+0.056
eway+0.054
 films+0.053
igators+0.051
 tricks+0.049
Neg logit contributions
 Em-0.031
 infected-0.030
 Gem-0.029
ama-0.029
 Johnson-0.028
Token a
Token ID257
Feature activation+1.21e+00

Pos logit contributions
 dives+0.015
eway+0.015
 films+0.014
 mer+0.014
fish+0.014
Neg logit contributions
 Em-0.004
 expensive-0.004
 groceries-0.004
 infected-0.004
 Gem-0.004
Token pe
Token ID613
Feature activation+6.07e+00

Pos logit contributions
 dives+0.038
eway+0.037
 films+0.036
 dances+0.035
 Fly+0.034
Neg logit contributions
 expensive-0.021
 Em-0.019
 groceries-0.019
 infected-0.018
ama-0.018
Tokenb
Token ID65
Feature activation+3.66e+00

Pos logit contributions
 dives+0.141
eway+0.126
 films+0.123
 mer+0.119
 dances+0.116
Neg logit contributions
ama-0.153
 Em-0.151
 Gem-0.149
 infected-0.145
 groceries-0.145
Tokenble
Token ID903
Feature activation+1.98e+00

Pos logit contributions
 dives+0.108
eway+0.100
 tricks+0.097
 mer+0.094
ull+0.093
Neg logit contributions
 Em-0.071
 checkout-0.069
 Gem-0.068
 Johnson-0.068
 groceries-0.067
Token at
Token ID379
Feature activation-3.99e-01

Pos logit contributions
 dives+0.060
 films+0.058
eway+0.057
 villains+0.054
 dances+0.054
Neg logit contributions
 first-0.033
 infected-0.033
 Em-0.033
 expensive-0.033
 already-0.033
Token her
Token ID607
Feature activation-7.80e-02

Pos logit contributions
ama+0.010
 severe+0.009
 pricey+0.009
 infected+0.009
pling+0.009
Neg logit contributions
 dives-0.009
eway-0.008
 Fly-0.008
 films-0.008
 tricks-0.008
Token friend
Token ID1545
Feature activation+7.35e-01

Pos logit contributions
 Em+0.002
 Gem+0.002
 checkout+0.002
ama+0.002
 groceries+0.002
Neg logit contributions
 dives-0.002
 tricks-0.002
 mer-0.002
eway-0.002
 dances-0.002
Token spoon
Token ID24556
Feature activation+1.25e+00

Pos logit contributions
eway+0.052
 dives+0.052
 villains+0.048
 films+0.048
 tricks+0.048
Neg logit contributions
 Em-0.033
 checkout-0.032
 Gem-0.032
 groceries-0.031
 expensive-0.030
Token.
Token ID13
Feature activation+1.07e+00

Pos logit contributions
 dives+0.032
eway+0.028
 mer+0.027
 tricks+0.027
 dances+0.026
Neg logit contributions
 Em-0.029
ama-0.029
 Gem-0.028
 Johnson-0.027
 checkout-0.027
Token She
Token ID1375
Feature activation+1.10e+00

Pos logit contributions
 dives+0.033
eway+0.030
 tricks+0.029
 films+0.029
 mer+0.029
Neg logit contributions
 Em-0.019
ama-0.019
 Gem-0.019
 Johnson-0.018
 groceries-0.018
Token put
Token ID1234
Feature activation+1.66e+00

Pos logit contributions
eway+0.031
 dives+0.030
 films+0.028
 villains+0.028
 tricks+0.028
Neg logit contributions
 Em-0.020
ama-0.020
 checkout-0.020
 expensive-0.019
 Gem-0.019
Token the
Token ID262
Feature activation+1.27e+00

Pos logit contributions
 dives+0.044
 mer+0.038
 tricks+0.037
eway+0.037
 films+0.037
Neg logit contributions
ama-0.037
 Em-0.036
 Johnson-0.035
 Gem-0.035
 checkout-0.034
Token pe
Token ID613
Feature activation+6.03e+00

Pos logit contributions
 dives+0.038
eway+0.035
 tricks+0.034
 films+0.034
 mer+0.033
Neg logit contributions
 Em-0.023
ama-0.023
 Gem-0.023
 Johnson-0.022
 groceries-0.022
Tokenaches
Token ID3694
Feature activation+1.27e+00

Pos logit contributions
 dives+0.141
eway+0.127
 films+0.121
 mer+0.119
 tricks+0.118
Neg logit contributions
ama-0.151
 Em-0.150
 Gem-0.148
 groceries-0.144
 checkout-0.142
Token in
Token ID287
Feature activation+7.27e-01

Pos logit contributions
 dives+0.026
eway+0.022
 mer+0.022
 tricks+0.021
 films+0.020
Neg logit contributions
 Em-0.036
ama-0.035
 Gem-0.034
 Johnson-0.034
 checkout-0.034
Token the
Token ID262
Feature activation+5.31e-01

Pos logit contributions
 dives+0.018
 mer+0.017
eway+0.016
 films+0.016
 tricks+0.016
Neg logit contributions
ama-0.017
 Em-0.016
 infected-0.016
ongo-0.015
 Johnson-0.015
Token bowl
Token ID9396
Feature activation-1.31e+00

Pos logit contributions
 dives+0.017
eway+0.015
 films+0.015
 tricks+0.015
 mer+0.014
Neg logit contributions
 Em-0.009
ama-0.009
 Gem-0.009
 groceries-0.009
 checkout-0.009
Token and
Token ID290
Feature activation+5.70e-01

Pos logit contributions
 Em+0.032
ama+0.030
 Gem+0.030
 infected+0.029
 Johnson+0.029
Neg logit contributions
 dives-0.032
eway-0.029
 mer-0.028
 films-0.027
 tricks-0.027
Token,
Token ID11
Feature activation+5.32e-01

Pos logit contributions
 dives+0.037
eway+0.034
 tricks+0.033
 films+0.032
 mer+0.032
Neg logit contributions
 Em-0.026
ama-0.026
 Gem-0.025
 Johnson-0.024
 groceries-0.024
Token Anna
Token ID11735
Feature activation-2.28e-01

Pos logit contributions
 dives+0.015
eway+0.013
 tricks+0.013
 films+0.013
 dances+0.012
Neg logit contributions
 Em-0.012
 Gem-0.011
ama-0.011
 Johnson-0.011
 groceries-0.011
Token picked
Token ID6497
Feature activation+1.16e-01

Pos logit contributions
 Em+0.005
ama+0.005
 Gem+0.005
 groceries+0.005
 Johnson+0.005
Neg logit contributions
 dives-0.006
eway-0.006
 tricks-0.005
 films-0.005
 mer-0.005
Token up
Token ID510
Feature activation+2.76e+00

Pos logit contributions
 dives+0.003
eway+0.003
 tricks+0.003
 mer+0.003
 films+0.003
Neg logit contributions
 Em-0.002
ama-0.002
 Gem-0.002
 groceries-0.002
 Johnson-0.002
Token a
Token ID257
Feature activation+1.65e+00

Pos logit contributions
 dives+0.085
eway+0.078
 tricks+0.075
 films+0.075
 mer+0.074
Neg logit contributions
 Em-0.049
ama-0.049
 Gem-0.048
 Johnson-0.046
 groceries-0.046
Token pe
Token ID613
Feature activation+6.02e+00

Pos logit contributions
 dives+0.051
eway+0.047
 films+0.045
 tricks+0.044
 mer+0.044
Neg logit contributions
 Em-0.030
ama-0.029
 Gem-0.029
 Johnson-0.028
 groceries-0.028
Tokenb
Token ID65
Feature activation+3.17e+00

Pos logit contributions
 dives+0.146
 films+0.132
eway+0.131
 mer+0.125
 villains+0.125
Neg logit contributions
ama-0.145
 Em-0.142
 Gem-0.140
 expensive-0.137
 groceries-0.137
Tokenble
Token ID903
Feature activation+1.35e+00

Pos logit contributions
 dives+0.092
eway+0.086
 tricks+0.083
 mer+0.081
ull+0.080
Neg logit contributions
 Em-0.062
 checkout-0.060
 Johnson-0.060
 groceries-0.059
 Gem-0.059
Token that
Token ID326
Feature activation-9.49e-01

Pos logit contributions
 dives+0.043
eway+0.039
 films+0.038
RO+0.037
 villains+0.037
Neg logit contributions
ama-0.023
 Em-0.023
 Gem-0.022
 groceries-0.022
 Johnson-0.021
Token was
Token ID373
Feature activation-6.61e-02

Pos logit contributions
 Em+0.018
 Gem+0.017
ama+0.017
 expensive+0.016
 Johnson+0.016
Neg logit contributions
 dives-0.029
eway-0.027
 films-0.026
 tricks-0.025
 villains-0.025
Token different
Token ID1180
Feature activation-2.43e-01

Pos logit contributions
ama+0.001
 Em+0.001
 Gem+0.001
 Johnson+0.001
 groceries+0.001
Neg logit contributions
 dives-0.002
eway-0.002
 tricks-0.002
 mer-0.002
 films-0.002
Token day
Token ID1110
Feature activation+1.98e+00

Pos logit contributions
ama+0.007
 Em+0.006
 Gem+0.006
 expensive+0.006
 groceries+0.006
Neg logit contributions
 dives-0.009
eway-0.008
 tricks-0.008
 films-0.008
 villains-0.008
Token,
Token ID11
Feature activation+1.69e-01

Pos logit contributions
 dives+0.063
eway+0.057
 mer+0.055
 tricks+0.055
 films+0.055
Neg logit contributions
 Em-0.034
ama-0.033
 Gem-0.033
 checkout-0.032
 groceries-0.032
Token she
Token ID673
Feature activation-8.70e-03

Pos logit contributions
 dives+0.005
eway+0.005
 tricks+0.004
 films+0.004
 mer+0.004
Neg logit contributions
 Em-0.003
ama-0.003
 Gem-0.003
 Johnson-0.003
 groceries-0.003
Token found
Token ID1043
Feature activation+1.63e-01

Pos logit contributions
 Em+0.000
ama+0.000
 Gem+0.000
 expensive+0.000
 checkout+0.000
Neg logit contributions
 dives-0.000
eway-0.000
 tricks-0.000
 films-0.000
 poses-0.000
Token a
Token ID257
Feature activation+1.18e+00

Pos logit contributions
 dives+0.005
eway+0.005
 mer+0.004
 tricks+0.004
 films+0.004
Neg logit contributions
ama-0.003
 Em-0.003
 Gem-0.003
 Johnson-0.003
 checkout-0.003
Token pe
Token ID613
Feature activation+6.01e+00

Pos logit contributions
 dives+0.040
eway+0.037
 films+0.036
 tricks+0.035
RO+0.035
Neg logit contributions
 Em-0.017
ama-0.017
 Gem-0.017
 expensive-0.016
 groceries-0.016
Tokenb
Token ID65
Feature activation+3.42e+00

Pos logit contributions
 dives+0.141
eway+0.125
 films+0.124
 mer+0.118
 Fly+0.117
Neg logit contributions
ama-0.151
 Em-0.148
 Gem-0.147
 expensive-0.142
 groceries-0.141
Tokenble
Token ID903
Feature activation+1.72e+00

Pos logit contributions
 dives+0.100
eway+0.094
 tricks+0.090
 mer+0.089
ull+0.087
Neg logit contributions
 Em-0.066
 checkout-0.064
 groceries-0.064
 Gem-0.063
 Johnson-0.062
Token that
Token ID326
Feature activation-7.08e-01

Pos logit contributions
 dives+0.052
eway+0.048
 films+0.048
RO+0.046
 villains+0.046
Neg logit contributions
ama-0.032
 Em-0.031
 Gem-0.031
 expensive-0.031
 Johnson-0.030
Token was
Token ID373
Feature activation+3.40e-01

Pos logit contributions
 Em+0.014
ama+0.014
 Gem+0.013
 Johnson+0.013
 groceries+0.013
Neg logit contributions
 dives-0.021
eway-0.019
 films-0.018
 tricks-0.018
 mer-0.018
Token very
Token ID845
Feature activation-1.47e+00

Pos logit contributions
 dives+0.012
eway+0.011
 films+0.011
 tricks+0.011
 dances+0.011
Neg logit contributions
 Em-0.005
ama-0.005
 Gem-0.005
 expensive-0.004
 Johnson-0.004
Token me
Token ID502
Feature activation+4.74e+00

Pos logit contributions
ama+0.033
 Em+0.032
 groceries+0.032
 Gem+0.032
 infected+0.031
Neg logit contributions
 dives-0.030
 dances-0.024
 hops-0.024
 tricks-0.024
 mer-0.024
Token?"
Token ID1701
Feature activation+1.59e+00

Pos logit contributions
 dives+0.150
 films+0.145
eway+0.144
 villains+0.143
RO+0.138
Neg logit contributions
ama-0.073
 Em-0.070
 first-0.068
 Gem-0.068
 already-0.067
Token
Token ID198
Feature activation+1.78e+00

Pos logit contributions
 dives+0.054
eway+0.051
 tricks+0.049
 films+0.048
 mer+0.047
Neg logit contributions
 Em-0.026
 Gem-0.025
ama-0.024
 Johnson-0.023
 grandma-0.022
Token
Token ID198
Feature activation+1.03e+00

Pos logit contributions
 dives+0.066
 tricks+0.060
eway+0.059
 films+0.059
 mer+0.058
Neg logit contributions
ama-0.023
 Em-0.023
 Gem-0.021
 Johnson-0.020
 grandma-0.018
TokenAn
Token ID2025
Feature activation+1.44e+00

Pos logit contributions
 dives+0.035
 tricks+0.031
 films+0.031
eway+0.031
 dances+0.030
Neg logit contributions
 Em-0.016
ama-0.016
 Gem-0.015
 Johnson-0.015
Mom-0.014
Tokench
Token ID354
Feature activation+5.96e+00

Pos logit contributions
 dives+0.048
eway+0.044
 tricks+0.043
 films+0.042
 mer+0.042
Neg logit contributions
 Em-0.023
ama-0.023
 expensive-0.022
 Gem-0.021
 checkout-0.020
Tokenor
Token ID273
Feature activation+3.56e+00

Pos logit contributions
 dives+0.148
 films+0.132
 warriors+0.128
 villains+0.126
 tricks+0.126
Neg logit contributions
ama-0.152
 Em-0.141
 Johnson-0.134
 infected-0.134
 Gem-0.133
Token said
Token ID531
Feature activation+9.39e-01

Pos logit contributions
 dives+0.090
eway+0.081
 films+0.079
 mer+0.077
 tricks+0.077
Neg logit contributions
 Em-0.083
ama-0.082
 Gem-0.080
 Johnson-0.077
 checkout-0.077
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
 dives+0.037
 films+0.035
eway+0.034
igators+0.034
 villains+0.033
Neg logit contributions
 Em-0.011
ama-0.010
 Gem-0.010
 Johnson-0.009
 Wil-0.008
Token "
Token ID366
Feature activation-4.45e-01

Pos logit contributions
 dives+0.062
eway+0.057
igators+0.056
 villains+0.056
 tricks+0.055
Neg logit contributions
 Em-0.038
 Johnson-0.036
 Gem-0.036
ama-0.035
 Wil-0.032
TokenYes
Token ID5297
Feature activation+5.35e-01

Pos logit contributions
 Em+0.008
 Gem+0.007
ama+0.007
 Johnson+0.007
 checkout+0.007
Neg logit contributions
 dives-0.015
eway-0.013
 films-0.013
 tricks-0.013
 dances-0.013
Tokened
Token ID276
Feature activation-1.42e-01

Pos logit contributions
 dives+0.017
eway+0.015
 tricks+0.014
 films+0.014
 mer+0.014
Neg logit contributions
 Em-0.021
ama-0.021
 Gem-0.021
 groceries-0.020
 Johnson-0.020
Token up
Token ID510
Feature activation+2.39e+00

Pos logit contributions
 Em+0.003
 Gem+0.003
ama+0.003
 groceries+0.003
 Johnson+0.003
Neg logit contributions
 dives-0.004
eway-0.004
 films-0.004
 tricks-0.004
 mer-0.004
Token some
Token ID617
Feature activation+2.12e-01

Pos logit contributions
 dives+0.077
eway+0.071
 films+0.068
 tricks+0.068
 mer+0.067
Neg logit contributions
 Em-0.040
 Gem-0.039
ama-0.038
 groceries-0.037
 Johnson-0.037
Token of
Token ID286
Feature activation+1.39e+00

Pos logit contributions
 dives+0.006
eway+0.006
 films+0.005
 tricks+0.005
 mer+0.005
Neg logit contributions
 Em-0.004
ama-0.004
 groceries-0.004
 Gem-0.004
 expensive-0.004
Token the
Token ID262
Feature activation+5.26e-01

Pos logit contributions
 dives+0.046
eway+0.043
 tricks+0.040
 films+0.040
 mer+0.040
Neg logit contributions
 Em-0.023
 Gem-0.023
 groceries-0.021
ama-0.021
 checkout-0.021
Token pe
Token ID613
Feature activation+5.95e+00

Pos logit contributions
 dives+0.015
eway+0.014
 films+0.013
 tricks+0.013
 mer+0.013
Neg logit contributions
 Em-0.010
ama-0.010
 groceries-0.010
 Gem-0.010
 checkout-0.010
Tokenb
Token ID65
Feature activation+3.12e+00

Pos logit contributions
 dives+0.147
 films+0.133
eway+0.133
 villains+0.128
 mer+0.128
Neg logit contributions
ama-0.141
 Gem-0.137
 Em-0.136
 groceries-0.133
 expensive-0.131
Tokenbles
Token ID7689
Feature activation+3.67e-01

Pos logit contributions
 dives+0.093
eway+0.085
 tricks+0.082
 mer+0.081
 films+0.080
Neg logit contributions
 Em-0.059
ama-0.057
 Gem-0.056
 Johnson-0.055
 checkout-0.055
Token and
Token ID290
Feature activation+1.10e+00

Pos logit contributions
 dives+0.011
eway+0.010
 films+0.009
 tricks+0.009
 mer+0.009
Neg logit contributions
 Em-0.007
ama-0.007
 Gem-0.007
 groceries-0.007
 Johnson-0.007
Token the
Token ID262
Feature activation+4.55e-01

Pos logit contributions
eway+0.032
 dives+0.031
 films+0.030
 villains+0.029
ag+0.028
Neg logit contributions
 Em-0.022
 Gem-0.022
 checkout-0.021
ama-0.020
 groceries-0.020
Token sticks
Token ID16461
Feature activation+5.71e-01

Pos logit contributions
 dives+0.013
eway+0.012
 tricks+0.011
 films+0.011
 mer+0.011
Neg logit contributions
 Em-0.009
ama-0.009
 Gem-0.009
 Johnson-0.008
 groceries-0.008
Token his
Token ID465
Feature activation+1.07e+00

Pos logit contributions
 dives+0.077
 mer+0.070
RO+0.068
eway+0.068
 films+0.067
Neg logit contributions
 Em-0.034
 Johnson-0.033
 Gem-0.032
 expensive-0.032
 first-0.032
Token phone
Token ID3072
Feature activation+3.45e-01

Pos logit contributions
 dives+0.034
eway+0.032
RO+0.031
 mer+0.031
 Fly+0.030
Neg logit contributions
ama-0.017
 groceries-0.017
 expensive-0.017
 Em-0.016
 grandma-0.016
Token and
Token ID290
Feature activation+7.78e-01

Pos logit contributions
 dives+0.010
eway+0.009
 tricks+0.009
 films+0.009
 mer+0.009
Neg logit contributions
 Em-0.006
ama-0.006
 Gem-0.006
 Johnson-0.006
 groceries-0.006
Token threw
Token ID9617
Feature activation+1.59e+00

Pos logit contributions
eway+0.022
 dives+0.021
ile+0.020
ull+0.020
 Fly+0.019
Neg logit contributions
 Em-0.015
 grandma-0.015
 expensive-0.014
 Gem-0.014
 already-0.014
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
 dives+0.049
eway+0.047
 films+0.045
 villains+0.045
 mer+0.044
Neg logit contributions
 Em-0.029
 groceries-0.028
 Gem-0.027
 expensive-0.026
 infected-0.025
Token pe
Token ID613
Feature activation+5.92e+00

Pos logit contributions
 dives+0.045
eway+0.041
 Fly+0.039
 films+0.038
 dances+0.038
Neg logit contributions
 Em-0.029
 groceries-0.029
 expensive-0.028
 Gem-0.027
 infected-0.027
Tokenb
Token ID65
Feature activation+3.22e+00

Pos logit contributions
 dives+0.156
 films+0.148
 villains+0.141
eway+0.141
 Fly+0.140
Neg logit contributions
ama-0.127
 Gem-0.122
 infected-0.122
 expensive-0.120
 Em-0.120
Tokenble
Token ID903
Feature activation+1.87e+00

Pos logit contributions
 dives+0.096
eway+0.087
 films+0.085
 tricks+0.084
 mer+0.083
Neg logit contributions
ama-0.061
 Em-0.060
 Gem-0.059
 groceries-0.056
 Johnson-0.056
Token as
Token ID355
Feature activation+9.03e-01

Pos logit contributions
 dives+0.052
 films+0.048
eway+0.048
RO+0.046
 villains+0.046
Neg logit contributions
 Em-0.037
ama-0.037
 expensive-0.036
 groceries-0.036
 Gem-0.036
Token hard
Token ID1327
Feature activation+1.34e+00

Pos logit contributions
 dives+0.029
eway+0.026
 films+0.025
 tricks+0.025
 mer+0.025
Neg logit contributions
 Em-0.015
ama-0.015
 Gem-0.015
 groceries-0.014
 Johnson-0.014
Token as
Token ID355
Feature activation+4.40e-01

Pos logit contributions
 dives+0.034
eway+0.033
 films+0.031
igators+0.030
 mer+0.030
Neg logit contributions
 Em-0.031
 Gem-0.030
 groceries-0.029
ama-0.029
 expensive-0.028
Token He
Token ID679
Feature activation+5.00e-01

Pos logit contributions
ama+0.009
 Johnson+0.008
 Em+0.008
 grandma+0.008
 Gem+0.008
Neg logit contributions
 dives-0.018
eway-0.017
 mer-0.017
 films-0.017
ile-0.016
Token picked
Token ID6497
Feature activation+3.90e-01

Pos logit contributions
eway+0.018
 films+0.017
igators+0.016
 stunts+0.015
asm+0.015
Neg logit contributions
 already-0.008
 still-0.008
 expensive-0.007
 first-0.007
 spoiled-0.007
Token up
Token ID510
Feature activation+2.61e+00

Pos logit contributions
 dives+0.012
eway+0.012
 villains+0.012
 films+0.011
RO+0.011
Neg logit contributions
 Em-0.006
 Gem-0.006
 groceries-0.006
 expensive-0.006
ama-0.006
Token a
Token ID257
Feature activation+1.61e+00

Pos logit contributions
 dives+0.076
 mer+0.068
eway+0.067
 tricks+0.067
 films+0.067
Neg logit contributions
ama-0.052
 Em-0.050
 Gem-0.049
 checkout-0.047
 Johnson-0.046
Token round
Token ID2835
Feature activation+2.33e+00

Pos logit contributions
 dives+0.049
eway+0.044
 tricks+0.043
 mer+0.043
 films+0.043
Neg logit contributions
 Em-0.030
ama-0.029
 Gem-0.029
 Johnson-0.028
 groceries-0.028
Token pe
Token ID613
Feature activation+5.91e+00

Pos logit contributions
 dives+0.068
 films+0.064
eway+0.064
 villains+0.063
igators+0.062
Neg logit contributions
 Em-0.042
ama-0.042
 Gem-0.041
 checkout-0.040
 expensive-0.040
Tokenb
Token ID65
Feature activation+3.41e+00

Pos logit contributions
 dives+0.149
 films+0.143
eway+0.137
 villains+0.135
 mer+0.132
Neg logit contributions
ama-0.134
 Gem-0.126
 expensive-0.125
 Em-0.125
 infected-0.123
Tokenble
Token ID903
Feature activation+1.76e+00

Pos logit contributions
 dives+0.109
eway+0.100
 tricks+0.096
 films+0.096
 mer+0.096
Neg logit contributions
 Em-0.057
ama-0.057
 Gem-0.055
 Johnson-0.052
 groceries-0.052
Token and
Token ID290
Feature activation+8.55e-01

Pos logit contributions
 dives+0.059
eway+0.057
 films+0.057
 villains+0.056
RO+0.056
Neg logit contributions
 first-0.026
ama-0.024
 already-0.023
 expensive-0.023
 no-0.021
Token threw
Token ID9617
Feature activation+1.49e+00

Pos logit contributions
eway+0.028
 films+0.025
 villains+0.024
 aids+0.024
ile+0.024
Neg logit contributions
 Em-0.016
 expensive-0.015
 Gem-0.015
 already-0.014
 tired-0.014
Token it
Token ID340
Feature activation+4.38e-01

Pos logit contributions
 dives+0.050
eway+0.049
 films+0.049
 villains+0.047
igators+0.046
Neg logit contributions
 Em-0.022
 Gem-0.020
 expensive-0.019
 infected-0.018
 first-0.018
Token saw
Token ID2497
Feature activation+3.79e-01

Pos logit contributions
 Em+0.009
ama+0.009
 Gem+0.009
 Johnson+0.008
 checkout+0.008
Neg logit contributions
 dives-0.012
eway-0.011
 films-0.011
 tricks-0.011
 mer-0.011
Token something
Token ID1223
Feature activation+1.33e+00

Pos logit contributions
 dives+0.011
eway+0.010
 tricks+0.010
 mer+0.010
 films+0.010
Neg logit contributions
ama-0.007
 Em-0.007
 Gem-0.007
 checkout-0.007
 Johnson-0.007
Token strange
Token ID6283
Feature activation+2.16e+00

Pos logit contributions
 dives+0.048
eway+0.045
 films+0.044
 villains+0.043
RO+0.043
Neg logit contributions
 expensive-0.018
 Em-0.017
 Gem-0.016
 groceries-0.015
ama-0.015
Token!
Token ID0
Feature activation+6.51e-01

Pos logit contributions
 dives+0.083
 villains+0.080
 films+0.077
RO+0.076
 Fly+0.076
Neg logit contributions
 already-0.020
 expensive-0.020
 first-0.019
 yet-0.018
 Johnson-0.016
Token A
Token ID317
Feature activation+6.76e-01

Pos logit contributions
 dives+0.015
 films+0.014
eway+0.013
 tricks+0.013
 villains+0.013
Neg logit contributions
ama-0.016
 Gem-0.015
 Em-0.014
bur-0.014
 checkout-0.014
Token pe
Token ID613
Feature activation+5.90e+00

Pos logit contributions
 dives+0.022
eway+0.020
 tricks+0.019
 mer+0.019
 films+0.019
Neg logit contributions
 Em-0.011
ama-0.011
 Gem-0.011
 groceries-0.010
 Johnson-0.010
Tokenb
Token ID65
Feature activation+3.35e+00

Pos logit contributions
 dives+0.133
eway+0.117
 films+0.112
 tricks+0.110
 mer+0.110
Neg logit contributions
ama-0.154
 Em-0.154
 Gem-0.151
 Johnson-0.146
 groceries-0.145
Tokenble
Token ID903
Feature activation+2.28e+00

Pos logit contributions
 dives+0.092
eway+0.089
ull+0.084
 mer+0.082
 tricks+0.081
Neg logit contributions
 checkout-0.073
 groceries-0.072
 Em-0.070
 expensive-0.066
 Gem-0.066
Token next
Token ID1306
Feature activation+2.51e+00

Pos logit contributions
 films+0.077
 dives+0.077
eway+0.073
 poses+0.072
 villains+0.071
Neg logit contributions
 already-0.031
ama-0.031
 Em-0.030
 expensive-0.030
 Johnson-0.028
Token to
Token ID284
Feature activation-4.61e-01

Pos logit contributions
 villains+0.094
bors+0.091
RO+0.090
 films+0.090
 tunes+0.089
Neg logit contributions
 first-0.031
ama-0.027
 last-0.024
 grandma-0.024
 Gem-0.023
Token him
Token ID683
Feature activation+5.21e-01

Pos logit contributions
ama+0.012
 Gem+0.009
 hardest+0.009
 Johnson+0.009
 infected+0.009
Neg logit contributions
 dives-0.011
 films-0.010
 tricks-0.010
 swim-0.010
 mer-0.010
Token So
Token ID1406
Feature activation-1.41e+00

Pos logit contributions
 dives+0.028
eway+0.025
 films+0.024
 dances+0.024
 mer+0.023
Neg logit contributions
ama-0.018
 Em-0.018
 groceries-0.017
 Gem-0.017
 infected-0.017
Token,
Token ID11
Feature activation+1.34e-01

Pos logit contributions
 infected+0.033
 groceries+0.033
bur+0.031
 severe+0.031
 Johnson+0.031
Neg logit contributions
 dives-0.034
 mer-0.029
 dances-0.028
 jokes-0.027
 tricks-0.027
Token Lily
Token ID20037
Feature activation-6.84e-01

Pos logit contributions
 dives+0.003
 mer+0.003
 films+0.003
eway+0.003
 tricks+0.003
Neg logit contributions
ama-0.003
 Em-0.003
 infected-0.003
 Gem-0.003
 groceries-0.003
Token gave
Token ID2921
Feature activation-1.79e+00

Pos logit contributions
 Em+0.014
ama+0.014
 groceries+0.014
 Gem+0.014
 Johnson+0.014
Neg logit contributions
 dives-0.019
 mer-0.016
 tricks-0.016
eway-0.016
 dances-0.016
Token the
Token ID262
Feature activation+1.30e+00

Pos logit contributions
ama+0.045
 Gem+0.043
 pricey+0.043
 severe+0.043
 infected+0.042
Neg logit contributions
 dives-0.038
 films-0.034
 mer-0.033
 jokes-0.033
 tricks-0.032
Token pe
Token ID613
Feature activation+5.84e+00

Pos logit contributions
 dives+0.021
 tricks+0.020
 mer+0.018
ull+0.016
 hops+0.016
Neg logit contributions
 Johnson-0.042
 severe-0.042
 checkout-0.041
 infected-0.041
ama-0.041
Tokenb
Token ID65
Feature activation+3.38e+00

Pos logit contributions
 dives+0.127
eway+0.111
 tricks+0.105
 films+0.104
 mer+0.104
Neg logit contributions
 Em-0.158
ama-0.157
 Gem-0.154
 Johnson-0.151
 groceries-0.150
Tokenble
Token ID903
Feature activation+1.97e+00

Pos logit contributions
 dives+0.096
eway+0.089
 tricks+0.087
ull+0.085
 mer+0.084
Neg logit contributions
 checkout-0.070
 Em-0.069
 groceries-0.067
 Johnson-0.066
 Gem-0.065
Token to
Token ID284
Feature activation-2.23e+00

Pos logit contributions
 dives+0.056
eway+0.051
 tricks+0.049
 films+0.048
 mer+0.048
Neg logit contributions
 Em-0.040
ama-0.040
 Gem-0.039
 groceries-0.038
 Johnson-0.038
Token Jack
Token ID3619
Feature activation-1.23e-01

Pos logit contributions
 pricey+0.045
 infected+0.045
ama+0.045
 groceries+0.044
 expensive+0.043
Neg logit contributions
 dives-0.056
 mer-0.055
 jokes-0.054
 films-0.054
 tricks-0.051
Token and
Token ID290
Feature activation+5.27e-01

Pos logit contributions
ama+0.003
 Em+0.003
 Gem+0.003
 Johnson+0.002
 groceries+0.002
Neg logit contributions
 dives-0.003
eway-0.003
 tricks-0.003
 films-0.003
 mer-0.003
Token lonely
Token ID21757
Feature activation+2.20e-01

Pos logit contributions
 Gem+0.009
 Em+0.009
ama+0.008
 infected+0.008
 Wil+0.008
Neg logit contributions
 dives-0.010
 films-0.010
 tricks-0.010
 tunes-0.009
 poses-0.009
Token clock
Token ID8801
Feature activation+8.53e-01

Pos logit contributions
 dives+0.007
eway+0.006
 tricks+0.006
 films+0.006
 mer+0.006
Neg logit contributions
 Em-0.004
ama-0.004
 Gem-0.004
 Johnson-0.003
 groceries-0.003
Token on
Token ID319
Feature activation-7.16e-01

Pos logit contributions
 dives+0.024
eway+0.022
RO+0.021
 films+0.021
 mer+0.021
Neg logit contributions
 Em-0.017
ama-0.017
 Johnson-0.016
 groceries-0.016
 Gem-0.016
Token his
Token ID465
Feature activation-1.53e+00

Pos logit contributions
ama+0.017
 Em+0.016
 Gem+0.016
 infected+0.015
 Johnson+0.015
Neg logit contributions
 dives-0.018
eway-0.017
 tricks-0.016
 films-0.016
 mer-0.016
Token bed
Token ID3996
Feature activation-3.02e+00

Pos logit contributions
 Em+0.030
 Gem+0.029
ama+0.029
 infected+0.028
 Johnson+0.027
Neg logit contributions
 dives-0.045
 tricks-0.041
 films-0.041
 dances-0.039
 jokes-0.039
Tokenside
Token ID1589
Feature activation-5.25e+00

Pos logit contributions
 Em+0.057
ama+0.057
 Gem+0.056
 Johnson+0.054
 groceries+0.053
Neg logit contributions
 dives-0.089
eway-0.081
 tricks-0.078
 films-0.078
 mer-0.078
Token table
Token ID3084
Feature activation-3.18e+00

Pos logit contributions
 Gem+0.077
ama+0.076
 Em+0.076
 groceries+0.074
 Johnson+0.073
Neg logit contributions
 dives-0.178
RO-0.163
eway-0.162
 Fly-0.160
 mer-0.155
Token and
Token ID290
Feature activation-3.94e-01

Pos logit contributions
 Em+0.059
ama+0.059
 Gem+0.058
 Johnson+0.056
 groceries+0.056
Neg logit contributions
 dives-0.095
eway-0.087
 tricks-0.083
 films-0.083
 mer-0.082
Token he
Token ID339
Feature activation-9.19e-01

Pos logit contributions
 Em+0.007
 buy+0.007
 checkout+0.007
 Gem+0.007
 grandma+0.006
Neg logit contributions
 dives-0.012
eway-0.012
 films-0.011
ile-0.011
RO-0.011
Token made
Token ID925
Feature activation-4.03e-01

Pos logit contributions
ama+0.019
 Em+0.019
 Gem+0.018
 Johnson+0.018
 groceries+0.018
Neg logit contributions
 dives-0.026
eway-0.024
 tricks-0.023
 mer-0.023
 films-0.022
Token sure
Token ID1654
Feature activation-5.46e-01

Pos logit contributions
 Em+0.005
 groceries+0.005
 grandma+0.005
 expensive+0.005
 Gem+0.005
Neg logit contributions
 dives-0.014
igators-0.013
eway-0.013
ile-0.013
RO-0.013
Token toys
Token ID14958
Feature activation-2.06e+00

Pos logit contributions
 Em+0.003
ama+0.003
 Gem+0.003
 Johnson+0.003
 checkout+0.003
Neg logit contributions
 dives-0.007
eway-0.007
 tricks-0.006
 films-0.006
 mer-0.006
Token and
Token ID290
Feature activation-3.35e-01

Pos logit contributions
ama+0.050
 Em+0.050
 Gem+0.048
 infected+0.047
 checkout+0.046
Neg logit contributions
 dives-0.051
eway-0.046
 mer-0.044
 tricks-0.044
 films-0.043
Token clothes
Token ID8242
Feature activation-2.53e+00

Pos logit contributions
 Em+0.007
 Gem+0.006
 groceries+0.006
ama+0.006
 checkout+0.006
Neg logit contributions
 dives-0.010
eway-0.009
 films-0.008
 tricks-0.008
 mer-0.008
Token in
Token ID287
Feature activation-1.03e+00

Pos logit contributions
ama+0.060
 Em+0.059
 Gem+0.057
 infected+0.056
 Johnson+0.055
Neg logit contributions
 dives-0.062
 tricks-0.055
 mer-0.055
eway-0.055
 films-0.053
Token their
Token ID511
Feature activation-2.19e+00

Pos logit contributions
ama+0.036
uch+0.033
ongo+0.033
 infected+0.032
mm+0.032
Neg logit contributions
 films-0.017
 dives-0.015
 tricks-0.013
eway-0.013
 mer-0.013
Token bags
Token ID11668
Feature activation-5.24e+00

Pos logit contributions
 groceries+0.036
ama+0.036
 Em+0.035
 expensive+0.035
 grandma+0.035
Neg logit contributions
 dives-0.070
eway-0.068
RO-0.062
 mer-0.062
ull-0.062
Token.
Token ID13
Feature activation-2.97e-01

Pos logit contributions
 Em+0.143
ama+0.141
 infected+0.141
 Gem+0.134
mm+0.131
Neg logit contributions
 dives-0.103
eway-0.098
 mer-0.091
 tricks-0.090
ag-0.088
Token They
Token ID1119
Feature activation-1.36e+00

Pos logit contributions
ama+0.006
 Em+0.006
 infected+0.006
 Gem+0.006
 groceries+0.006
Neg logit contributions
 dives-0.009
eway-0.008
 films-0.007
 dances-0.007
 tricks-0.007
Token got
Token ID1392
Feature activation-1.08e+00

Pos logit contributions
ama+0.038
 groceries+0.035
 Johnson+0.035
mm+0.035
 infected+0.035
Neg logit contributions
 dives-0.031
 mer-0.027
 swim-0.026
 dances-0.025
RO-0.025
Token in
Token ID287
Feature activation-4.78e-01

Pos logit contributions
ama+0.023
 Em+0.023
 Gem+0.023
 Johnson+0.022
 checkout+0.022
Neg logit contributions
 dives-0.029
eway-0.026
 films-0.025
 tricks-0.025
 mer-0.025
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
ama+0.016
uch+0.015
ongo+0.014
ppa+0.014
mm+0.014
Neg logit contributions
 dives-0.008
 films-0.008
eway-0.007
 mer-0.007
 dances-0.007
Token packed
Token ID11856
Feature activation-1.20e+00

Pos logit contributions
ama+0.048
 groceries+0.046
ummy+0.045
mm+0.045
 Johnson+0.044
Neg logit contributions
 dives-0.033
 swim-0.030
 slit-0.029
 jokes-0.028
 tricks-0.028
Token many
Token ID867
Feature activation-7.63e-02

Pos logit contributions
ama+0.037
 Em+0.036
 Gem+0.036
 Johnson+0.035
 infected+0.035
Neg logit contributions
 dives-0.022
eway-0.018
 tricks-0.018
 films-0.018
 mer-0.017
Token toys
Token ID14958
Feature activation-1.48e+00

Pos logit contributions
ama+0.002
 Johnson+0.002
 Em+0.002
 Gem+0.002
 infected+0.002
Neg logit contributions
 dives-0.002
 films-0.002
 tricks-0.002
 dances-0.002
 mer-0.002
Token in
Token ID287
Feature activation-1.05e+00

Pos logit contributions
ama+0.039
 Em+0.038
 infected+0.038
 Gem+0.037
 Johnson+0.035
Neg logit contributions
 dives-0.032
eway-0.028
 tricks-0.028
 mer-0.028
 films-0.027
Token their
Token ID511
Feature activation-2.18e+00

Pos logit contributions
ongo+0.040
uch+0.040
ama+0.040
mm+0.037
ivery+0.036
Neg logit contributions
 films-0.014
 their-0.012
 games-0.009
 harmony-0.009
 dives-0.009
Token bags
Token ID11668
Feature activation-5.15e+00

Pos logit contributions
 Em+0.042
ama+0.042
 Gem+0.041
 infected+0.040
 Johnson+0.039
Neg logit contributions
 dives-0.064
 films-0.058
 tricks-0.056
 dances-0.055
 mer-0.054
Token.
Token ID13
Feature activation-4.28e-01

Pos logit contributions
 infected+0.159
 Em+0.156
ama+0.149
 Gem+0.143
 severe+0.143
Neg logit contributions
 dives-0.077
eway-0.074
 films-0.066
ag-0.065
 mer-0.065
Token
Token ID198
Feature activation+3.81e-01

Pos logit contributions
 infected+0.011
ama+0.011
 severe+0.011
pling+0.010
 lowest+0.010
Neg logit contributions
 dives-0.009
 films-0.009
 dances-0.008
 Fly-0.007
eway-0.007
Token
Token ID198
Feature activation-7.92e-01

Pos logit contributions
 dives+0.010
eway+0.009
 films+0.009
 tricks+0.008
 Fly+0.008
Neg logit contributions
 groceries-0.008
 Em-0.008
 Gem-0.008
 checkout-0.008
ama-0.008
TokenMom
Token ID29252
Feature activation-9.23e-01

Pos logit contributions
ama+0.017
 Em+0.017
 Gem+0.017
 groceries+0.017
 Johnson+0.017
Neg logit contributions
 dives-0.020
eway-0.018
 films-0.018
 mer-0.018
RO-0.017
Token was
Token ID373
Feature activation+2.73e-01

Pos logit contributions
 Em+0.021
 Gem+0.021
ama+0.021
 groceries+0.020
 infected+0.020
Neg logit contributions
 dives-0.024
 mer-0.020
eway-0.020
 films-0.020
 tricks-0.020
Token v
Token ID410
Feature activation+2.39e-01

Pos logit contributions
 dives+0.010
eway+0.010
 films+0.009
 tricks+0.009
RO+0.009
Neg logit contributions
 Em-0.005
ama-0.005
 Gem-0.005
 checkout-0.005
 groceries-0.004
Tokenase
Token ID589
Feature activation-9.78e-01

Pos logit contributions
 dives+0.005
eway+0.004
 films+0.004
 tricks+0.004
 mer+0.004
Neg logit contributions
ama-0.007
 Em-0.007
 Gem-0.007
 Johnson-0.007
 checkout-0.007
Token on
Token ID319
Feature activation-6.05e-01

Pos logit contributions
 Em+0.019
ama+0.019
 Gem+0.019
 Johnson+0.018
 groceries+0.018
Neg logit contributions
 dives-0.028
eway-0.026
 tricks-0.024
 films-0.024
 mer-0.024
Token her
Token ID607
Feature activation-1.07e+00

Pos logit contributions
ama+0.015
 infected+0.013
ongo+0.013
 groceries+0.013
 Gem+0.013
Neg logit contributions
 dives-0.014
eway-0.013
 films-0.013
 tricks-0.013
 mer-0.013
Token bed
Token ID3996
Feature activation-3.01e+00

Pos logit contributions
 Em+0.020
ama+0.019
 Gem+0.019
 Johnson+0.018
 infected+0.018
Neg logit contributions
 dives-0.032
 tricks-0.029
eway-0.029
 films-0.028
 mer-0.028
Tokenside
Token ID1589
Feature activation-5.05e+00

Pos logit contributions
 Em+0.060
ama+0.060
 Gem+0.058
 groceries+0.057
 Johnson+0.056
Neg logit contributions
 dives-0.085
eway-0.078
 tricks-0.075
 mer-0.075
 films-0.074
Token table
Token ID3084
Feature activation-3.09e+00

Pos logit contributions
 Gem+0.075
ama+0.073
 Em+0.072
 groceries+0.071
 checkout+0.070
Neg logit contributions
 dives-0.172
RO-0.158
eway-0.156
 Fly-0.155
 films-0.149
Token.
Token ID13
Feature activation+2.51e-01

Pos logit contributions
 Em+0.057
ama+0.056
 Gem+0.055
 Johnson+0.053
 groceries+0.053
Neg logit contributions
 dives-0.094
eway-0.085
 films-0.082
 tricks-0.082
 mer-0.081
Token She
Token ID1375
Feature activation-2.03e-01

Pos logit contributions
 dives+0.007
eway+0.006
 Fly+0.006
 dances+0.006
 films+0.006
Neg logit contributions
ama-0.005
 groceries-0.005
 infected-0.005
 severe-0.004
 expensive-0.004
Token remembered
Token ID12086
Feature activation-1.96e-01

Pos logit contributions
ama+0.004
 Em+0.004
 Gem+0.004
 groceries+0.004
 Johnson+0.004
Neg logit contributions
 dives-0.006
eway-0.005
 mer-0.005
 tricks-0.005
 dances-0.005
Token why
Token ID1521
Feature activation+8.48e-02

Pos logit contributions
ama+0.004
 Em+0.004
 Gem+0.004
 Johnson+0.004
 checkout+0.004
Neg logit contributions
 dives-0.005
eway-0.005
 mer-0.005
 tricks-0.005
 films-0.004
Token clothes
Token ID8242
Feature activation-2.85e+00

Pos logit contributions
ama+0.014
 Johnson+0.013
 Em+0.012
mm+0.012
 Gem+0.012
Neg logit contributions
 dives-0.017
 films-0.015
 tricks-0.015
 mer-0.014
 dances-0.014
Token and
Token ID290
Feature activation+4.37e-01

Pos logit contributions
 infected+0.081
ama+0.080
 Em+0.080
mm+0.076
Phill+0.075
Neg logit contributions
 dives-0.048
 mer-0.045
fish-0.040
eway-0.039
 swim-0.039
Token toys
Token ID14958
Feature activation-2.18e+00

Pos logit contributions
 dives+0.012
eway+0.011
 tricks+0.011
 films+0.011
 mer+0.011
Neg logit contributions
ama-0.009
 Em-0.009
 Gem-0.009
 Johnson-0.008
 groceries-0.008
Token into
Token ID656
Feature activation-1.03e-01

Pos logit contributions
ama+0.052
 Em+0.050
 Gem+0.048
 infected+0.048
 Johnson+0.047
Neg logit contributions
 dives-0.054
eway-0.048
 tricks-0.047
 mer-0.047
 films-0.045
Token big
Token ID1263
Feature activation-7.70e-01

Pos logit contributions
ama+0.002
 Johnson+0.002
 Em+0.002
 Gem+0.002
mm+0.002
Neg logit contributions
 dives-0.003
 films-0.002
 tricks-0.002
eway-0.002
 mer-0.002
Token bags
Token ID11668
Feature activation-5.05e+00

Pos logit contributions
ama+0.015
 Em+0.014
 Gem+0.014
 Johnson+0.014
 checkout+0.014
Neg logit contributions
 dives-0.023
 films-0.021
 tricks-0.020
 dances-0.020
 mer-0.020
Token.
Token ID13
Feature activation+5.03e-01

Pos logit contributions
 Em+0.130
ama+0.130
 infected+0.129
mm+0.124
 Gem+0.121
Neg logit contributions
 dives-0.104
eway-0.098
 mer-0.093
 tricks-0.088
 films-0.086
Token
Token ID220
Feature activation-2.04e+00

Pos logit contributions
 dives+0.014
eway+0.013
 films+0.012
 Fly+0.012
 dances+0.012
Neg logit contributions
ama-0.010
 Em-0.010
 Gem-0.010
 groceries-0.010
 infected-0.009
Token
Token ID198
Feature activation+3.16e-01

Pos logit contributions
 checkout+0.042
 Em+0.041
 Gem+0.040
 groceries+0.040
ama+0.040
Neg logit contributions
 dives-0.054
eway-0.052
 films-0.048
 Fly-0.047
 tricks-0.047
Token
Token ID198
Feature activation-3.46e-01

Pos logit contributions
 dives+0.009
eway+0.009
 films+0.008
 tricks+0.008
 mer+0.008
Neg logit contributions
ama-0.006
 Em-0.006
 Gem-0.006
 groceries-0.006
 checkout-0.006
TokenWhen
Token ID2215
Feature activation+8.40e-01

Pos logit contributions
 Em+0.007
ama+0.006
 Gem+0.006
 Johnson+0.006
 groceries+0.006
Neg logit contributions
 dives-0.010
eway-0.009
 tricks-0.009
 films-0.009
 mer-0.009
Token throwing
Token ID9644
Feature activation+1.27e+00

Pos logit contributions
 dives+0.011
eway+0.011
RO+0.010
 Fly+0.010
 films+0.010
Neg logit contributions
 checkout-0.008
 Johnson-0.007
 Gem-0.007
 Em-0.007
 groceries-0.007
Token the
Token ID262
Feature activation+7.99e-01

Pos logit contributions
 dives+0.039
eway+0.038
 mer+0.036
 villains+0.036
RO+0.035
Neg logit contributions
 groceries-0.022
 expensive-0.020
 Em-0.020
 Gem-0.019
 Johnson-0.019
Token corn
Token ID11676
Feature activation+6.54e-01

Pos logit contributions
 dives+0.021
eway+0.019
 tricks+0.018
 films+0.018
 mer+0.018
Neg logit contributions
 Em-0.018
ama-0.018
 Gem-0.018
 Johnson-0.017
 groceries-0.017
Token in
Token ID287
Feature activation-1.50e+00

Pos logit contributions
 dives+0.019
eway+0.018
RO+0.018
 films+0.017
 villains+0.017
Neg logit contributions
 groceries-0.012
ama-0.011
 Johnson-0.011
 first-0.011
 Gem-0.011
Token their
Token ID511
Feature activation-1.70e+00

Pos logit contributions
ama+0.041
 Em+0.037
ongo+0.037
ilda+0.036
 infected+0.036
Neg logit contributions
 dives-0.034
eway-0.031
 mer-0.030
 films-0.029
 tricks-0.029
Token baskets
Token ID46530
Feature activation-5.03e+00

Pos logit contributions
 groceries+0.025
 expensive+0.023
 grandma+0.022
 checkout+0.022
ama+0.021
Neg logit contributions
eway-0.061
RO-0.057
 dives-0.056
 Fly-0.055
ull-0.055
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
 Em+0.126
ama+0.125
 Gem+0.120
 infected+0.118
 Johnson+0.114
Neg logit contributions
 dives-0.116
eway-0.103
 mer-0.101
 tricks-0.100
 films-0.095
Token
Token ID198
Feature activation+3.73e-01

Pos logit contributions
 Em+0.003
ama+0.003
 Gem+0.003
 groceries+0.003
 checkout+0.003
Neg logit contributions
 dives-0.003
eway-0.002
 films-0.002
 tricks-0.002
 Fly-0.002
Token
Token ID198
Feature activation-1.93e-01

Pos logit contributions
 dives+0.010
eway+0.009
 tricks+0.008
ull+0.008
 Fly+0.008
Neg logit contributions
 Em-0.008
 groceries-0.008
 Gem-0.008
 checkout-0.008
ama-0.008
TokenSoon
Token ID28093
Feature activation+1.17e+00

Pos logit contributions
 Em+0.004
 Gem+0.004
ama+0.004
 groceries+0.004
 Johnson+0.004
Neg logit contributions
 dives-0.006
eway-0.005
 tricks-0.005
 films-0.005
 mer-0.005
Token,
Token ID11
Feature activation-3.51e-01

Pos logit contributions
 dives+0.039
eway+0.036
 tricks+0.034
 films+0.034
 mer+0.034
Neg logit contributions
 Em-0.019
ama-0.018
 Gem-0.018
 Johnson-0.017
 groceries-0.017
Token,
Token ID11
Feature activation-1.19e-01

Pos logit contributions
 Em+0.019
ama+0.019
 Gem+0.018
 Johnson+0.017
 groceries+0.017
Neg logit contributions
 dives-0.033
eway-0.030
 tricks-0.029
 films-0.029
 mer-0.029
Token which
Token ID543
Feature activation-1.03e+00

Pos logit contributions
 expensive+0.002
 groceries+0.002
 Em+0.002
 Gem+0.002
 Johnson+0.002
Neg logit contributions
 dives-0.004
eway-0.003
RO-0.003
 tricks-0.003
 dances-0.003
Token are
Token ID389
Feature activation-1.44e+00

Pos logit contributions
ama+0.018
 Em+0.017
 expensive+0.017
 Gem+0.017
 Johnson+0.017
Neg logit contributions
 dives-0.031
eway-0.029
 mer-0.027
 films-0.027
 tricks-0.027
Token like
Token ID588
Feature activation+4.98e-01

Pos logit contributions
 Em+0.022
ama+0.022
 Gem+0.021
 groceries+0.020
 Johnson+0.020
Neg logit contributions
 dives-0.048
eway-0.045
 films-0.043
 tricks-0.043
 mer-0.042
Token big
Token ID1263
Feature activation+6.12e-01

Pos logit contributions
 dives+0.016
eway+0.016
RO+0.014
 dances+0.014
ag+0.014
Neg logit contributions
 expensive-0.008
 Em-0.008
 groceries-0.008
 Gem-0.008
ama-0.007
Token bags
Token ID11668
Feature activation-5.02e+00

Pos logit contributions
eway+0.019
 dives+0.018
RO+0.016
 Fly+0.016
ag+0.016
Neg logit contributions
 groceries-0.011
 expensive-0.010
 Em-0.010
 Johnson-0.010
 Gem-0.010
Token inside
Token ID2641
Feature activation-1.70e+00

Pos logit contributions
 Em+0.111
ama+0.110
 Gem+0.106
 checkout+0.102
 infected+0.102
Neg logit contributions
 dives-0.134
eway-0.119
 tricks-0.118
 mer-0.115
 films-0.115
Token us
Token ID514
Feature activation-8.29e-02

Pos logit contributions
 Em+0.036
ama+0.035
 Gem+0.034
 checkout+0.033
 Johnson+0.033
Neg logit contributions
 dives-0.047
eway-0.043
 films-0.041
 tricks-0.041
 mer-0.040
Token.
Token ID13
Feature activation+2.61e-01

Pos logit contributions
 Em+0.002
ama+0.002
 Gem+0.002
 checkout+0.002
 groceries+0.001
Neg logit contributions
 dives-0.002
eway-0.002
 tricks-0.002
 films-0.002
 mer-0.002
Token We
Token ID775
Feature activation+9.90e-02

Pos logit contributions
 dives+0.007
eway+0.006
 films+0.006
 Fly+0.006
 mer+0.006
Neg logit contributions
ama-0.006
 Em-0.006
 Gem-0.006
 groceries-0.006
 checkout-0.006
Token breathe
Token ID18044
Feature activation+1.73e+00

Pos logit contributions
 dives+0.003
eway+0.003
 tricks+0.003
 mer+0.003
 films+0.003
Neg logit contributions
ama-0.002
 Em-0.002
 Gem-0.002
 Johnson-0.002
 groceries-0.002
Token put
Token ID1234
Feature activation+6.05e-01

Pos logit contributions
ama+0.022
 Johnson+0.021
 groceries+0.020
 Em+0.020
 infected+0.020
Neg logit contributions
 dives-0.025
 mer-0.022
 dances-0.021
 swim-0.021
 films-0.021
Token their
Token ID511
Feature activation-4.95e-02

Pos logit contributions
 dives+0.017
eway+0.016
 tricks+0.015
 mer+0.015
 films+0.015
Neg logit contributions
 Em-0.013
ama-0.012
 Gem-0.012
 groceries-0.012
 Johnson-0.012
Token things
Token ID1243
Feature activation-9.18e-01

Pos logit contributions
 groceries+0.001
ama+0.001
 Em+0.001
 expensive+0.001
 Gem+0.001
Neg logit contributions
 dives-0.002
eway-0.001
 mer-0.001
RO-0.001
 Fly-0.001
Token in
Token ID287
Feature activation-1.12e+00

Pos logit contributions
ama+0.026
 Em+0.025
 Gem+0.025
 Johnson+0.024
 infected+0.024
Neg logit contributions
 dives-0.019
eway-0.016
 mer-0.016
 tricks-0.016
 films-0.015
Token their
Token ID511
Feature activation-1.60e+00

Pos logit contributions
ama+0.037
uch+0.036
ongo+0.034
mm+0.034
ivery+0.032
Neg logit contributions
 films-0.017
 mer-0.017
 dives-0.015
 triangles-0.015
eway-0.015
Token bags
Token ID11668
Feature activation-4.99e+00

Pos logit contributions
 groceries+0.025
 checkout+0.023
 grandma+0.023
ama+0.023
 expensive+0.023
Neg logit contributions
 dives-0.053
eway-0.052
ull-0.049
RO-0.049
 mer-0.048
Token and
Token ID290
Feature activation-1.39e-01

Pos logit contributions
 Em+0.160
 infected+0.157
ama+0.152
innie+0.150
mm+0.148
Neg logit contributions
 dives-0.068
eway-0.061
ks-0.060
ag-0.059
 mer-0.057
Token zip
Token ID19974
Feature activation-1.38e-01

Pos logit contributions
 Em+0.003
 Gem+0.003
 checkout+0.003
 groceries+0.003
ama+0.003
Neg logit contributions
 dives-0.004
eway-0.004
 films-0.004
 tricks-0.004
 mer-0.004
Token them
Token ID606
Feature activation+3.66e-01

Pos logit contributions
 Em+0.003
 Gem+0.003
ama+0.003
 groceries+0.003
 checkout+0.003
Neg logit contributions
 dives-0.004
eway-0.003
 mer-0.003
 films-0.003
 tricks-0.003
Token up
Token ID510
Feature activation+1.33e+00

Pos logit contributions
 dives+0.009
eway+0.008
 films+0.007
 mer+0.007
RO+0.007
Neg logit contributions
 Em-0.009
ama-0.009
 Gem-0.009
 groceries-0.009
 Johnson-0.009
Token.
Token ID13
Feature activation-4.84e-01

Pos logit contributions
 dives+0.037
eway+0.034
 tricks+0.032
 mer+0.032
 films+0.032
Neg logit contributions
ama-0.028
 Em-0.028
 Gem-0.027
 Johnson-0.026
 groceries-0.026
Tokens
Token ID82
Feature activation-1.33e+00

Pos logit contributions
 Em+0.009
ama+0.009
 Gem+0.008
 groceries+0.008
 Johnson+0.008
Neg logit contributions
 dives-0.010
eway-0.009
 tricks-0.009
 films-0.009
 mer-0.009
Token and
Token ID290
Feature activation+2.23e-01

Pos logit contributions
 Em+0.030
ama+0.030
 Gem+0.029
 groceries+0.029
 Johnson+0.028
Neg logit contributions
 dives-0.034
eway-0.031
 films-0.029
 tricks-0.029
 mer-0.029
Token paper
Token ID3348
Feature activation+5.14e-02

Pos logit contributions
eway+0.007
 dives+0.006
ull+0.006
RO+0.006
ile+0.006
Neg logit contributions
 Em-0.004
 grandma-0.004
 groceries-0.004
 expensive-0.004
 Gem-0.004
Token in
Token ID287
Feature activation-2.14e-01

Pos logit contributions
 dives+0.002
eway+0.002
RO+0.002
 villains+0.002
 Fly+0.001
Neg logit contributions
 groceries-0.001
 grandma-0.001
ama-0.001
 first-0.001
 Em-0.001
Token their
Token ID511
Feature activation-1.42e+00

Pos logit contributions
ama+0.006
 Em+0.006
 Gem+0.006
 Johnson+0.006
 infected+0.006
Neg logit contributions
 dives-0.004
 films-0.004
eway-0.004
 mer-0.004
 tricks-0.004
Token bags
Token ID11668
Feature activation-4.96e+00

Pos logit contributions
 grandma+0.023
 expensive+0.022
 groceries+0.021
 checkout+0.020
 mom+0.020
Neg logit contributions
eway-0.048
ull-0.045
 dives-0.045
RO-0.045
 Fly-0.043
Token.
Token ID13
Feature activation-2.61e-01

Pos logit contributions
 Em+0.138
ama+0.136
 Gem+0.131
 infected+0.131
 Johnson+0.128
Neg logit contributions
 dives-0.100
eway-0.087
 mer-0.085
 tricks-0.084
ks-0.083
Token They
Token ID1119
Feature activation-1.11e+00

Pos logit contributions
 Em+0.006
ama+0.006
 Gem+0.006
 Johnson+0.006
 groceries+0.006
Neg logit contributions
 dives-0.007
eway-0.006
 tricks-0.006
 mer-0.006
 films-0.006
Token go
Token ID467
Feature activation+1.07e+00

Pos logit contributions
ama+0.023
 Em+0.022
 Gem+0.022
 Johnson+0.021
 groceries+0.021
Neg logit contributions
 dives-0.032
 tricks-0.028
eway-0.028
 mer-0.028
 films-0.028
Token to
Token ID284
Feature activation-7.82e-01

Pos logit contributions
 dives+0.028
eway+0.025
 tricks+0.024
 mer+0.024
 films+0.024
Neg logit contributions
ama-0.025
 Em-0.025
 Gem-0.024
 Johnson-0.023
 groceries-0.023
Token the
Token ID262
Feature activation+7.94e-01

Pos logit contributions
 Em+0.017
ama+0.016
 Gem+0.016
 groceries+0.016
 Johnson+0.016
Neg logit contributions
 dives-0.022
eway-0.020
 tricks-0.019
 films-0.019
 mer-0.019
Token the
Token ID262
Feature activation+1.45e+00

Pos logit contributions
ama+0.050
 Em+0.049
 Gem+0.048
 Johnson+0.047
 checkout+0.046
Neg logit contributions
 dives-0.060
eway-0.054
 tricks-0.052
 films-0.051
 mer-0.051
Token last
Token ID938
Feature activation+1.47e+00

Pos logit contributions
 dives+0.038
 tricks+0.034
eway+0.032
 mer+0.032
 dances+0.031
Neg logit contributions
ama-0.035
 Em-0.034
 Johnson-0.034
 Gem-0.033
 infected-0.032
Token things
Token ID1243
Feature activation-7.72e-01

Pos logit contributions
 dives+0.043
eway+0.041
RO+0.039
 Fly+0.039
 films+0.039
Neg logit contributions
 groceries-0.027
 expensive-0.026
 Em-0.026
 Gem-0.026
ama-0.025
Token into
Token ID656
Feature activation-3.89e-02

Pos logit contributions
ama+0.020
 Em+0.019
 infected+0.019
 Gem+0.018
 Johnson+0.018
Neg logit contributions
 dives-0.018
 tricks-0.015
eway-0.015
 mer-0.014
 swim-0.014
Token their
Token ID511
Feature activation-1.60e+00

Pos logit contributions
ama+0.001
mm+0.001
ongo+0.001
 Johnson+0.001
uch+0.001
Neg logit contributions
 dives-0.001
 films-0.001
eway-0.001
 tricks-0.001
 mer-0.001
Token bags
Token ID11668
Feature activation-4.95e+00

Pos logit contributions
 Em+0.028
ama+0.028
 Gem+0.027
 Johnson+0.026
 checkout+0.026
Neg logit contributions
 dives-0.050
eway-0.045
 tricks-0.044
 films-0.044
 mer-0.044
Token and
Token ID290
Feature activation+4.33e-01

Pos logit contributions
 Em+0.139
 infected+0.137
ama+0.133
mm+0.132
innie+0.128
Neg logit contributions
 dives-0.088
eway-0.082
 mer-0.075
 swim-0.071
 tricks-0.071
Token they
Token ID484
Feature activation-1.05e+00

Pos logit contributions
 dives+0.013
eway+0.012
 films+0.011
 tricks+0.011
 mer+0.011
Neg logit contributions
 Em-0.008
ama-0.008
 Gem-0.008
 groceries-0.008
 checkout-0.008
Token stepped
Token ID10764
Feature activation+5.33e-01

Pos logit contributions
ama+0.025
 groceries+0.023
 Johnson+0.023
 Em+0.023
mm+0.023
Neg logit contributions
 dives-0.026
 mer-0.024
eway-0.023
 swim-0.022
 tricks-0.022
Token outside
Token ID2354
Feature activation+8.68e-01

Pos logit contributions
 dives+0.013
eway+0.011
 mer+0.011
 films+0.011
 tricks+0.011
Neg logit contributions
ama-0.013
 Em-0.013
 Gem-0.013
 Johnson-0.013
 groceries-0.013
Token with
Token ID351
Feature activation+8.75e-03

Pos logit contributions
 dives+0.026
eway+0.024
 tricks+0.023
 films+0.022
 mer+0.022
Neg logit contributions
 Em-0.016
ama-0.016
 Gem-0.016
 Johnson-0.015
 groceries-0.015
Token and
Token ID290
Feature activation+9.89e-01

Pos logit contributions
ama+0.009
 Johnson+0.009
 Gem+0.009
 groceries+0.009
 Em+0.009
Neg logit contributions
 dives-0.017
eway-0.016
RO-0.015
 dances-0.015
 tricks-0.015
Token stuff
Token ID3404
Feature activation-1.58e+00

Pos logit contributions
eway+0.030
 dives+0.028
ull+0.027
 tricks+0.027
ile+0.027
Neg logit contributions
 groceries-0.018
 checkout-0.018
 Em-0.018
 Gem-0.017
ama-0.017
Token it
Token ID340
Feature activation-2.12e-01

Pos logit contributions
 Em+0.036
ama+0.035
 Gem+0.035
 groceries+0.034
 Johnson+0.034
Neg logit contributions
 dives-0.041
eway-0.037
 tricks-0.035
 films-0.035
 mer-0.035
Token in
Token ID287
Feature activation-1.23e+00

Pos logit contributions
 Em+0.004
ama+0.004
 infected+0.004
 Gem+0.004
 groceries+0.004
Neg logit contributions
 dives-0.006
eway-0.005
 films-0.005
 mer-0.005
 villains-0.005
Token the
Token ID262
Feature activation-5.77e-01

Pos logit contributions
ama+0.031
 Em+0.030
 groceries+0.029
 Gem+0.029
 checkout+0.029
Neg logit contributions
 dives-0.029
eway-0.027
 films-0.025
 mer-0.025
 Fly-0.024
Token bags
Token ID11668
Feature activation-4.95e+00

Pos logit contributions
 Em+0.013
ama+0.013
 Gem+0.013
 Johnson+0.012
 groceries+0.012
Neg logit contributions
 dives-0.015
eway-0.013
 tricks-0.013
 films-0.013
 mer-0.013
Token.
Token ID13
Feature activation-2.95e-01

Pos logit contributions
 Em+0.124
ama+0.120
 infected+0.118
 Gem+0.114
 Johnson+0.113
Neg logit contributions
 dives-0.114
eway-0.106
 mer-0.098
ull-0.096
 tricks-0.094
Token Molly
Token ID30236
Feature activation-4.94e-01

Pos logit contributions
 Em+0.007
ama+0.006
 Gem+0.006
 Johnson+0.006
 checkout+0.006
Neg logit contributions
 dives-0.008
eway-0.007
 tricks-0.007
 mer-0.007
 films-0.007
Token helps
Token ID5419
Feature activation-1.60e+00

Pos logit contributions
ama+0.011
 Em+0.011
 Gem+0.010
 checkout+0.010
 groceries+0.010
Neg logit contributions
 dives-0.012
eway-0.012
 mer-0.011
 tricks-0.011
 films-0.011
Token too
Token ID1165
Feature activation-3.39e-02

Pos logit contributions
 Em+0.033
ama+0.033
 Gem+0.032
 Johnson+0.031
 groceries+0.031
Neg logit contributions
 dives-0.045
eway-0.041
 films-0.040
 tricks-0.039
 mer-0.039
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
 Em+0.001
 checkout+0.001
 Gem+0.001
bur+0.001
mm+0.001
Neg logit contributions
 dives-0.001
 tricks-0.001
ks-0.001
eway-0.001
 warriors-0.001
Token saw
Token ID2497
Feature activation+2.26e-01

Pos logit contributions
 Em+0.019
ama+0.019
 Gem+0.018
 Johnson+0.018
 groceries+0.018
Neg logit contributions
 dives-0.028
eway-0.025
 tricks-0.024
 films-0.024
 mer-0.024
Token Sammy
Token ID44067
Feature activation-5.62e-01

Pos logit contributions
 dives+0.007
eway+0.007
 films+0.007
 tricks+0.006
 dances+0.006
Neg logit contributions
 Em-0.004
ama-0.004
 Gem-0.004
 groceries-0.003
 infected-0.003
Token leaving
Token ID4305
Feature activation-1.74e+00

Pos logit contributions
 Em+0.010
ama+0.010
 Johnson+0.010
 Gem+0.010
 infected+0.009
Neg logit contributions
 dives-0.017
eway-0.016
 films-0.015
RO-0.015
 tricks-0.015
Token with
Token ID351
Feature activation+5.32e-01

Pos logit contributions
 Em+0.034
 Gem+0.033
 groceries+0.032
ama+0.032
 Johnson+0.032
Neg logit contributions
 dives-0.052
eway-0.047
 films-0.045
RO-0.044
 dances-0.044
Token his
Token ID465
Feature activation-5.64e-01

Pos logit contributions
 dives+0.016
eway+0.015
 films+0.014
 tricks+0.014
 mer+0.014
Neg logit contributions
 Em-0.009
ama-0.009
 Gem-0.009
 groceries-0.009
 Johnson-0.009
Token bags
Token ID11668
Feature activation-4.94e+00

Pos logit contributions
 Em+0.010
ama+0.010
 Gem+0.010
 checkout+0.010
 Johnson+0.009
Neg logit contributions
 dives-0.017
eway-0.015
 tricks-0.015
 mer-0.015
 films-0.015
Token.
Token ID13
Feature activation+2.47e-01

Pos logit contributions
 Em+0.127
ama+0.123
mm+0.119
 Gem+0.119
 checkout+0.111
Neg logit contributions
 dives-0.107
eway-0.100
 mer-0.095
ag-0.095
 tricks-0.092
Token Benny
Token ID44275
Feature activation-4.55e-01

Pos logit contributions
 dives+0.007
eway+0.006
 tricks+0.006
 films+0.006
 mer+0.006
Neg logit contributions
 Em-0.005
ama-0.005
 Gem-0.005
 Johnson-0.005
 groceries-0.005
Token felt
Token ID2936
Feature activation+3.98e-01

Pos logit contributions
 Em+0.009
ama+0.009
 Gem+0.008
 Johnson+0.008
 groceries+0.008
Neg logit contributions
 dives-0.014
eway-0.012
 tricks-0.012
 films-0.012
 mer-0.012
Token en
Token ID551
Feature activation-2.23e+00

Pos logit contributions
 dives+0.013
eway+0.012
 tricks+0.012
 mer+0.011
 films+0.011
Neg logit contributions
ama-0.007
 Em-0.006
 Gem-0.006
 Johnson-0.006
 groceries-0.006
Tokenvious
Token ID1442
Feature activation-1.32e+00

Pos logit contributions
 Em+0.056
ama+0.055
 Gem+0.054
 groceries+0.052
 checkout+0.052
Neg logit contributions
 dives-0.054
eway-0.049
 films-0.045
 tricks-0.045
 mer-0.045
Token they
Token ID484
Feature activation-1.50e+00

Pos logit contributions
ama+0.001
 Em+0.001
 Gem+0.001
 Johnson+0.001
 checkout+0.001
Neg logit contributions
 dives-0.001
eway-0.001
 films-0.001
 tricks-0.001
 mer-0.001
Token had
Token ID550
Feature activation-2.15e+00

Pos logit contributions
ama+0.040
 Johnson+0.035
 Gem+0.035
 Em+0.035
 groceries+0.034
Neg logit contributions
 dives-0.037
 mer-0.032
 dances-0.031
 tricks-0.031
 swim-0.031
Token unp
Token ID8593
Feature activation-2.12e+00

Pos logit contributions
ama+0.042
 Em+0.041
 Gem+0.039
 Johnson+0.038
 checkout+0.037
Neg logit contributions
 dives-0.064
eway-0.057
 tricks-0.056
 mer-0.056
 films-0.055
Tokenacked
Token ID6021
Feature activation-2.83e-01

Pos logit contributions
 Em+0.078
ama+0.078
 Gem+0.077
 Johnson+0.075
 groceries+0.075
Neg logit contributions
 dives-0.026
eway-0.021
 films-0.018
 tricks-0.018
 mer-0.017
Token their
Token ID511
Feature activation-7.34e-01

Pos logit contributions
 Em+0.006
 Gem+0.006
ama+0.006
 groceries+0.006
 checkout+0.006
Neg logit contributions
 dives-0.008
eway-0.007
 tricks-0.007
 films-0.007
 mer-0.007
Token bags
Token ID11668
Feature activation-4.93e+00

Pos logit contributions
ama+0.015
 Em+0.014
 Gem+0.014
 Johnson+0.013
 infected+0.013
Neg logit contributions
 dives-0.022
 tricks-0.019
 films-0.019
eway-0.019
 mer-0.019
Token.
Token ID13
Feature activation-4.09e-02

Pos logit contributions
 Em+0.136
ama+0.134
 infected+0.132
mm+0.127
 Gem+0.125
Neg logit contributions
 dives-0.092
eway-0.088
 mer-0.080
 tricks-0.077
ag-0.075
Token Tom
Token ID4186
Feature activation-8.35e-01

Pos logit contributions
ama+0.001
 infected+0.001
 Em+0.001
 groceries+0.001
 Gem+0.001
Neg logit contributions
 dives-0.001
eway-0.001
 films-0.001
 Fly-0.001
 dances-0.001
Token put
Token ID1234
Feature activation+2.47e-01

Pos logit contributions
 groceries+0.019
ama+0.019
 Em+0.019
 Gem+0.019
 infected+0.018
Neg logit contributions
 dives-0.022
 mer-0.018
 tricks-0.018
 dances-0.018
 hops-0.017
Token the
Token ID262
Feature activation+2.30e-02

Pos logit contributions
 dives+0.006
eway+0.006
 tricks+0.006
 films+0.006
 mer+0.006
Neg logit contributions
ama-0.006
 Em-0.006
 Gem-0.005
 Johnson-0.005
 checkout-0.005
Token card
Token ID2657
Feature activation+1.53e-01

Pos logit contributions
 dives+0.001
 tricks+0.001
 mer+0.001
 films+0.001
 jokes+0.001
Neg logit contributions
ama-0.001
 Gem-0.000
 Em-0.000
mm-0.000
 Johnson-0.000
Token again
Token ID757
Feature activation-2.00e-01

Pos logit contributions
RO+0.008
 dives+0.008
 Fly+0.007
eway+0.007
ag+0.007
Neg logit contributions
 groceries-0.004
ama-0.004
 first-0.004
 Johnson-0.004
 expensive-0.004
Token and
Token ID290
Feature activation-1.02e+00

Pos logit contributions
 Em+0.004
ama+0.004
 Gem+0.004
 Johnson+0.004
 checkout+0.004
Neg logit contributions
 dives-0.006
eway-0.005
 tricks-0.005
 mer-0.005
 films-0.005
Token saved
Token ID7448
Feature activation-2.13e+00

Pos logit contributions
 Em+0.019
 Gem+0.018
 checkout+0.017
 grandma+0.017
 Johnson+0.017
Neg logit contributions
 dives-0.031
eway-0.030
 films-0.029
ag-0.028
RO-0.028
Token it
Token ID340
Feature activation-8.96e-01

Pos logit contributions
 Em+0.043
 Gem+0.042
 groceries+0.041
 Johnson+0.041
 expensive+0.040
Neg logit contributions
 dives-0.062
eway-0.055
 villains-0.054
RO-0.054
 mer-0.054
Token in
Token ID287
Feature activation-1.48e+00

Pos logit contributions
 Em+0.015
ama+0.014
 Gem+0.014
 Johnson+0.014
 groceries+0.014
Neg logit contributions
 dives-0.029
eway-0.026
 films-0.026
 mer-0.025
 Fly-0.025
Token bags
Token ID11668
Feature activation-4.92e+00

Pos logit contributions
ama+0.033
 Em+0.031
 Gem+0.030
 groceries+0.030
 checkout+0.029
Neg logit contributions
 dives-0.040
eway-0.036
 films-0.035
 mer-0.035
 tricks-0.034
Token for
Token ID329
Feature activation-2.10e-01

Pos logit contributions
ama+0.112
 Em+0.111
 Gem+0.106
 infected+0.105
 groceries+0.103
Neg logit contributions
 dives-0.124
eway-0.114
 mer-0.110
 tricks-0.108
 films-0.105
Token the
Token ID262
Feature activation-6.27e-01

Pos logit contributions
 Em+0.005
ama+0.005
 Gem+0.005
 Johnson+0.004
 groceries+0.004
Neg logit contributions
 dives-0.006
eway-0.005
 tricks-0.005
 films-0.005
 mer-0.005
Token next
Token ID1306
Feature activation+6.07e-01

Pos logit contributions
 Em+0.012
ama+0.011
 Gem+0.011
 groceries+0.011
 checkout+0.011
Neg logit contributions
 dives-0.019
eway-0.018
 tricks-0.017
 films-0.016
 mer-0.016
Token day
Token ID1110
Feature activation-1.06e+00

Pos logit contributions
 dives+0.019
eway+0.018
RO+0.018
 hops+0.017
 Fly+0.017
Neg logit contributions
 grandma-0.010
 expensive-0.010
 groceries-0.010
 first-0.010
 Johnson-0.010
Token.
Token ID13
Feature activation+4.44e-02

Pos logit contributions
 Em+0.018
ama+0.018
 Gem+0.018
 Johnson+0.017
 groceries+0.017
Neg logit contributions
 dives-0.033
eway-0.030
 tricks-0.029
 films-0.029
 mer-0.029
Token and
Token ID290
Feature activation+1.88e-01

Pos logit contributions
 Em+0.001
ama+0.001
 Gem+0.001
 groceries+0.001
 checkout+0.001
Neg logit contributions
 dives-0.001
eway-0.001
 tricks-0.001
 mer-0.001
 films-0.001
Token put
Token ID1234
Feature activation-9.61e-02

Pos logit contributions
eway+0.006
ile+0.006
 dives+0.006
ag+0.005
 films+0.005
Neg logit contributions
 Gem-0.003
 buy-0.003
 checkout-0.003
 Em-0.003
 groceries-0.003
Token them
Token ID606
Feature activation-3.75e-01

Pos logit contributions
 Em+0.002
 Gem+0.002
ama+0.002
 groceries+0.002
 Johnson+0.002
Neg logit contributions
 dives-0.002
eway-0.002
 villains-0.002
 tricks-0.002
 films-0.002
Token in
Token ID287
Feature activation-8.17e-01

Pos logit contributions
 groceries+0.008
 Em+0.008
ama+0.007
 Gem+0.007
 Johnson+0.007
Neg logit contributions
 dives-0.010
eway-0.010
 films-0.009
 villains-0.009
 mer-0.009
Token their
Token ID511
Feature activation-1.28e+00

Pos logit contributions
ama+0.025
ongo+0.023
ilda+0.023
uch+0.023
mm+0.022
Neg logit contributions
 dives-0.015
 mer-0.014
eway-0.014
 films-0.013
 tricks-0.013
Token baskets
Token ID46530
Feature activation-4.92e+00

Pos logit contributions
 groceries+0.020
 expensive+0.018
ama+0.017
 grandma+0.017
 checkout+0.017
Neg logit contributions
eway-0.044
 dives-0.042
RO-0.041
ull-0.041
 mer-0.040
Token.
Token ID13
Feature activation+3.18e-01

Pos logit contributions
 Em+0.124
ama+0.121
 Gem+0.116
 infected+0.116
mm+0.114
Neg logit contributions
 dives-0.112
eway-0.101
 mer-0.098
 tricks-0.095
fish-0.092
Token
Token ID198
Feature activation+5.83e-01

Pos logit contributions
 dives+0.010
eway+0.009
 tricks+0.009
 mer+0.009
 films+0.008
Neg logit contributions
 Em-0.006
ama-0.006
 Gem-0.006
 Johnson-0.006
 groceries-0.005
Token
Token ID198
Feature activation-2.62e-01

Pos logit contributions
 dives+0.016
eway+0.015
 tricks+0.014
 films+0.014
 Fly+0.014
Neg logit contributions
 Em-0.012
 groceries-0.012
 Gem-0.012
ama-0.012
 checkout-0.012
Token"
Token ID1
Feature activation-1.10e+00

Pos logit contributions
 Em+0.005
ama+0.005
 Gem+0.005
 groceries+0.005
 Johnson+0.005
Neg logit contributions
 dives-0.008
eway-0.007
 tricks-0.007
 films-0.007
 mer-0.007
TokenLook
Token ID8567
Feature activation-2.20e-01

Pos logit contributions
 Em+0.021
 checkout+0.020
 Gem+0.020
Mom+0.019
 groceries+0.019
Neg logit contributions
 dives-0.034
eway-0.032
 tricks-0.030
 films-0.029
 hops-0.029
Token She
Token ID1375
Feature activation+4.51e-01

Pos logit contributions
 dives+0.015
eway+0.013
 dances+0.013
 Fly+0.013
 films+0.013
Neg logit contributions
 Em-0.009
ama-0.009
 infected-0.009
 groceries-0.008
 checkout-0.008
Token writes
Token ID6797
Feature activation+1.35e+00

Pos logit contributions
eway+0.012
 dives+0.011
 films+0.010
ull+0.010
 mer+0.010
Neg logit contributions
 Em-0.010
 expensive-0.010
 Gem-0.009
ama-0.009
 checkout-0.009
Token "
Token ID366
Feature activation-1.38e+00

Pos logit contributions
 dives+0.038
eway+0.034
 tricks+0.033
 films+0.032
 mer+0.032
Neg logit contributions
 Em-0.028
ama-0.028
 Gem-0.027
 Johnson-0.026
 groceries-0.026
TokenTo
Token ID2514
Feature activation+8.61e-01

Pos logit contributions
ama+0.031
 Gem+0.029
 groceries+0.029
 Em+0.029
 checkout+0.029
Neg logit contributions
 dives-0.036
eway-0.033
RO-0.033
 tricks-0.032
 films-0.032
Token Ben
Token ID3932
Feature activation-1.08e+00

Pos logit contributions
 dives+0.024
eway+0.021
 tricks+0.021
 films+0.021
 mer+0.021
Neg logit contributions
ama-0.018
 Em-0.018
 Johnson-0.017
 Gem-0.017
 groceries-0.017
Token"
Token ID1
Feature activation-4.91e+00

Pos logit contributions
 Em+0.022
 groceries+0.021
 Gem+0.021
 checkout+0.020
ama+0.020
Neg logit contributions
 dives-0.030
 films-0.028
 tricks-0.027
eway-0.027
 mer-0.026
Token on
Token ID319
Feature activation+1.44e+00

Pos logit contributions
 checkout+0.120
 Em+0.119
ama+0.118
 infected+0.118
 groceries+0.116
Neg logit contributions
 dives-0.109
eway-0.098
 tricks-0.096
 films-0.093
 dances-0.092
Token the
Token ID262
Feature activation+7.84e-01

Pos logit contributions
 dives+0.038
 tricks+0.035
 films+0.034
eway+0.034
 dances+0.033
Neg logit contributions
ama-0.032
 Em-0.030
 Johnson-0.029
 Gem-0.029
 infected-0.029
Token heart
Token ID2612
Feature activation+9.29e-01

Pos logit contributions
 dives+0.021
eway+0.019
 tricks+0.019
 films+0.019
 mer+0.019
Neg logit contributions
 Em-0.017
ama-0.017
 Gem-0.016
 Johnson-0.016
 infected-0.016
Token.
Token ID13
Feature activation-7.66e-02

Pos logit contributions
 dives+0.027
eway+0.024
 tricks+0.023
 films+0.023
 mer+0.023
Neg logit contributions
 Em-0.019
ama-0.018
 Gem-0.018
 groceries-0.017
 Johnson-0.017
Token
Token ID198
Feature activation+3.64e-01

Pos logit contributions
 severe+0.002
 infected+0.002
 groceries+0.002
 expensive+0.002
ama+0.002
Neg logit contributions
 dives-0.002
 Fly-0.002
 dances-0.002
 films-0.002
eway-0.002
Token go
Token ID467
Feature activation+9.53e-01

Pos logit contributions
 Em+0.021
ama+0.021
 Gem+0.020
 Johnson+0.019
 groceries+0.019
Neg logit contributions
 dives-0.028
eway-0.026
 tricks-0.024
 films-0.024
 mer-0.024
Token back
Token ID736
Feature activation+9.61e-01

Pos logit contributions
 dives+0.028
eway+0.025
 mer+0.024
 tricks+0.024
 films+0.023
Neg logit contributions
 Em-0.019
ama-0.019
 Gem-0.019
 checkout-0.018
 groceries-0.018
Token to
Token ID284
Feature activation-1.03e+00

Pos logit contributions
 dives+0.028
eway+0.025
 tricks+0.024
 films+0.024
 mer+0.024
Neg logit contributions
 Em-0.019
ama-0.019
 Gem-0.019
 checkout-0.018
 groceries-0.018
Token the
Token ID262
Feature activation+1.53e+00

Pos logit contributions
 Em+0.017
 Gem+0.016
ama+0.016
 Johnson+0.016
 groceries+0.016
Neg logit contributions
 dives-0.033
eway-0.032
 tricks-0.030
 mer-0.029
RO-0.029
Token pool
Token ID5933
Feature activation-1.63e+00

Pos logit contributions
 dives+0.037
eway+0.036
RO+0.033
 Fly+0.032
 films+0.032
Neg logit contributions
 groceries-0.035
 checkout-0.035
 expensive-0.034
ama-0.034
 Johnson-0.033
Tokenside
Token ID1589
Feature activation-4.88e+00

Pos logit contributions
 Em+0.021
ama+0.021
 Gem+0.020
 Johnson+0.019
 groceries+0.019
Neg logit contributions
 dives-0.058
eway-0.054
 tricks-0.053
 films-0.052
 mer-0.052
Token,
Token ID11
Feature activation-1.79e+00

Pos logit contributions
ama+0.063
 Gem+0.061
 Em+0.061
 Johnson+0.060
 groceries+0.059
Neg logit contributions
 dives-0.170
eway-0.160
RO-0.156
 Fly-0.154
 films-0.152
Token Mia
Token ID32189
Feature activation-8.78e-01

Pos logit contributions
 first+0.037
 grandma+0.037
 Em+0.037
 Johnson+0.036
ama+0.036
Neg logit contributions
 dives-0.047
eway-0.047
 tricks-0.043
 films-0.043
 mer-0.042
Token.
Token ID13
Feature activation-3.57e-01

Pos logit contributions
ama+0.011
 Em+0.011
 Gem+0.011
 Johnson+0.010
 groceries+0.010
Neg logit contributions
 dives-0.031
eway-0.030
 films-0.028
 tricks-0.028
 mer-0.028
Token Maybe
Token ID6674
Feature activation-6.25e-01

Pos logit contributions
 Em+0.008
ama+0.008
 Gem+0.007
 Johnson+0.007
 groceries+0.007
Neg logit contributions
 dives-0.010
eway-0.009
 tricks-0.008
 mer-0.008
 films-0.008
Token we
Token ID356
Feature activation+1.38e-01

Pos logit contributions
 Em+0.012
ama+0.012
 Gem+0.012
 Johnson+0.011
 groceries+0.011
Neg logit contributions
 dives-0.018
eway-0.017
 tricks-0.016
 films-0.016
 mer-0.016
Token,
Token ID11
Feature activation-1.48e+00

Pos logit contributions
 Em+0.025
ama+0.025
 Gem+0.024
 groceries+0.023
 Johnson+0.023
Neg logit contributions
 dives-0.050
eway-0.046
 tricks-0.044
 films-0.044
 mer-0.044
Token they
Token ID484
Feature activation-2.04e+00

Pos logit contributions
 Em+0.036
ama+0.035
 Gem+0.035
 groceries+0.034
 Johnson+0.034
Neg logit contributions
 dives-0.037
eway-0.033
 tricks-0.031
 films-0.031
 mer-0.031
Token checked
Token ID10667
Feature activation-1.10e+00

Pos logit contributions
ama+0.052
 Em+0.051
 groceries+0.050
 Johnson+0.049
 Gem+0.049
Neg logit contributions
 dives-0.049
 mer-0.042
eway-0.042
RO-0.040
 dances-0.040
Token in
Token ID287
Feature activation-6.35e-01

Pos logit contributions
ama+0.031
 Em+0.031
 checkout+0.030
 Gem+0.030
 infected+0.030
Neg logit contributions
 dives-0.022
eway-0.020
 films-0.018
 tricks-0.018
 mer-0.018
Token their
Token ID511
Feature activation-1.78e+00

Pos logit contributions
ama+0.017
uch+0.016
ongo+0.016
mm+0.016
ppa+0.015
Neg logit contributions
 dives-0.014
 films-0.014
eway-0.013
 tricks-0.013
 mer-0.013
Token bags
Token ID11668
Feature activation-4.87e+00

Pos logit contributions
ama+0.032
 groceries+0.032
 Em+0.032
 Gem+0.031
 expensive+0.031
Neg logit contributions
 dives-0.053
eway-0.051
 mer-0.048
 tricks-0.047
RO-0.047
Token and
Token ID290
Feature activation-5.05e-01

Pos logit contributions
 Em+0.142
 infected+0.139
mm+0.134
ama+0.130
innie+0.130
Neg logit contributions
 dives-0.083
eway-0.082
ag-0.074
 mer-0.071
ull-0.068
Token got
Token ID1392
Feature activation-1.47e+00

Pos logit contributions
 Em+0.010
 Gem+0.010
 groceries+0.009
 checkout+0.009
ama+0.009
Neg logit contributions
 dives-0.015
eway-0.014
 films-0.013
 tricks-0.013
RO-0.013
Token their
Token ID511
Feature activation-9.96e-01

Pos logit contributions
 Em+0.028
 Gem+0.027
ama+0.027
 groceries+0.026
 checkout+0.026
Neg logit contributions
 dives-0.044
eway-0.041
 tricks-0.039
 films-0.038
 mer-0.038
Token tickets
Token ID8587
Feature activation-2.03e+00

Pos logit contributions
 Em+0.019
ama+0.019
 Gem+0.018
 groceries+0.018
 Johnson+0.018
Neg logit contributions
 dives-0.030
eway-0.027
 tricks-0.026
 films-0.026
 mer-0.026
Token.
Token ID13
Feature activation-2.05e-01

Pos logit contributions
 Em+0.041
ama+0.041
 Gem+0.039
 checkout+0.038
 Johnson+0.038
Neg logit contributions
 dives-0.057
eway-0.052
 tricks-0.050
 mer-0.050
 films-0.049
Token pack
Token ID2353
Feature activation-7.37e-01

Pos logit contributions
ama+0.022
 Em+0.022
 Gem+0.021
 Johnson+0.021
 groceries+0.021
Neg logit contributions
 dives-0.031
eway-0.027
 tricks-0.027
 mer-0.027
 films-0.027
Token some
Token ID617
Feature activation+6.11e-03

Pos logit contributions
ama+0.021
 Em+0.021
 Gem+0.020
 Johnson+0.020
 checkout+0.020
Neg logit contributions
 dives-0.015
eway-0.013
 tricks-0.013
 films-0.012
 mer-0.012
Token gems
Token ID23685
Feature activation-7.47e-01

Pos logit contributions
 dives+0.000
eway+0.000
 tricks+0.000
 films+0.000
 mer+0.000
Neg logit contributions
 Em-0.000
ama-0.000
 Gem-0.000
 Johnson-0.000
 groceries-0.000
Token in
Token ID287
Feature activation-8.70e-01

Pos logit contributions
 Em+0.014
ama+0.014
 Gem+0.014
 groceries+0.014
 Johnson+0.013
Neg logit contributions
 dives-0.022
eway-0.020
 films-0.019
 tricks-0.019
RO-0.019
Token their
Token ID511
Feature activation-1.88e+00

Pos logit contributions
ama+0.032
ongo+0.030
uch+0.030
mm+0.029
ilda+0.029
Neg logit contributions
 dives-0.011
 mer-0.010
eway-0.010
 films-0.010
 swim-0.010
Token bags
Token ID11668
Feature activation-4.84e+00

Pos logit contributions
 groceries+0.025
ama+0.024
 expensive+0.024
 Em+0.024
 Gem+0.024
Neg logit contributions
 dives-0.065
eway-0.064
RO-0.060
ull-0.059
 mer-0.058
Token.
Token ID13
Feature activation-5.78e-01

Pos logit contributions
 Em+0.143
 infected+0.139
ama+0.133
 severe+0.129
mm+0.128
Neg logit contributions
 dives-0.086
eway-0.083
ag-0.075
 mer-0.073
ull-0.073
Token They
Token ID1119
Feature activation-8.53e-01

Pos logit contributions
ama+0.016
 Em+0.015
 infected+0.015
 Gem+0.015
 groceries+0.015
Neg logit contributions
 dives-0.013
eway-0.011
 tricks-0.010
 films-0.010
 dances-0.010
Token do
Token ID466
Feature activation+3.21e+00

Pos logit contributions
ama+0.019
 Em+0.018
 Johnson+0.018
 Gem+0.018
 infected+0.017
Neg logit contributions
 dives-0.024
 mer-0.020
 tricks-0.020
 swim-0.020
 dances-0.020
Token not
Token ID407
Feature activation-4.54e-01

Pos logit contributions
 dives+0.118
eway+0.109
 tricks+0.106
 films+0.105
 mer+0.105
Neg logit contributions
 Em-0.040
ama-0.040
 Gem-0.038
 Johnson-0.036
 groceries-0.036
Token see
Token ID766
Feature activation+7.62e-01

Pos logit contributions
ama+0.008
 Em+0.008
 Gem+0.008
 Johnson+0.008
 groceries+0.008
Neg logit contributions
 dives-0.014
eway-0.013
 tricks-0.012
 mer-0.012
 films-0.012
Token coats
Token ID30720
Feature activation-2.69e+00

Pos logit contributions
 dives+0.002
eway+0.002
 tricks+0.002
 films+0.002
 mer+0.002
Neg logit contributions
 Em-0.002
 Gem-0.002
 groceries-0.002
ama-0.002
 checkout-0.002
Token and
Token ID290
Feature activation+9.67e-01

Pos logit contributions
ama+0.064
 Em+0.061
 Gem+0.060
 checkout+0.059
 infected+0.058
Neg logit contributions
 dives-0.066
eway-0.059
 mer-0.058
 tricks-0.057
 films-0.055
Token put
Token ID1234
Feature activation+4.06e-02

Pos logit contributions
 dives+0.026
eway+0.025
 films+0.023
 tricks+0.023
 mer+0.023
Neg logit contributions
 Em-0.020
 Gem-0.020
 groceries-0.020
ama-0.019
 expensive-0.019
Token away
Token ID1497
Feature activation+5.49e-01

Pos logit contributions
 dives+0.001
eway+0.001
 villains+0.001
RO+0.001
 mer+0.001
Neg logit contributions
 Em-0.001
 groceries-0.001
 Gem-0.001
 expensive-0.001
ama-0.001
Token their
Token ID511
Feature activation-6.16e-01

Pos logit contributions
 dives+0.014
eway+0.012
 villains+0.012
RO+0.012
ile+0.012
Neg logit contributions
 groceries-0.013
 Em-0.013
 Gem-0.012
 expensive-0.012
 grandma-0.012
Token bags
Token ID11668
Feature activation-4.83e+00

Pos logit contributions
 groceries+0.012
 expensive+0.012
 Em+0.011
ama+0.011
 grandma+0.011
Neg logit contributions
eway-0.017
 dives-0.017
ull-0.016
 Fly-0.016
RO-0.015
Token.
Token ID13
Feature activation-2.52e-01

Pos logit contributions
ama+0.134
 Em+0.129
mm+0.128
 Gem+0.125
innie+0.122
Neg logit contributions
 dives-0.092
 mer-0.083
eway-0.082
ag-0.080
 swim-0.076
Token They
Token ID1119
Feature activation-1.19e+00

Pos logit contributions
 Em+0.006
ama+0.006
 Gem+0.006
 Johnson+0.005
 checkout+0.005
Neg logit contributions
 dives-0.007
eway-0.006
 tricks-0.006
 mer-0.006
 films-0.006
Token c
Token ID269
Feature activation-7.57e-01

Pos logit contributions
ama+0.032
 Johnson+0.030
 groceries+0.030
ummy+0.030
mm+0.029
Neg logit contributions
 dives-0.027
 mer-0.024
 swim-0.024
 slit-0.023
 dances-0.022
Tokenuddled
Token ID32745
Feature activation-1.12e+00

Pos logit contributions
ama+0.015
 Em+0.015
 Gem+0.014
 groceries+0.014
 checkout+0.014
Neg logit contributions
 dives-0.022
eway-0.020
 mer-0.019
 films-0.019
 tricks-0.019
Token with
Token ID351
Feature activation-4.43e-01

Pos logit contributions
 Em+0.025
 Johnson+0.024
 Gem+0.023
 groceries+0.023
ama+0.023
Neg logit contributions
 dives-0.031
eway-0.028
 villains-0.026
RO-0.026
igators-0.026
Token said
Token ID531
Feature activation-1.37e-01

Pos logit contributions
 Em+0.022
ama+0.022
 groceries+0.021
 Gem+0.021
 checkout+0.021
Neg logit contributions
 dives-0.029
 mer-0.024
eway-0.024
 tricks-0.024
 dances-0.024
Token goodbye
Token ID24829
Feature activation-1.51e+00

Pos logit contributions
 Em+0.003
ama+0.003
 Gem+0.003
 Johnson+0.002
 groceries+0.002
Neg logit contributions
 dives-0.004
eway-0.004
 films-0.004
igators-0.003
RO-0.003
Token to
Token ID284
Feature activation-1.66e+00

Pos logit contributions
 Em+0.035
ama+0.034
 Gem+0.034
 groceries+0.033
 checkout+0.033
Neg logit contributions
 dives-0.039
eway-0.035
 tricks-0.033
 mer-0.033
 films-0.033
Token the
Token ID262
Feature activation+2.27e-01

Pos logit contributions
ama+0.042
 infected+0.040
 Johnson+0.039
 groceries+0.039
 Em+0.039
Neg logit contributions
 dives-0.039
 films-0.034
 tricks-0.034
 mer-0.033
eway-0.033
Token se
Token ID384
Feature activation+2.72e+00

Pos logit contributions
 dives+0.004
 mer+0.004
eway+0.004
 tricks+0.004
 films+0.004
Neg logit contributions
 Em-0.007
ama-0.007
 Johnson-0.006
 Gem-0.006
 infected-0.006
Tokenag
Token ID363
Feature activation+4.71e+00

Pos logit contributions
 dives+0.047
 warriors+0.044
 Fly+0.042
 films+0.041
 mer+0.041
Neg logit contributions
ama-0.083
my-0.080
 expensive-0.079
bur-0.079
 Em-0.079
Tokenull
Token ID724
Feature activation+1.47e+00

Pos logit contributions
 dives+0.080
 villains+0.071
 poses+0.070
igators+0.068
 warriors+0.066
Neg logit contributions
ama-0.157
 first-0.145
 Gem-0.143
 Em-0.139
 two-0.138
Tokens
Token ID82
Feature activation-9.99e-01

Pos logit contributions
 dives+0.044
eway+0.041
 films+0.039
 tricks+0.039
 mer+0.038
Neg logit contributions
 Em-0.028
ama-0.028
 Gem-0.027
 Johnson-0.026
 groceries-0.025
Token and
Token ID290
Feature activation-3.27e-01

Pos logit contributions
 Em+0.019
ama+0.019
 Gem+0.019
 groceries+0.018
 Johnson+0.018
Neg logit contributions
 dives-0.030
eway-0.027
 tricks-0.026
 films-0.026
 mer-0.026
Token put
Token ID1234
Feature activation+2.15e-01

Pos logit contributions
 Em+0.007
 Gem+0.006
ama+0.006
 grandma+0.006
 checkout+0.006
Neg logit contributions
 dives-0.009
eway-0.009
 films-0.009
 tricks-0.008
igators-0.008
Token his
Token ID465
Feature activation-2.89e-02

Pos logit contributions
 dives+0.006
eway+0.006
 films+0.005
 villains+0.005
 tricks+0.005
Neg logit contributions
 Em-0.005
 Gem-0.004
ama-0.004
 groceries-0.004
 checkout-0.004
Token.
Token ID13
Feature activation+8.89e-01

Pos logit contributions
 dives+0.047
eway+0.044
 films+0.042
 mer+0.042
RO+0.041
Neg logit contributions
 Em-0.018
ama-0.018
 Gem-0.017
 Johnson-0.016
 groceries-0.016
Token The
Token ID383
Feature activation+6.00e-01

Pos logit contributions
 dives+0.026
eway+0.023
 tricks+0.023
 mer+0.022
 films+0.022
Neg logit contributions
 Em-0.018
ama-0.018
 Gem-0.017
 Johnson-0.017
 checkout-0.016
Token more
Token ID517
Feature activation+2.85e+00

Pos logit contributions
 dives+0.017
eway+0.015
 tricks+0.014
 films+0.014
 mer+0.014
Neg logit contributions
 Em-0.013
ama-0.013
 Gem-0.012
 groceries-0.012
 Johnson-0.012
Token,
Token ID11
Feature activation+1.22e+00

Pos logit contributions
 dives+0.081
eway+0.080
RO+0.079
 mer+0.075
 films+0.074
Neg logit contributions
 expensive-0.051
 grandma-0.047
 first-0.046
 Em-0.046
 Gem-0.046
Token the
Token ID262
Feature activation+3.55e-01

Pos logit contributions
 dives+0.038
eway+0.036
RO+0.033
 tricks+0.033
 films+0.033
Neg logit contributions
 Em-0.021
 Gem-0.021
 expensive-0.020
 groceries-0.020
ama-0.020
Token mer
Token ID4017
Feature activation+4.83e+00

Pos logit contributions
 dives+0.011
eway+0.010
 films+0.009
 tricks+0.009
 mer+0.009
Neg logit contributions
 Em-0.007
ama-0.006
 Gem-0.006
 groceries-0.006
 checkout-0.006
Tokenrier
Token ID5277
Feature activation+2.08e+00

Pos logit contributions
RO+0.140
 slit+0.137
 Skip+0.135
igators+0.134
Ro+0.132
Neg logit contributions
 first-0.069
ama-0.069
 biggest-0.066
ummy-0.063
 grandma-0.063
Token.
Token ID13
Feature activation+3.48e-01

Pos logit contributions
 dives+0.070
eway+0.065
 films+0.065
RO+0.063
 Fly+0.062
Neg logit contributions
ama-0.029
 Em-0.027
 first-0.027
 Gem-0.027
 already-0.027
Token Come
Token ID7911
Feature activation-3.01e-01

Pos logit contributions
 dives+0.009
eway+0.009
 tricks+0.008
 films+0.008
 mer+0.008
Neg logit contributions
 Em-0.008
ama-0.007
 Gem-0.007
 Johnson-0.007
 groceries-0.007
Token to
Token ID284
Feature activation+4.38e-02

Pos logit contributions
 Em+0.007
 Gem+0.007
ama+0.007
 infected+0.007
 groceries+0.007
Neg logit contributions
 dives-0.008
eway-0.007
 mer-0.006
 tricks-0.006
 Fly-0.006
Token my
Token ID616
Feature activation-5.21e-02

Pos logit contributions
 dives+0.001
eway+0.001
 tricks+0.001
 poses+0.001
 films+0.001
Neg logit contributions
 Em-0.001
 Gem-0.001
ama-0.001
 grandma-0.001
 checkout-0.001
Token
Token ID220
Feature activation-1.59e+00

Pos logit contributions
 Em+0.000
ama+0.000
 Gem+0.000
 Johnson+0.000
 checkout+0.000
Neg logit contributions
 dives-0.001
eway-0.000
 mer-0.000
 tricks-0.000
 films-0.000
Token
Token ID198
Feature activation+7.73e-03

Pos logit contributions
 checkout+0.032
 Em+0.032
 Gem+0.032
 groceries+0.032
ama+0.031
Neg logit contributions
 dives-0.043
eway-0.041
 tricks-0.038
 Fly-0.037
 films-0.037
Token
Token ID198
Feature activation-7.06e-01

Pos logit contributions
 dives+0.000
eway+0.000
 tricks+0.000
 Fly+0.000
ull+0.000
Neg logit contributions
 groceries-0.000
 Em-0.000
 checkout-0.000
 Gem-0.000
ama-0.000
TokenThe
Token ID464
Feature activation-2.03e-01

Pos logit contributions
 Em+0.014
ama+0.014
 Gem+0.013
 groceries+0.013
 Johnson+0.013
Neg logit contributions
 dives-0.021
eway-0.019
 tricks-0.018
 films-0.018
 mer-0.018
Token big
Token ID1263
Feature activation+2.07e+00

Pos logit contributions
 first+0.003
 expensive+0.003
ama+0.003
 checkout+0.003
 groceries+0.002
Neg logit contributions
eway-0.007
 dives-0.007
igators-0.006
ull-0.006
 films-0.006
Token do
Token ID466
Feature activation+4.66e+00

Pos logit contributions
eway+0.059
 dives+0.058
 mer+0.054
RO+0.053
ull+0.052
Neg logit contributions
ama-0.039
 expensive-0.039
 Johnson-0.038
 first-0.038
 checkout-0.038
Tokenggy
Token ID19970
Feature activation+2.64e+00

Pos logit contributions
igators+0.123
 dives+0.122
 films+0.118
 mer+0.114
 dances+0.109
Neg logit contributions
ama-0.114
 already-0.100
't-0.095
 first-0.094
 no-0.089
Token got
Token ID1392
Feature activation-1.27e+00

Pos logit contributions
 dives+0.078
eway+0.073
 films+0.068
 mer+0.068
 tricks+0.068
Neg logit contributions
 Em-0.050
ama-0.050
 Gem-0.048
 checkout-0.047
 Johnson-0.047
Token sick
Token ID6639
Feature activation-4.18e-01

Pos logit contributions
 Em+0.020
ama+0.019
 Gem+0.019
 groceries+0.018
 Johnson+0.018
Neg logit contributions
 dives-0.042
eway-0.039
 tricks-0.038
 films-0.038
 mer-0.037
Tokener
Token ID263
Feature activation-1.31e+00

Pos logit contributions
 groceries+0.006
 Em+0.006
 Johnson+0.006
ama+0.006
 Gem+0.006
Neg logit contributions
 dives-0.014
eway-0.013
RO-0.013
 films-0.012
 dances-0.012
Token and
Token ID290
Feature activation-4.07e-01

Pos logit contributions
 Em+0.025
ama+0.025
 Gem+0.024
 Johnson+0.024
 groceries+0.023
Neg logit contributions
 dives-0.039
eway-0.035
 tricks-0.034
 films-0.034
 mer-0.033
Token morning
Token ID3329
Feature activation+7.53e-01

Pos logit contributions
ama+0.013
 Em+0.013
 expensive+0.013
 Gem+0.012
 Johnson+0.012
Neg logit contributions
 dives-0.021
eway-0.020
 films-0.019
 tricks-0.019
 mer-0.018
Token,
Token ID11
Feature activation-9.80e-02

Pos logit contributions
 dives+0.030
 films+0.030
igators+0.029
 poses+0.029
 tricks+0.029
Neg logit contributions
ama-0.006
 Em-0.005
 Johnson-0.005
 Gem-0.005
 already-0.004
Token he
Token ID339
Feature activation+1.70e-01

Pos logit contributions
 Em+0.002
 Gem+0.002
 Johnson+0.002
ama+0.002
 expensive+0.002
Neg logit contributions
 dives-0.003
 films-0.003
eway-0.003
igators-0.003
 dances-0.003
Token found
Token ID1043
Feature activation-1.59e-01

Pos logit contributions
 dives+0.005
eway+0.004
 films+0.004
 tricks+0.004
 mer+0.004
Neg logit contributions
 Em-0.003
ama-0.003
 Gem-0.003
 Johnson-0.003
 groceries-0.003
Token a
Token ID257
Feature activation+7.93e-01

Pos logit contributions
 Em+0.003
ama+0.003
 Gem+0.003
 Johnson+0.003
 checkout+0.003
Neg logit contributions
 dives-0.005
eway-0.005
 tricks-0.004
 mer-0.004
 films-0.004
Token pe
Token ID613
Feature activation+5.38e+00

Pos logit contributions
 dives+0.026
eway+0.024
 tricks+0.024
 mer+0.023
 films+0.023
Neg logit contributions
 Em-0.012
ama-0.012
 Gem-0.012
 groceries-0.011
 Johnson-0.011
Tokenb
Token ID65
Feature activation+3.14e+00

Pos logit contributions
 dives+0.112
eway+0.099
 tricks+0.095
 mer+0.091
 films+0.088
Neg logit contributions
 Em-0.150
ama-0.147
 Gem-0.146
 Johnson-0.145
 checkout-0.143
Tokenble
Token ID903
Feature activation+1.56e+00

Pos logit contributions
 dives+0.083
eway+0.080
 tricks+0.077
ull+0.075
 mer+0.073
Neg logit contributions
 checkout-0.069
 Em-0.068
 groceries-0.067
 Johnson-0.065
 Gem-0.064
Token sitting
Token ID5586
Feature activation+1.15e+00

Pos logit contributions
 dives+0.046
eway+0.043
 films+0.042
RO+0.041
 dances+0.041
Neg logit contributions
ama-0.029
 already-0.028
 expensive-0.028
 Em-0.028
 first-0.028
Token on
Token ID319
Feature activation+3.84e-01

Pos logit contributions
 dives+0.019
 mer+0.018
eway+0.017
ull+0.016
 tricks+0.016
Neg logit contributions
 Em-0.037
 Gem-0.036
ama-0.035
 checkout-0.034
 Johnson-0.033
Token the
Token ID262
Feature activation+8.36e-01

Pos logit contributions
 dives+0.012
eway+0.011
 tricks+0.011
 mer+0.011
 films+0.011
Neg logit contributions
 Em-0.006
ama-0.006
 Gem-0.006
 Johnson-0.006
 groceries-0.006
Token.
Token ID13
Feature activation+7.55e-01

Pos logit contributions
 dives+0.008
eway+0.008
RO+0.008
 films+0.008
igators+0.008
Neg logit contributions
 Em-0.002
 first-0.002
ama-0.001
 tired-0.001
 infected-0.001
Token He
Token ID679
Feature activation-2.62e-02

Pos logit contributions
 dives+0.027
eway+0.027
igators+0.025
 tunes+0.025
 dances+0.025
Neg logit contributions
 Em-0.009
 Johnson-0.009
ama-0.008
Mom-0.008
 mom-0.008
Token showed
Token ID3751
Feature activation-4.87e-01

Pos logit contributions
 already+0.000
 Em+0.000
 checkout+0.000
 still+0.000
 expensive+0.000
Neg logit contributions
eway-0.001
 films-0.001
 dives-0.001
igators-0.001
ag-0.001
Token Lily
Token ID20037
Feature activation-8.92e-01

Pos logit contributions
 Em+0.008
 grandma+0.007
 Gem+0.007
 groceries+0.007
 expensive+0.007
Neg logit contributions
 dives-0.016
eway-0.015
 films-0.015
 sym-0.014
RO-0.014
Token his
Token ID465
Feature activation+1.09e+00

Pos logit contributions
 Em+0.017
 Gem+0.016
 expensive+0.016
ama+0.016
 groceries+0.016
Neg logit contributions
 dives-0.026
eway-0.024
RO-0.023
 villains-0.023
 films-0.023
Token pe
Token ID613
Feature activation+4.73e+00

Pos logit contributions
 dives+0.026
 tricks+0.023
eway+0.022
 mer+0.022
 hops+0.021
Neg logit contributions
 Em-0.028
ama-0.028
 Johnson-0.027
 checkout-0.027
 Gem-0.027
Tokenb
Token ID65
Feature activation+2.25e+00

Pos logit contributions
 dives+0.103
eway+0.090
 tricks+0.085
 films+0.084
 mer+0.084
Neg logit contributions
 Em-0.127
ama-0.127
 Gem-0.124
 Johnson-0.121
 groceries-0.121
Tokenble
Token ID903
Feature activation+5.55e-01

Pos logit contributions
 dives+0.066
eway+0.061
 tricks+0.059
 mer+0.058
ull+0.057
Neg logit contributions
 Em-0.044
 checkout-0.042
 groceries-0.041
 Gem-0.041
ama-0.041
Token.
Token ID13
Feature activation+6.70e-01

Pos logit contributions
 dives+0.017
eway+0.016
 films+0.015
 mer+0.015
 tricks+0.015
Neg logit contributions
ama-0.010
 Em-0.010
 Gem-0.009
 groceries-0.009
 Johnson-0.009
Token It
Token ID632
Feature activation+5.19e-01

Pos logit contributions
 dives+0.023
eway+0.021
igators+0.021
 films+0.020
 tricks+0.020
Neg logit contributions
 Em-0.010
ama-0.009
 Gem-0.009
 Johnson-0.009
 expensive-0.008
Token was
Token ID373
Feature activation+3.59e-01

Pos logit contributions
 dives+0.017
eway+0.017
 films+0.016
 villains+0.015
 mer+0.015
Neg logit contributions
 Em-0.008
 expensive-0.008
 infected-0.007
 already-0.007
 Gem-0.007
Token
Token ID198
Feature activation+1.50e+00

Pos logit contributions
 dives+0.089
 tricks+0.081
 films+0.080
 dances+0.078
 mer+0.078
Neg logit contributions
ama-0.035
 Em-0.034
 Gem-0.032
Mom-0.031
 Johnson-0.030
Token"
Token ID1
Feature activation-5.02e-01

Pos logit contributions
 dives+0.052
 tricks+0.046
 films+0.046
eway+0.045
 dances+0.045
Neg logit contributions
ama-0.023
 Em-0.023
 Gem-0.022
 Johnson-0.020
 checkout-0.020
TokenWe
Token ID1135
Feature activation+1.37e+00

Pos logit contributions
 Em+0.009
 Gem+0.009
 Johnson+0.008
ama+0.008
 checkout+0.008
Neg logit contributions
 dives-0.017
eway-0.015
 films-0.015
 tricks-0.015
 dances-0.014
Token didn
Token ID1422
Feature activation+3.65e-01

Pos logit contributions
 dives+0.045
eway+0.041
 tricks+0.040
 mer+0.040
 films+0.040
Neg logit contributions
ama-0.022
 Em-0.021
 Gem-0.021
 Johnson-0.020
 groceries-0.020
Token't
Token ID470
Feature activation+1.00e+00

Pos logit contributions
 dives+0.013
eway+0.012
 tricks+0.012
 films+0.012
 Fly+0.012
Neg logit contributions
ama-0.004
 Gem-0.004
 Em-0.004
 checkout-0.004
 groceries-0.004
Token know
Token ID760
Feature activation+2.45e+00

Pos logit contributions
 dives+0.031
 tricks+0.028
eway+0.028
 mer+0.027
 films+0.026
Neg logit contributions
ama-0.019
 Em-0.018
 groceries-0.018
 checkout-0.017
 Gem-0.017
Token it
Token ID340
Feature activation+1.41e+00

Pos logit contributions
 dives+0.080
eway+0.073
 tricks+0.070
 films+0.070
 mer+0.070
Neg logit contributions
 Em-0.040
ama-0.039
 Gem-0.038
 groceries-0.037
 Johnson-0.037
Token was
Token ID373
Feature activation+2.37e-01

Pos logit contributions
 dives+0.041
eway+0.037
 tricks+0.036
 films+0.036
 mer+0.035
Neg logit contributions
 Em-0.028
ama-0.028
 Gem-0.027
 Johnson-0.026
 groceries-0.026
Token your
Token ID534
Feature activation-8.15e-01

Pos logit contributions
 dives+0.008
eway+0.007
 films+0.007
 mer+0.007
 tricks+0.007
Neg logit contributions
 Em-0.004
 Gem-0.004
 expensive-0.004
ama-0.004
 Johnson-0.004
Token plane
Token ID6614
Feature activation-1.23e+00

Pos logit contributions
 Em+0.013
ama+0.013
 Gem+0.013
 checkout+0.012
 Johnson+0.012
Neg logit contributions
 dives-0.027
eway-0.024
 tricks-0.024
 films-0.023
 mer-0.023
Token,"
Token ID553
Feature activation-7.91e-01

Pos logit contributions
 Em+0.020
ama+0.020
 Gem+0.019
 checkout+0.018
 groceries+0.018
Neg logit contributions
 dives-0.040
eway-0.037
 tricks-0.036
 films-0.035
 mer-0.035
Token.
Token ID13
Feature activation+1.73e-01

Pos logit contributions
 Em+0.005
ama+0.005
 Gem+0.005
 groceries+0.005
 Johnson+0.005
Neg logit contributions
 dives-0.008
eway-0.007
 tricks-0.007
 films-0.007
 mer-0.007
Token They
Token ID1119
Feature activation-1.12e+00

Pos logit contributions
 dives+0.005
eway+0.005
 tricks+0.005
 mer+0.005
 films+0.005
Neg logit contributions
 Em-0.003
ama-0.003
 Gem-0.003
 Johnson-0.003
 groceries-0.003
Token knocked
Token ID13642
Feature activation-1.70e+00

Pos logit contributions
ama+0.035
ummy+0.033
 groceries+0.033
mm+0.033
 Johnson+0.032
Neg logit contributions
 dives-0.021
 slit-0.019
ks-0.018
 swim-0.018
RO-0.017
Token again
Token ID757
Feature activation+1.20e+00

Pos logit contributions
ama+0.048
 Em+0.048
 Gem+0.047
 checkout+0.046
 expensive+0.046
Neg logit contributions
 dives-0.034
eway-0.030
 films-0.027
igators-0.027
ull-0.026
Token,
Token ID11
Feature activation-6.44e-01

Pos logit contributions
 dives+0.028
eway+0.025
 films+0.023
 tricks+0.023
 dances+0.022
Neg logit contributions
 Em-0.030
ama-0.030
 checkout-0.030
 infected-0.030
 Gem-0.029
Token louder
Token ID27089
Feature activation+1.64e+00

Pos logit contributions
ama+0.016
 Em+0.015
 Gem+0.015
 checkout+0.014
 Johnson+0.014
Neg logit contributions
 dives-0.016
 films-0.014
 mer-0.013
eway-0.013
 dances-0.013
Token,
Token ID11
Feature activation-3.78e-01

Pos logit contributions
 dives+0.055
eway+0.052
igators+0.051
RO+0.050
 Fly+0.049
Neg logit contributions
ama-0.023
 Em-0.022
 Gem-0.022
 grandma-0.021
 Johnson-0.021
Token but
Token ID475
Feature activation-6.92e-01

Pos logit contributions
ama+0.009
 Em+0.008
 Gem+0.008
 groceries+0.008
 Johnson+0.008
Neg logit contributions
 dives-0.010
eway-0.009
 mer-0.009
 films-0.009
 tricks-0.009
Token still
Token ID991
Feature activation-7.36e-02

Pos logit contributions
 Em+0.012
ama+0.012
 Gem+0.012
 groceries+0.011
 Johnson+0.011
Neg logit contributions
 dives-0.022
eway-0.020
 tricks-0.019
 mer-0.019
 films-0.019
Token no
Token ID645
Feature activation-4.82e-02

Pos logit contributions
 Em+0.001
ama+0.001
 Gem+0.001
 Johnson+0.001
 expensive+0.001
Neg logit contributions
 dives-0.002
eway-0.002
 films-0.002
 tricks-0.002
 mer-0.002
Token one
Token ID530
Feature activation+2.02e-01

Pos logit contributions
 Em+0.001
 groceries+0.001
 expensive+0.001
 Johnson+0.001
ama+0.001
Neg logit contributions
 dives-0.002
eway-0.002
 mer-0.001
 films-0.001
RO-0.001
Token were
Token ID547
Feature activation-8.20e-01

Pos logit contributions
 Em+0.002
 Gem+0.002
ama+0.002
 expensive+0.002
 Johnson+0.002
Neg logit contributions
 dives-0.003
eway-0.003
 films-0.002
 tricks-0.002
RO-0.002
Token glad
Token ID9675
Feature activation-8.67e-01

Pos logit contributions
 Em+0.012
ama+0.012
 Gem+0.012
 Johnson+0.011
 expensive+0.011
Neg logit contributions
 dives-0.028
eway-0.026
 films-0.025
 tricks-0.025
 mer-0.024
Token that
Token ID326
Feature activation-5.32e-01

Pos logit contributions
 Em+0.015
 Gem+0.014
 grandma+0.014
 already+0.013
 Johnson+0.013
Neg logit contributions
 dives-0.028
eway-0.027
RO-0.026
igators-0.025
 films-0.025
Token the
Token ID262
Feature activation-5.27e-01

Pos logit contributions
 Em+0.011
 Gem+0.011
ama+0.010
 Johnson+0.010
 expensive+0.010
Neg logit contributions
 dives-0.015
eway-0.014
 films-0.013
 mer-0.013
 tricks-0.013
Token z
Token ID1976
Feature activation+2.11e+00

Pos logit contributions
 Em+0.012
ama+0.012
 Gem+0.012
 Johnson+0.011
 groceries+0.011
Neg logit contributions
 dives-0.014
eway-0.013
 films-0.012
 tricks-0.012
 mer-0.012
Tokenebra
Token ID37052
Feature activation+1.36e+00

Pos logit contributions
 dives+0.051
 films+0.047
eway+0.046
igators+0.044
 mer+0.043
Neg logit contributions
ama-0.055
 first-0.046
mm-0.045
bur-0.044
 already-0.044
Token had
Token ID550
Feature activation-1.68e+00

Pos logit contributions
 dives+0.043
eway+0.040
 films+0.038
 mer+0.038
 tricks+0.037
Neg logit contributions
ama-0.023
 Em-0.023
 Gem-0.021
 Johnson-0.021
 already-0.021
Token changed
Token ID3421
Feature activation-1.71e+00

Pos logit contributions
 Em+0.031
 Gem+0.030
ama+0.029
 groceries+0.028
 expensive+0.028
Neg logit contributions
 dives-0.051
eway-0.048
 films-0.045
 mer-0.044
 tricks-0.044
Token his
Token ID465
Feature activation-8.87e-01

Pos logit contributions
 Em+0.033
 Gem+0.032
ama+0.031
 expensive+0.031
 groceries+0.031
Neg logit contributions
 dives-0.050
eway-0.046
RO-0.045
 films-0.044
 Fly-0.043
Token ways
Token ID2842
Feature activation-1.26e+00

Pos logit contributions
 Em+0.016
ama+0.016
 Gem+0.016
 groceries+0.015
 Johnson+0.015
Neg logit contributions
 dives-0.027
eway-0.025
 films-0.024
 tricks-0.024
 mer-0.024
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 Em+0.025
ama+0.025
 Gem+0.024
 groceries+0.023
 Johnson+0.023
Neg logit contributions
 dives-0.036
eway-0.033
 tricks-0.032
 mer-0.031
 films-0.031
Token Max
Token ID5436
Feature activation-1.55e+00

Pos logit contributions
ama+0.030
 Em+0.029
 checkout+0.028
 groceries+0.028
 Gem+0.028
Neg logit contributions
 dives-0.042
eway-0.038
 films-0.037
 tricks-0.037
 mer-0.037
Token are
Token ID389
Feature activation-1.48e+00

Pos logit contributions
ama+0.036
 groceries+0.033
 Em+0.033
 Gem+0.033
 infected+0.032
Neg logit contributions
 dives-0.042
 mer-0.036
 dances-0.036
RO-0.035
 tricks-0.035
Token twins
Token ID20345
Feature activation-1.34e+00

Pos logit contributions
 Em+0.036
 Gem+0.034
 checkout+0.034
 Johnson+0.034
 infected+0.034
Neg logit contributions
 dives-0.037
 films-0.033
 mer-0.031
 dances-0.031
 tricks-0.030
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
ama+0.033
 groceries+0.032
 Gem+0.032
 infected+0.031
 Em+0.031
Neg logit contributions
 dives-0.031
 mer-0.028
 tricks-0.028
 films-0.028
 dances-0.027
Token They
Token ID1119
Feature activation-1.52e+00

Pos logit contributions
 Em+0.025
ama+0.025
 Gem+0.024
 Johnson+0.024
 groceries+0.023
Neg logit contributions
 dives-0.028
eway-0.025
 tricks-0.024
 mer-0.023
 films-0.023
Token like
Token ID588
Feature activation+1.41e+00

Pos logit contributions
ama+0.035
 Em+0.033
 groceries+0.033
 Johnson+0.032
 infected+0.032
Neg logit contributions
 dives-0.041
 tricks-0.036
 mer-0.036
 dances-0.035
eway-0.035
Token to
Token ID284
Feature activation+8.92e-01

Pos logit contributions
 dives+0.045
eway+0.045
ile+0.040
RO+0.040
 mer+0.040
Neg logit contributions
 groceries-0.024
 expensive-0.023
 Gem-0.023
 grandma-0.023
 Em-0.022
Token play
Token ID711
Feature activation+5.41e-01

Pos logit contributions
 dives+0.023
eway+0.021
 mer+0.020
 films+0.020
 tricks+0.020
Neg logit contributions
 Em-0.020
ama-0.020
 Gem-0.019
 groceries-0.019
 Johnson-0.019
Token together
Token ID1978
Feature activation-2.88e-01

Pos logit contributions
eway+0.018
 dives+0.017
 aids+0.016
anne+0.016
ived+0.016
Neg logit contributions
 first-0.009
 groceries-0.009
 still-0.008
 two-0.008
 top-0.008
Token,
Token ID11
Feature activation+1.57e-01

Pos logit contributions
 first+0.004
ama+0.004
 checkout+0.004
 Em+0.003
 expensive+0.003
Neg logit contributions
 dives-0.010
eway-0.010
RO-0.009
 mer-0.009
 villains-0.009
Token but
Token ID475
Feature activation-6.62e-01

Pos logit contributions
 dives+0.005
eway+0.005
RO+0.005
ull+0.005
ile+0.005
Neg logit contributions
 Johnson-0.002
 expensive-0.002
 already-0.002
 buy-0.002
 Em-0.002
Token her
Token ID607
Feature activation+9.80e-01

Pos logit contributions
 dives+0.058
eway+0.053
 films+0.051
 tricks+0.051
 mer+0.050
Neg logit contributions
 Em-0.034
ama-0.033
 Gem-0.033
 Johnson-0.032
 groceries-0.031
Token mom
Token ID1995
Feature activation+5.02e-01

Pos logit contributions
 dives+0.036
eway+0.033
 tricks+0.033
 mer+0.033
 films+0.033
Neg logit contributions
 Em-0.011
ama-0.011
 Gem-0.011
 checkout-0.010
 groceries-0.010
Tokenmy
Token ID1820
Feature activation+2.54e-01

Pos logit contributions
 dives+0.014
 tricks+0.013
 mer+0.012
 jokes+0.012
 dances+0.012
Neg logit contributions
 groceries-0.009
ama-0.008
 Em-0.008
 Gem-0.008
 expensive-0.008
Token told
Token ID1297
Feature activation-2.71e-01

Pos logit contributions
 dives+0.007
 tricks+0.006
 mer+0.006
 dances+0.006
 jokes+0.006
Neg logit contributions
 groceries-0.006
 Em-0.005
ama-0.005
 Gem-0.005
 Johnson-0.005
Token her
Token ID607
Feature activation+1.97e+00

Pos logit contributions
 Em+0.004
 Gem+0.004
ama+0.004
 groceries+0.004
 Johnson+0.004
Neg logit contributions
 dives-0.009
eway-0.008
 mer-0.008
 tricks-0.008
RO-0.008
Token it
Token ID340
Feature activation+1.72e+00

Pos logit contributions
 dives+0.056
eway+0.051
 tricks+0.049
 films+0.048
 mer+0.048
Neg logit contributions
 Em-0.040
ama-0.040
 Gem-0.039
 checkout-0.038
 Johnson-0.038
Token was
Token ID373
Feature activation+7.33e-01

Pos logit contributions
 dives+0.042
 tricks+0.037
eway+0.037
 dances+0.035
 jokes+0.034
Neg logit contributions
ama-0.041
 Gem-0.041
 Em-0.041
 checkout-0.040
 groceries-0.040
Token fake
Token ID8390
Feature activation+8.54e-01

Pos logit contributions
 dives+0.018
 tricks+0.016
 films+0.016
eway+0.016
 mer+0.015
Neg logit contributions
ama-0.017
 Em-0.017
 Gem-0.017
 checkout-0.017
mm-0.016
Token.
Token ID13
Feature activation+1.25e+00

Pos logit contributions
 dives+0.027
eway+0.025
RO+0.024
 mer+0.024
 films+0.024
Neg logit contributions
 Em-0.014
ama-0.014
 groceries-0.014
 Gem-0.014
 Johnson-0.014
Token Lily
Token ID20037
Feature activation+2.06e-01

Pos logit contributions
 dives+0.037
eway+0.034
 films+0.033
 tricks+0.032
 mer+0.032
Neg logit contributions
ama-0.023
 Em-0.023
 Gem-0.023
 groceries-0.022
 Johnson-0.022
Token was
Token ID373
Feature activation+8.75e-01

Pos logit contributions
 dives+0.006
eway+0.005
 tricks+0.005
 mer+0.005
 dances+0.005
Neg logit contributions
ama-0.004
 Em-0.004
 Gem-0.004
 groceries-0.004
 Johnson-0.004
Token was
Token ID373
Feature activation-4.95e-01

Pos logit contributions
 films+0.023
 dives+0.023
eway+0.023
 villains+0.022
 aids+0.021
Neg logit contributions
 already-0.009
 Em-0.009
 still-0.009
 first-0.009
 expensive-0.008
Token the
Token ID262
Feature activation-1.39e+00

Pos logit contributions
 Em+0.008
ama+0.008
 Gem+0.008
 groceries+0.007
 Johnson+0.007
Neg logit contributions
 dives-0.016
eway-0.015
 tricks-0.014
 films-0.014
 mer-0.014
Token best
Token ID1266
Feature activation-1.60e-01

Pos logit contributions
 Em+0.014
ama+0.013
 Gem+0.013
 Johnson+0.012
 groceries+0.012
Neg logit contributions
 dives-0.054
eway-0.050
 tricks-0.049
 mer-0.049
 films-0.049
Token day
Token ID1110
Feature activation+5.86e-01

Pos logit contributions
 expensive+0.002
ama+0.002
 grandma+0.002
 Gem+0.002
 groceries+0.002
Neg logit contributions
RO-0.005
igators-0.005
 dives-0.005
 films-0.005
 aids-0.005
Token ever
Token ID1683
Feature activation+1.14e+00

Pos logit contributions
 dives+0.019
eway+0.018
 films+0.018
 tricks+0.018
 poses+0.017
Neg logit contributions
 Gem-0.009
ama-0.009
 Em-0.009
 already-0.008
 Johnson-0.008
Token!
Token ID0
Feature activation+1.22e+00

Pos logit contributions
 dives+0.040
eway+0.038
 films+0.037
 tricks+0.037
 villains+0.036
Neg logit contributions
 Em-0.015
ama-0.015
 Gem-0.014
 Johnson-0.014
 expensive-0.013
Token
Token ID220
Feature activation-2.20e+00

Pos logit contributions
 dives+0.039
eway+0.036
 tricks+0.035
 films+0.035
 mer+0.035
Neg logit contributions
 Em-0.020
ama-0.020
 Gem-0.019
 groceries-0.018
 Johnson-0.018
Token
Token ID198
Feature activation+5.12e-01

Pos logit contributions
 Em+0.036
ama+0.036
 Gem+0.035
 Johnson+0.034
 groceries+0.033
Neg logit contributions
 dives-0.071
eway-0.065
 tricks-0.063
 films-0.063
 mer-0.063
Token
Token ID198
Feature activation+4.84e-02

Pos logit contributions
 dives+0.016
eway+0.014
 films+0.014
 mer+0.014
 tricks+0.014
Neg logit contributions
ama-0.009
 Em-0.009
 Gem-0.009
 Johnson-0.009
 groceries-0.008
TokenWhen
Token ID2215
Feature activation+6.48e-01

Pos logit contributions
 dives+0.001
 films+0.001
 dances+0.001
 mer+0.001
 tricks+0.001
Neg logit contributions
ama-0.001
 Em-0.001
 Gem-0.001
 Johnson-0.001
 checkout-0.001
Token it
Token ID340
Feature activation+2.03e-01

Pos logit contributions
 dives+0.018
eway+0.017
 tricks+0.016
 films+0.016
 mer+0.016
Neg logit contributions
 Em-0.014
ama-0.014
 Gem-0.013
 Johnson-0.013
 groceries-0.013
Token mom
Token ID1995
Feature activation-1.43e+00

Pos logit contributions
 Em+0.017
ama+0.016
 Gem+0.016
 checkout+0.016
 groceries+0.016
Neg logit contributions
 dives-0.033
eway-0.030
 tricks-0.029
 films-0.029
 mer-0.029
Token.
Token ID13
Feature activation-1.21e+00

Pos logit contributions
ama+0.028
 Em+0.027
 infected+0.026
 checkout+0.026
 groceries+0.026
Neg logit contributions
 dives-0.039
 films-0.037
 mer-0.036
eway-0.036
 tricks-0.036
Token But
Token ID887
Feature activation-6.45e-01

Pos logit contributions
ama+0.019
 Em+0.018
 infected+0.018
 groceries+0.018
 Gem+0.017
Neg logit contributions
 dives-0.040
eway-0.036
 films-0.035
 dances-0.035
 mer-0.035
Token when
Token ID618
Feature activation-2.47e-01

Pos logit contributions
ama+0.013
 Em+0.013
 infected+0.013
 groceries+0.013
ongo+0.013
Neg logit contributions
 dives-0.016
 mer-0.015
eway-0.015
 Fly-0.015
 films-0.014
Token she
Token ID673
Feature activation-1.03e+00

Pos logit contributions
ama+0.004
 Em+0.004
 Gem+0.004
 groceries+0.004
 infected+0.004
Neg logit contributions
 dives-0.007
 mer-0.007
eway-0.007
 Fly-0.007
 dances-0.006
Token went
Token ID1816
Feature activation-1.06e+00

Pos logit contributions
 Em+0.021
ama+0.021
 Gem+0.020
 checkout+0.020
 Johnson+0.019
Neg logit contributions
 dives-0.029
eway-0.027
 films-0.026
 tricks-0.026
 villains-0.025
Token back
Token ID736
Feature activation+6.25e-01

Pos logit contributions
ama+0.019
 groceries+0.019
 Em+0.019
 Johnson+0.019
 Gem+0.018
Neg logit contributions
 dives-0.032
eway-0.030
RO-0.029
 films-0.029
 villains-0.029
Token inside
Token ID2641
Feature activation-1.38e+00

Pos logit contributions
 dives+0.017
eway+0.015
 mer+0.014
 tricks+0.014
 films+0.014
Neg logit contributions
 Em-0.014
ama-0.013
 Gem-0.013
 checkout-0.013
 infected-0.013
Token to
Token ID284
Feature activation-1.73e+00

Pos logit contributions
 infected+0.027
 Em+0.027
ama+0.027
 checkout+0.027
 groceries+0.026
Neg logit contributions
 dives-0.039
eway-0.034
 mer-0.034
 dances-0.033
 Fly-0.033
Token get
Token ID651
Feature activation-1.20e+00

Pos logit contributions
ama+0.035
 Em+0.034
 Johnson+0.033
 Gem+0.033
 groceries+0.033
Neg logit contributions
 dives-0.050
eway-0.044
 mer-0.044
 dances-0.043
 tricks-0.043
Token her
Token ID607
Feature activation-9.14e-01

Pos logit contributions
ama+0.028
 Johnson+0.028
ongo+0.027
mm+0.027
 checkout+0.027
Neg logit contributions
 dives-0.030
 mer-0.027
 dances-0.025
 Fly-0.024
ull-0.024
Token put
Token ID1234
Feature activation+1.68e-01

Pos logit contributions
 dives+0.009
eway+0.008
 films+0.008
 tricks+0.008
 mer+0.007
Neg logit contributions
 Em-0.006
ama-0.006
 Gem-0.006
 groceries-0.006
 checkout-0.006
Token them
Token ID606
Feature activation+6.03e-03

Pos logit contributions
 dives+0.004
eway+0.003
 tricks+0.003
 films+0.003
 mer+0.003
Neg logit contributions
 Em-0.005
ama-0.005
 Gem-0.004
 groceries-0.004
 Johnson-0.004
Token on
Token ID319
Feature activation+6.89e-02

Pos logit contributions
 dives+0.000
eway+0.000
 films+0.000
RO+0.000
 tricks+0.000
Neg logit contributions
 Em-0.000
 Gem-0.000
 groceries-0.000
ama-0.000
 expensive-0.000
Token her
Token ID607
Feature activation+3.76e-02

Pos logit contributions
 dives+0.002
eway+0.002
 tricks+0.002
 films+0.002
 mer+0.002
Neg logit contributions
ama-0.002
 infected-0.002
mm-0.001
ongo-0.001
 Johnson-0.001
Token desk
Token ID6915
Feature activation-1.54e+00

Pos logit contributions
 dives+0.001
 tricks+0.001
eway+0.001
 films+0.001
 mer+0.001
Neg logit contributions
 Em-0.001
ama-0.001
 Gem-0.001
 Johnson-0.001
 infected-0.001
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
ama+0.030
 Em+0.030
 Gem+0.029
 Johnson+0.029
 groceries+0.028
Neg logit contributions
 dives-0.044
eway-0.040
 tricks-0.039
 films-0.038
 mer-0.038
Token She
Token ID1375
Feature activation+3.12e-01

Pos logit contributions
 dives+0.011
eway+0.010
 Fly+0.010
 dances+0.010
 films+0.010
Neg logit contributions
 expensive-0.008
 groceries-0.007
 infected-0.007
 checkout-0.007
 severe-0.007
Token named
Token ID3706
Feature activation-2.15e+00

Pos logit contributions
 dives+0.009
eway+0.008
 tricks+0.008
 films+0.008
 mer+0.007
Neg logit contributions
 Em-0.007
ama-0.006
 Gem-0.006
 Johnson-0.006
 groceries-0.006
Token each
Token ID1123
Feature activation+3.63e-01

Pos logit contributions
 Em+0.038
 Gem+0.035
 groceries+0.034
ama+0.033
 Johnson+0.033
Neg logit contributions
 dives-0.069
eway-0.063
 mer-0.060
RO-0.060
 tricks-0.059
Token color
Token ID3124
Feature activation-1.27e-01

Pos logit contributions
 dives+0.010
eway+0.009
 tricks+0.009
 films+0.009
 mer+0.009
Neg logit contributions
 Em-0.008
ama-0.008
 Gem-0.007
 Johnson-0.007
 groceries-0.007
Token out
Token ID503
Feature activation+1.99e+00

Pos logit contributions
 Em+0.002
ama+0.002
 Gem+0.002
 groceries+0.002
 Johnson+0.002
Neg logit contributions
 dives-0.004
eway-0.004
 films-0.003
RO-0.003
 mer-0.003
Token said
Token ID531
Feature activation-1.34e-01

Pos logit contributions
 Em+0.001
 Gem+0.001
ama+0.001
 checkout+0.000
 Johnson+0.000
Neg logit contributions
 dives-0.001
eway-0.001
 films-0.001
 tricks-0.001
 mer-0.001
Token,
Token ID11
Feature activation+8.17e-01

Pos logit contributions
 Em+0.002
ama+0.002
 Gem+0.002
 Johnson+0.002
 groceries+0.002
Neg logit contributions
 dives-0.005
eway-0.004
 films-0.004
 tricks-0.004
RO-0.004
Token "
Token ID366
Feature activation-1.15e+00

Pos logit contributions
 dives+0.018
eway+0.016
 mer+0.016
 tricks+0.016
 films+0.015
Neg logit contributions
ama-0.021
 Em-0.021
 groceries-0.020
 Gem-0.020
 checkout-0.020
TokenI
Token ID40
Feature activation+8.00e-01

Pos logit contributions
ama+0.021
 groceries+0.020
 Em+0.020
 Gem+0.020
 expensive+0.019
Neg logit contributions
 dives-0.035
eway-0.032
RO-0.031
 mer-0.031
 Fly-0.031
Token want
Token ID765
Feature activation+1.12e+00

Pos logit contributions
 dives+0.025
 mer+0.022
eway+0.022
 hops+0.022
 tricks+0.021
Neg logit contributions
 Em-0.014
 Gem-0.014
ama-0.014
 groceries-0.014
 checkout-0.014
Token something
Token ID1223
Feature activation+6.33e-01

Pos logit contributions
 dives+0.029
 tricks+0.025
eway+0.025
 mer+0.024
 films+0.024
Neg logit contributions
 Em-0.026
ama-0.026
 Gem-0.025
 checkout-0.024
 Johnson-0.024
Token else
Token ID2073
Feature activation+8.10e-01

Pos logit contributions
 dives+0.018
eway+0.017
 films+0.016
 tricks+0.016
 mer+0.016
Neg logit contributions
 Em-0.013
ama-0.013
 Gem-0.012
 groceries-0.012
 Johnson-0.012
Token that
Token ID326
Feature activation-9.27e-01

Pos logit contributions
 dives+0.023
eway+0.021
 tricks+0.020
 films+0.020
 mer+0.020
Neg logit contributions
 Em-0.016
ama-0.016
 Gem-0.016
 Johnson-0.015
 groceries-0.015
Token's
Token ID338
Feature activation-9.30e-01

Pos logit contributions
 expensive+0.015
 Em+0.014
 first+0.014
ama+0.014
 groceries+0.014
Neg logit contributions
eway-0.028
 dives-0.027
 films-0.027
 villains-0.026
 mer-0.026
Token delicious
Token ID12625
Feature activation+7.01e-01

Pos logit contributions
 Em+0.015
ama+0.014
 Gem+0.014
 Johnson+0.014
 groceries+0.014
Neg logit contributions
 dives-0.031
eway-0.028
 tricks-0.027
 films-0.027
 mer-0.027
Token!"
Token ID2474
Feature activation-1.10e+00

Pos logit contributions
 dives+0.025
eway+0.024
RO+0.024
 films+0.024
 villains+0.024
Neg logit contributions
 Johnson-0.008
 groceries-0.008
ama-0.008
 Em-0.007
 Gem-0.007
Token Pam
Token ID24497
Feature activation+1.10e+00

Pos logit contributions
ama+0.025
 Em+0.025
 Gem+0.024
 groceries+0.023
 checkout+0.023
Neg logit contributions
 dives-0.041
eway-0.037
 tricks-0.036
 films-0.036
 mer-0.036
Token says
Token ID1139
Feature activation+8.85e-01

Pos logit contributions
 dives+0.026
eway+0.024
 films+0.022
 mer+0.022
 tricks+0.022
Neg logit contributions
 Em-0.028
ama-0.027
 Gem-0.027
 Johnson-0.026
 groceries-0.026
Token.
Token ID13
Feature activation+1.32e+00

Pos logit contributions
 dives+0.032
eway+0.030
RO+0.029
 films+0.029
igators+0.029
Neg logit contributions
ama-0.012
 Em-0.012
 Gem-0.010
 Johnson-0.010
 infected-0.010
Token
Token ID198
Feature activation-8.55e-02

Pos logit contributions
 dives+0.048
eway+0.044
 tricks+0.044
 films+0.043
igators+0.042
Neg logit contributions
 Em-0.018
ama-0.017
 Gem-0.017
 Johnson-0.017
 groceries-0.014
Token
Token ID198
Feature activation-4.50e-01

Pos logit contributions
 Em+0.002
 checkout+0.002
 groceries+0.002
 Gem+0.002
ama+0.002
Neg logit contributions
 dives-0.002
eway-0.002
 Fly-0.002
 tricks-0.002
 films-0.002
Token"
Token ID1
Feature activation-1.03e+00

Pos logit contributions
 Em+0.008
ama+0.008
 Gem+0.008
 Johnson+0.008
 groceries+0.008
Neg logit contributions
 dives-0.014
eway-0.012
 tricks-0.012
 films-0.012
 mer-0.012
TokenRot
Token ID24864
Feature activation-7.19e-01

Pos logit contributions
ama+0.020
 Em+0.020
 Gem+0.019
 groceries+0.019
 Johnson+0.018
Neg logit contributions
 dives-0.030
eway-0.027
 tricks-0.027
 mer-0.027
 films-0.026
Token?
Token ID30
Feature activation+1.41e-01

Pos logit contributions
 Em+0.018
ama+0.018
 checkout+0.018
 Gem+0.018
 Johnson+0.017
Neg logit contributions
 dives-0.015
 tricks-0.014
eway-0.014
ile-0.013
 films-0.013
Token What
Token ID1867
Feature activation+2.52e+00

Pos logit contributions
 dives+0.003
 Fly+0.003
 films+0.003
RO+0.003
eway+0.003
Neg logit contributions
 groceries-0.004
 checkout-0.004
bur-0.003
 severe-0.003
ama-0.003
Token is
Token ID318
Feature activation-1.99e+00

Pos logit contributions
 dives+0.069
eway+0.061
 tricks+0.060
 films+0.059
 mer+0.058
Neg logit contributions
 Em-0.054
ama-0.054
 Gem-0.053
 checkout-0.052
 Johnson-0.051
Token rot
Token ID5724
Feature activation-1.42e+00

Pos logit contributions
ama+0.039
 Em+0.039
 Gem+0.038
 Johnson+0.037
 checkout+0.037
Neg logit contributions
 dives-0.058
eway-0.052
 tricks-0.051
 films-0.050
 mer-0.050
Token and
Token ID290
Feature activation+3.61e-01

Pos logit contributions
 Em+0.012
ama+0.012
 Gem+0.012
 Johnson+0.011
 groceries+0.011
Neg logit contributions
 dives-0.018
eway-0.017
 films-0.016
 mer-0.016
 tricks-0.016
Token slides
Token ID19392
Feature activation+5.50e-01

Pos logit contributions
eway+0.011
ull+0.011
ile+0.011
 villains+0.010
ag+0.010
Neg logit contributions
 first-0.007
 Em-0.007
 Grand-0.007
 grandma-0.007
 tired-0.007
Token down
Token ID866
Feature activation+3.43e-01

Pos logit contributions
 dives+0.016
eway+0.015
 films+0.015
 villains+0.015
 mer+0.014
Neg logit contributions
 Em-0.010
 Gem-0.010
 Johnson-0.010
 groceries-0.010
ama-0.010
Token.
Token ID13
Feature activation+6.13e-02

Pos logit contributions
 dives+0.010
eway+0.010
 films+0.009
 tricks+0.009
 dances+0.009
Neg logit contributions
 Em-0.006
 Johnson-0.006
 Gem-0.006
ama-0.006
 checkout-0.006
Token "
Token ID366
Feature activation-3.71e-01

Pos logit contributions
 dives+0.002
eway+0.002
 mer+0.002
 films+0.002
 tricks+0.002
Neg logit contributions
 Em-0.001
ama-0.001
 Gem-0.001
 Johnson-0.001
 checkout-0.001
TokenY
Token ID56
Feature activation-2.82e+00

Pos logit contributions
 Em+0.007
 Gem+0.006
 checkout+0.006
 Johnson+0.006
ama+0.006
Neg logit contributions
 dives-0.011
eway-0.010
 films-0.010
 tricks-0.010
 mer-0.010
Tokenay
Token ID323
Feature activation+2.23e+00

Pos logit contributions
 Em+0.059
 Gem+0.059
 severe+0.058
 groceries+0.058
 infected+0.058
Neg logit contributions
 dives-0.076
eway-0.066
ived-0.064
 tricks-0.064
RO-0.063
Token!"
Token ID2474
Feature activation-7.60e-01

Pos logit contributions
 dives+0.077
eway+0.072
 films+0.069
 mer+0.069
 tricks+0.069
Neg logit contributions
ama-0.032
 Em-0.032
 Gem-0.030
 Johnson-0.029
 groceries-0.028
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
 Em+0.012
ama+0.012
 Gem+0.012
 groceries+0.012
 Johnson+0.012
Neg logit contributions
 dives-0.024
eway-0.023
 mer-0.022
 films-0.022
igators-0.022
Token
Token ID198
Feature activation-4.92e-01

Pos logit contributions
 dives+0.005
eway+0.005
 tricks+0.004
 films+0.004
 mer+0.004
Neg logit contributions
 Em-0.003
ama-0.003
 Gem-0.003
 groceries-0.003
 checkout-0.003
TokenThey
Token ID2990
Feature activation-5.57e-01

Pos logit contributions
ama+0.010
 Em+0.010
 Gem+0.009
 checkout+0.009
 Johnson+0.009
Neg logit contributions
 dives-0.014
eway-0.013
 films-0.013
 tricks-0.012
 mer-0.012
Tokenmy
Token ID1820
Feature activation-1.43e+00

Pos logit contributions
 Em+0.028
ama+0.028
mm+0.027
 groceries+0.027
 Gem+0.027
Neg logit contributions
 dives-0.072
 mer-0.069
ull-0.067
 films-0.066
 swim-0.065
Token decided
Token ID3066
Feature activation-2.33e+00

Pos logit contributions
ama+0.037
 Em+0.037
 groceries+0.036
 Gem+0.035
 expensive+0.035
Neg logit contributions
 dives-0.032
 mer-0.029
 films-0.027
 swim-0.026
eway-0.026
Token to
Token ID284
Feature activation+8.92e-01

Pos logit contributions
ama+0.055
 Em+0.054
 Gem+0.053
 Johnson+0.052
 checkout+0.051
Neg logit contributions
 dives-0.059
eway-0.053
 tricks-0.051
 mer-0.050
 films-0.050
Token cook
Token ID4255
Feature activation-7.22e-01

Pos logit contributions
 dives+0.024
eway+0.022
 tricks+0.021
 mer+0.021
 films+0.021
Neg logit contributions
 Em-0.019
ama-0.019
 Gem-0.018
 Johnson-0.018
 groceries-0.018
Token something
Token ID1223
Feature activation+2.44e-01

Pos logit contributions
 groceries+0.012
ama+0.011
 Em+0.011
 Gem+0.011
 checkout+0.011
Neg logit contributions
 dives-0.023
eway-0.022
 villains-0.021
RO-0.021
 mer-0.021
Token y
Token ID331
Feature activation-2.79e+00

Pos logit contributions
 dives+0.008
eway+0.007
 villains+0.007
RO+0.007
 Fly+0.007
Neg logit contributions
 expensive-0.004
 Em-0.004
 groceries-0.004
ama-0.004
 Gem-0.004
Tokenummy
Token ID13513
Feature activation+7.25e-01

Pos logit contributions
 Em+0.029
 Gem+0.025
 infected+0.024
 Johnson+0.024
 checkout+0.023
Neg logit contributions
 dives-0.108
eway-0.099
 films-0.097
 tricks-0.097
 mer-0.096
Token to
Token ID284
Feature activation-1.04e+00

Pos logit contributions
 dives+0.023
eway+0.022
RO+0.022
 villains+0.021
 Fly+0.021
Neg logit contributions
 groceries-0.012
 Gem-0.011
 expensive-0.011
 Em-0.011
ama-0.010
Token eat
Token ID4483
Feature activation-1.31e+00

Pos logit contributions
ama+0.025
 Em+0.024
 Gem+0.023
 Johnson+0.023
 infected+0.022
Neg logit contributions
 dives-0.027
 tricks-0.024
 films-0.023
eway-0.023
 mer-0.023
Token.
Token ID13
Feature activation-9.01e-02

Pos logit contributions
 Em+0.025
ama+0.025
 Gem+0.024
 Johnson+0.023
 checkout+0.023
Neg logit contributions
 dives-0.039
eway-0.035
 tricks-0.034
 films-0.034
 mer-0.034
Token They
Token ID1119
Feature activation-8.58e-01

Pos logit contributions
ama+0.002
 Em+0.002
 Gem+0.002
 groceries+0.002
 infected+0.002
Neg logit contributions
 dives-0.003
eway-0.002
 films-0.002
 tricks-0.002
 dances-0.002
Token He
Token ID679
Feature activation+5.00e-01

Pos logit contributions
 dives+0.007
eway+0.006
 tricks+0.006
 films+0.006
 mer+0.006
Neg logit contributions
 Em-0.005
ama-0.005
 Gem-0.005
 Johnson-0.005
 groceries-0.005
Token blew
Token ID17948
Feature activation-5.94e-02

Pos logit contributions
 dives+0.014
eway+0.014
 films+0.014
 tricks+0.013
 villains+0.013
Neg logit contributions
 Em-0.009
ama-0.009
 Gem-0.009
 checkout-0.009
 expensive-0.009
Token on
Token ID319
Feature activation+1.07e+00

Pos logit contributions
 Em+0.001
 Gem+0.001
 groceries+0.001
 expensive+0.001
 infected+0.001
Neg logit contributions
 dives-0.002
eway-0.002
 villains-0.002
 films-0.002
RO-0.002
Token the
Token ID262
Feature activation+6.74e-01

Pos logit contributions
 dives+0.033
eway+0.031
 films+0.029
 mer+0.029
RO+0.029
Neg logit contributions
 Em-0.019
 Gem-0.018
 groceries-0.018
ama-0.018
 checkout-0.018
Token sticks
Token ID16461
Feature activation-2.02e-02

Pos logit contributions
 dives+0.017
 tricks+0.015
eway+0.014
 mer+0.014
 films+0.014
Neg logit contributions
ama-0.017
 Em-0.016
 Gem-0.016
 Johnson-0.016
 checkout-0.015
Token until
Token ID1566
Feature activation-2.27e+00

Pos logit contributions
 Em+0.000
ama+0.000
 Gem+0.000
 Johnson+0.000
 groceries+0.000
Neg logit contributions
 dives-0.001
eway-0.001
 films-0.001
RO-0.001
 villains-0.001
Token the
Token ID262
Feature activation-2.96e-01

Pos logit contributions
 Em+0.043
 Gem+0.042
ama+0.041
 groceries+0.041
 checkout+0.040
Neg logit contributions
 dives-0.067
eway-0.064
 films-0.061
 tricks-0.061
 dances-0.059
Token sun
Token ID4252
Feature activation+8.53e-02

Pos logit contributions
 Em+0.006
ama+0.006
 Gem+0.006
 groceries+0.006
 Johnson+0.006
Neg logit contributions
 dives-0.008
eway-0.007
 films-0.007
 tricks-0.007
 mer-0.007
Token got
Token ID1392
Feature activation-3.77e+00

Pos logit contributions
 dives+0.003
eway+0.002
 films+0.002
 villains+0.002
 tricks+0.002
Neg logit contributions
 Em-0.002
ama-0.002
 Gem-0.002
 Johnson-0.001
 checkout-0.001
Token hot
Token ID3024
Feature activation-6.15e-01

Pos logit contributions
ama+0.090
mm+0.082
 Em+0.082
 Gem+0.080
 checkout+0.078
Neg logit contributions
 dives-0.095
 mer-0.087
ull-0.082
eway-0.081
RO-0.080
Token and
Token ID290
Feature activation-9.53e-01

Pos logit contributions
 Em+0.012
ama+0.011
 Gem+0.011
 groceries+0.011
 Johnson+0.011
Neg logit contributions
 dives-0.018
eway-0.017
 tricks-0.016
 films-0.016
 mer-0.016
Token might
Token ID1244
Feature activation-1.16e+00

Pos logit contributions
 Em+0.000
ama+0.000
 Gem+0.000
 Johnson+0.000
 groceries+0.000
Neg logit contributions
 dives-0.001
eway-0.001
 tricks-0.000
 mer-0.000
 dances-0.000
Token find
Token ID1064
Feature activation-1.32e+00

Pos logit contributions
 Em+0.019
 Gem+0.019
ama+0.019
 expensive+0.018
 Johnson+0.018
Neg logit contributions
 dives-0.036
eway-0.033
 films-0.033
 mer-0.032
 tricks-0.032
Token next
Token ID1306
Feature activation-3.32e-01

Pos logit contributions
ama+0.026
 Em+0.026
 Gem+0.025
 checkout+0.025
 Johnson+0.024
Neg logit contributions
 dives-0.038
eway-0.035
 tricks-0.034
 mer-0.033
 films-0.033
Token?
Token ID30
Feature activation+2.87e-01

Pos logit contributions
 Em+0.007
ama+0.007
 Gem+0.006
 checkout+0.006
 groceries+0.006
Neg logit contributions
 dives-0.010
eway-0.009
 tricks-0.008
 mer-0.008
 films-0.008
Token<|endoftext|>
Token ID50256
Feature activation+2.46e-01

Pos logit contributions
 dives+0.008
eway+0.008
 Fly+0.007
RO+0.007
 mer+0.007
Neg logit contributions
 groceries-0.006
 expensive-0.005
 checkout-0.005
ama-0.005
 infected-0.005
TokenOnce
Token ID7454
Feature activation-2.52e+00

Pos logit contributions
 dives+0.007
eway+0.007
 tricks+0.007
 films+0.007
 mer+0.007
Neg logit contributions
 Em-0.004
ama-0.004
 Gem-0.004
 Johnson-0.004
 groceries-0.004
Token upon
Token ID2402
Feature activation+1.11e+00

Pos logit contributions
 checkout+0.054
 groceries+0.051
 Em+0.050
 infected+0.049
 Gem+0.049
Neg logit contributions
 dives-0.069
eway-0.064
 dances-0.058
ull-0.058
 Fly-0.058
Token a
Token ID257
Feature activation+5.97e-01

Pos logit contributions
 dives+0.037
eway+0.034
 films+0.033
 tricks+0.033
 mer+0.033
Neg logit contributions
 Em-0.017
ama-0.016
 Gem-0.016
 groceries-0.015
 Johnson-0.015
Token time
Token ID640
Feature activation-5.86e-01

Pos logit contributions
 dives+0.016
eway+0.015
 mer+0.014
 tricks+0.014
 films+0.014
Neg logit contributions
ama-0.013
 Em-0.012
 expensive-0.012
 Johnson-0.012
 Gem-0.012
Token,
Token ID11
Feature activation-1.77e+00

Pos logit contributions
 Em+0.008
ama+0.008
 Gem+0.008
 Johnson+0.008
 groceries+0.007
Neg logit contributions
 dives-0.020
eway-0.019
 films-0.018
 tricks-0.018
 mer-0.018
Token there
Token ID612
Feature activation-1.02e+00

Pos logit contributions
 Em+0.031
ama+0.030
 Gem+0.029
 Johnson+0.029
 expensive+0.027
Neg logit contributions
 dives-0.056
eway-0.051
 tricks-0.050
 films-0.050
 mer-0.049
Token Ben
Token ID3932
Feature activation-1.25e+00

Pos logit contributions
ama+0.026
 Em+0.026
 Gem+0.025
 checkout+0.025
 groceries+0.025
Neg logit contributions
 dives-0.042
eway-0.038
 tricks-0.036
 films-0.036
 mer-0.036
Token were
Token ID547
Feature activation-1.45e+00

Pos logit contributions
ama+0.029
 Em+0.027
 groceries+0.027
 Gem+0.027
 Johnson+0.026
Neg logit contributions
 dives-0.034
 mer-0.029
 dances-0.029
RO-0.028
eway-0.028
Token playing
Token ID2712
Feature activation+7.74e-01

Pos logit contributions
 Em+0.021
ama+0.020
 Gem+0.020
 Johnson+0.019
 groceries+0.019
Neg logit contributions
 dives-0.050
eway-0.046
 films-0.045
 tricks-0.044
 mer-0.044
Token with
Token ID351
Feature activation-1.40e+00

Pos logit contributions
anne+0.030
 aids+0.029
eway+0.028
igators+0.028
 dives+0.028
Neg logit contributions
 first-0.011
 top-0.010
 two-0.010
 still-0.009
 all-0.009
Token their
Token ID511
Feature activation-1.39e+00

Pos logit contributions
 Em+0.033
 groceries+0.032
 Gem+0.032
 expensive+0.031
 Johnson+0.031
Neg logit contributions
 dives-0.037
eway-0.034
RO-0.031
 tricks-0.030
 villains-0.030
Token toys
Token ID14958
Feature activation-2.61e+00

Pos logit contributions
 groceries+0.023
ama+0.022
 expensive+0.022
 Em+0.022
 Johnson+0.021
Neg logit contributions
 dives-0.045
eway-0.043
RO-0.040
 mer-0.040
 Fly-0.039
Token in
Token ID287
Feature activation-1.27e+00

Pos logit contributions
 Em+0.052
ama+0.051
 Gem+0.050
 groceries+0.049
 Johnson+0.049
Neg logit contributions
 dives-0.076
eway-0.069
 tricks-0.065
 films-0.065
 mer-0.065
Token the
Token ID262
Feature activation-1.18e+00

Pos logit contributions
 Em+0.025
ama+0.024
 Gem+0.024
 Johnson+0.023
 groceries+0.023
Neg logit contributions
 dives-0.038
eway-0.034
 tricks-0.033
 mer-0.033
 films-0.033
Token garden
Token ID11376
Feature activation-2.56e+00

Pos logit contributions
 groceries+0.019
 checkout+0.019
 Gem+0.019
 Em+0.019
 expensive+0.019
Neg logit contributions
 dives-0.038
eway-0.037
RO-0.034
 tricks-0.034
 villains-0.034
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
 Em+0.046
ama+0.046
 Gem+0.045
 Johnson+0.043
 groceries+0.043
Neg logit contributions
 dives-0.079
eway-0.072
 tricks-0.069
 films-0.069
 mer-0.068
Token Lily
Token ID20037
Feature activation-7.97e-01

Pos logit contributions
 Em+0.003
 Gem+0.003
 checkout+0.003
 Johnson+0.003
ama+0.003
Neg logit contributions
 dives-0.005
eway-0.004
 tricks-0.004
 mer-0.004
 villains-0.004