TOP ACTIVATIONS
MAX = 0.499

the clown s , the jug glers , the crazy ac
ía que mi hij a jug ara con e lla .
Wh ist ling Woods to vac ate 14 . 5 acre
," Ger ads tells Heat Vision via phone . " My
the first family soon to vac ate the White House for
has always been non - existent , but the allegations ,
haunt Sullivan and Ma ia va . They have been diagnosed
- harm ." Ma ia va , a former policeman from
, K atic a Jane va in front ot the Secret
arrest , Jane va said , adding that the
Prosecutor K atic a Jane va personally intervened at the B
. Washington , DC : Hemisphere Publishing . Google
Knowledge Sri Hay ag ri va have se perate shr ines
to eight , Ma ia va withdrew from family and friends
(@ ren lav o iet va ) June 12 , 2017
(@ ren lav o iet va ) June 12 , 2017
like to resolve non - existent domains to search . d
of democracy in the Western Hemisphere s only one
The fourth big Project DI va X update is in .
ing and obstruct ing Jane va s special prosecution

MIN ACTIVATIONS
MIN = -0.535

author of a study of Brah ms , dismiss es the
as true the allegation that Brah ms slaughtered fel ines ,
explains that Wagner never visited Brah ms 's flat , so
<|endoftext|> J oh ann es Brah ms , be wh is
presumably have to have given Brah ms the bow in person
a very limited time for Brah ms to become an expert
. Psycho was a cert ifiable smash , and he ended
to Wagner , who disliked Brah ms , he worked these
. D vor ak and Brah ms met in 1880 ,
submit the required and ver ifiable registration information prior to the
ins , editor of Johannes Brah ms : Life and Letters
that in 1893 - when Brah ms was still alive -
1996 , which claims that Brah ms began cat bag ging
marijuana . H emp Supporters State Senators Russell Rud
he notes that stories of Brah ms killing cats surface mainly
groundwork to make them just ifiable . Thanks for your time
, Brian Todd , Jason Carroll , Pete Ham by ,
produced by Cub by Bro ccoli or the Bro ccoli family
Bro ccoli or the Bro ccoli family ( E on Productions
he met Cub by Bro ccoli : ----- 1954 : "

INTERVAL 0.241 - 0.499
CONTAINS 0.929%

sometimes Archie would take the session . You wouldn 't ever
. R ough ly 18 million people eligible for
images directory ") args = v ars ( ap . parse
in and out of Lib o last year .
one of the most skill fully - l iked media centers

INTERVAL -0.018 - 0.241
CONTAINS 69.248%

Policy Center based in Washington . <|endoftext|> As a pub storm
paths . list _ images ( args [" images "] ):
] What kind of projects are done with Te ens y
more observers , however , believe that excessive speculation in the
the children .' T ori posted this cryptic message

INTERVAL -0.276 - -0.018
CONTAINS 29.404%

s a simple case of economic logic . In order to
ly or un gener ous criticism , ridicule , or satire
Presidential spokesman Ye H t ut told me their actions had
you held . En light enment is like that
an interview with legendary Michigan State basketball coach Tom I zzo

INTERVAL -0.535 - -0.276
CONTAINS 0.420%

trend for teen girls : dressing up like dolls . Why
68 46 . <|endoftext|> ( FIL ES ) US Treasury Secretary
select labs throughout the United States , including Puerto Rico ,
t see that in the States . The manager can say
they were s omew hat satisfied .
Token the
Token ID262
Feature activation+1.72e-03

Pos logit contributions
amental+0.008
enders+0.008
 vac+0.007
vas+0.007
NJ+0.007
Neg logit contributions
stab-0.009
achelor-0.008
RED-0.008
ifiable-0.008
 Brah-0.008
Token clown
Token ID25573
Feature activation+8.42e-03

Pos logit contributions
amental+0.001
enders+0.001
 vac+0.001
vas+0.001
 wax+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Tokens
Token ID82
Feature activation-1.18e-02

Pos logit contributions
amental+0.006
enders+0.006
vas+0.005
NJ+0.005
 vac+0.005
Neg logit contributions
stab-0.006
achelor-0.006
RED-0.006
 Brah-0.006
ifiable-0.006
Token,
Token ID11
Feature activation+4.25e-03

Pos logit contributions
stab+0.009
achelor+0.008
RED+0.008
ifiable+0.008
 Brah+0.008
Neg logit contributions
amental-0.008
enders-0.008
vas-0.007
 vac-0.007
NJ-0.007
Token the
Token ID262
Feature activation+1.70e-03

Pos logit contributions
amental+0.003
enders+0.003
 vac+0.002
vas+0.002
NJ+0.002
Neg logit contributions
stab-0.003
achelor-0.003
RED-0.003
ifiable-0.003
 Brah-0.003
Token jug
Token ID45808
Feature activation+4.99e-01

Pos logit contributions
amental+0.001
enders+0.001
 vac+0.001
vas+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Tokenglers
Token ID33641
Feature activation+9.10e-02

Pos logit contributions
amental+0.268
enders+0.265
vas+0.236
 vac+0.235
NJ+0.234
Neg logit contributions
stab-0.431
achelor-0.395
RED-0.395
ifiable-0.392
 Brah-0.391
Token,
Token ID11
Feature activation-9.95e-04

Pos logit contributions
amental+0.059
enders+0.058
vas+0.053
 vac+0.053
NJ+0.053
Neg logit contributions
stab-0.068
RED-0.062
achelor-0.062
ifiable-0.061
 Brah-0.061
Token the
Token ID262
Feature activation+3.50e-03

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token crazy
Token ID7165
Feature activation-5.63e-02

Pos logit contributions
amental+0.002
enders+0.002
 vac+0.002
vas+0.002
NJ+0.002
Neg logit contributions
stab-0.003
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.002
Token ac
Token ID936
Feature activation-1.18e-01

Pos logit contributions
stab+0.043
achelor+0.039
RED+0.039
ifiable+0.038
 Brah+0.038
Neg logit contributions
amental-0.036
enders-0.036
vas-0.032
 vac-0.032
NJ-0.032
Tokenía
Token ID29690
Feature activation+7.31e-03

Pos logit contributions
amental+0.079
enders+0.079
NJ+0.071
vas+0.070
 vac+0.070
Neg logit contributions
stab-0.102
RED-0.093
achelor-0.092
ifiable-0.092
 Brah-0.091
Token que
Token ID8358
Feature activation+1.82e-01

Pos logit contributions
amental+0.004
enders+0.004
vas+0.004
NJ+0.004
eper+0.004
Neg logit contributions
stab-0.006
RED-0.005
achelor-0.005
ifiable-0.005
 Brah-0.005
Token mi
Token ID21504
Feature activation+1.64e-02

Pos logit contributions
amental+0.112
enders+0.112
NJ+0.100
vas+0.100
eper+0.099
Neg logit contributions
stab-0.142
RED-0.128
achelor-0.128
 Brah-0.128
ifiable-0.127
Token hij
Token ID16836
Feature activation+1.31e-01

Pos logit contributions
amental+0.010
enders+0.010
NJ+0.009
vas+0.009
eper+0.009
Neg logit contributions
stab-0.013
achelor-0.012
RED-0.012
 Brah-0.012
ifiable-0.012
Tokena
Token ID64
Feature activation+8.90e-02

Pos logit contributions
amental+0.059
enders+0.058
NJ+0.050
 vac+0.050
vas+0.050
Neg logit contributions
stab-0.125
achelor-0.115
RED-0.115
ifiable-0.115
 Brah-0.114
Token jug
Token ID45808
Feature activation+4.94e-01

Pos logit contributions
amental+0.055
enders+0.054
NJ+0.049
vas+0.049
eper+0.048
Neg logit contributions
stab-0.070
RED-0.064
achelor-0.063
ifiable-0.063
 Brah-0.063
Tokenara
Token ID3301
Feature activation-2.11e-01

Pos logit contributions
amental+0.288
enders+0.286
vas+0.257
 vac+0.256
NJ+0.256
Neg logit contributions
stab-0.403
achelor-0.368
RED-0.367
ifiable-0.364
 Brah-0.362
Token con
Token ID369
Feature activation+3.85e-02

Pos logit contributions
stab+0.165
RED+0.150
achelor+0.150
ifiable+0.149
 Brah+0.148
Neg logit contributions
amental-0.129
enders-0.129
NJ-0.115
vas-0.115
eper-0.114
Token e
Token ID304
Feature activation+1.62e-01

Pos logit contributions
amental+0.024
enders+0.024
NJ+0.022
vas+0.021
 vac+0.021
Neg logit contributions
stab-0.030
RED-0.027
achelor-0.027
ifiable-0.027
 Brah-0.027
Tokenlla
Token ID8466
Feature activation-1.80e-03

Pos logit contributions
amental+0.093
enders+0.093
NJ+0.082
 vac+0.082
vas+0.082
Neg logit contributions
stab-0.134
RED-0.122
achelor-0.122
ifiable-0.120
 Brah-0.120
Token.
Token ID13
Feature activation-2.54e-03

Pos logit contributions
stab+0.001
RED+0.001
achelor+0.001
 Brah+0.001
ifiable+0.001
Neg logit contributions
amental-0.001
enders-0.001
NJ-0.001
vas-0.001
eper-0.001
Token Wh
Token ID854
Feature activation-1.83e-01

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
NJ-0.000
Tokenist
Token ID396
Feature activation-2.18e-01

Pos logit contributions
stab+0.087
RED+0.074
achelor+0.074
ifiable+0.073
 Brah+0.073
Neg logit contributions
amental-0.169
enders-0.168
vas-0.157
 vac-0.157
NJ-0.156
Tokenling
Token ID1359
Feature activation+1.46e-01

Pos logit contributions
stab+0.202
RED+0.186
achelor+0.185
ifiable+0.184
 Brah+0.182
Neg logit contributions
amental-0.104
enders-0.102
 vac-0.090
vas-0.089
NJ-0.089
Token Woods
Token ID16483
Feature activation+3.67e-02

Pos logit contributions
amental+0.093
enders+0.092
vas+0.083
 vac+0.083
NJ+0.083
Neg logit contributions
stab-0.112
RED-0.101
achelor-0.101
ifiable-0.100
 Brah-0.100
Token to
Token ID284
Feature activation+8.80e-04

Pos logit contributions
amental+0.024
enders+0.023
 vac+0.021
vas+0.021
NJ+0.021
Neg logit contributions
stab-0.028
RED-0.025
achelor-0.025
ifiable-0.025
 Brah-0.025
Token vac
Token ID6658
Feature activation+4.94e-01

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
NJ+0.001
 vac+0.001
Neg logit contributions
stab-0.001
RED-0.001
achelor-0.001
ifiable-0.001
 Brah-0.001
Tokenate
Token ID378
Feature activation-2.05e-02

Pos logit contributions
enders+0.343
amental+0.340
NJ+0.314
existent+0.314
vas+0.313
Neg logit contributions
stab-0.345
achelor-0.309
ifiable-0.307
RED-0.306
 Brah-0.305
Token 14
Token ID1478
Feature activation-1.02e-01

Pos logit contributions
stab+0.015
achelor+0.014
RED+0.014
ifiable+0.013
 Brah+0.013
Neg logit contributions
amental-0.014
enders-0.014
vas-0.012
 vac-0.012
NJ-0.012
Token.
Token ID13
Feature activation-4.51e-03

Pos logit contributions
stab+0.072
achelor+0.065
RED+0.065
 Brah+0.065
ifiable+0.064
Neg logit contributions
amental-0.070
enders-0.070
vas-0.064
 vac-0.063
NJ-0.063
Token5
Token ID20
Feature activation+5.66e-02

Pos logit contributions
stab+0.004
RED+0.003
achelor+0.003
 Brah+0.003
ifiable+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.002
 vac-0.002
NJ-0.002
Token acre
Token ID31244
Feature activation-1.08e-01

Pos logit contributions
amental+0.041
enders+0.041
vas+0.038
 vac+0.038
NJ+0.038
Neg logit contributions
stab-0.038
achelor-0.034
RED-0.034
 Brah-0.033
ifiable-0.033
Token,"
Token ID553
Feature activation-3.13e-02

Pos logit contributions
stab+0.143
achelor+0.129
RED+0.129
 Brah+0.127
ifiable+0.127
Neg logit contributions
amental-0.130
enders-0.129
 vac-0.118
vas-0.117
 wax-0.117
Token Ger
Token ID13573
Feature activation-1.80e-01

Pos logit contributions
stab+0.025
RED+0.022
achelor+0.022
ifiable+0.022
 Brah+0.022
Neg logit contributions
amental-0.019
enders-0.019
vas-0.017
 vac-0.017
NJ-0.017
Tokenads
Token ID5643
Feature activation+1.11e-01

Pos logit contributions
stab+0.156
achelor+0.143
RED+0.143
ifiable+0.142
 Brah+0.141
Neg logit contributions
amental-0.095
enders-0.094
 vac-0.084
NJ-0.084
 expiration-0.083
Token tells
Token ID4952
Feature activation-1.25e-02

Pos logit contributions
amental+0.070
enders+0.070
vas+0.063
 vac+0.063
NJ+0.063
Neg logit contributions
stab-0.084
achelor-0.077
RED-0.077
ifiable-0.076
 Brah-0.076
Token Heat
Token ID12308
Feature activation+1.25e-01

Pos logit contributions
stab+0.008
achelor+0.008
RED+0.008
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.009
enders-0.009
vas-0.008
 vac-0.008
NJ-0.008
Token Vision
Token ID19009
Feature activation+4.82e-01

Pos logit contributions
amental+0.073
enders+0.071
vas+0.065
 vac+0.064
eper+0.064
Neg logit contributions
stab-0.103
RED-0.094
achelor-0.093
ifiable-0.093
 Brah-0.092
Token via
Token ID2884
Feature activation-1.22e-01

Pos logit contributions
amental+0.319
enders+0.316
vas+0.288
 vac+0.288
NJ+0.286
Neg logit contributions
stab-0.354
RED-0.320
achelor-0.320
ifiable-0.317
 Brah-0.316
Token phone
Token ID3072
Feature activation-8.05e-02

Pos logit contributions
stab+0.086
RED+0.078
achelor+0.077
ifiable+0.077
 Brah+0.076
Neg logit contributions
amental-0.085
enders-0.084
vas-0.077
 vac-0.077
NJ-0.076
Token.
Token ID13
Feature activation-5.75e-03

Pos logit contributions
stab+0.058
achelor+0.053
RED+0.053
ifiable+0.052
 Brah+0.052
Neg logit contributions
amental-0.054
enders-0.054
vas-0.049
 vac-0.049
NJ-0.049
Token "
Token ID366
Feature activation-8.12e-02

Pos logit contributions
stab+0.004
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
TokenMy
Token ID3666
Feature activation-2.88e-02

Pos logit contributions
stab+0.059
achelor+0.053
RED+0.053
ifiable+0.053
 Brah+0.052
Neg logit contributions
amental-0.055
enders-0.054
vas-0.050
NJ-0.049
 vac-0.049
Token the
Token ID262
Feature activation-4.21e-03

Pos logit contributions
stab+0.008
achelor+0.007
RED+0.007
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.007
enders-0.007
 vac-0.007
vas-0.007
NJ-0.007
Token first
Token ID717
Feature activation-1.80e-02

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.002
 vac-0.002
NJ-0.002
Token family
Token ID1641
Feature activation-1.76e-01

Pos logit contributions
stab+0.013
achelor+0.011
RED+0.011
ifiable+0.011
 Brah+0.011
Neg logit contributions
amental-0.013
enders-0.013
vas-0.011
 vac-0.011
NJ-0.011
Token soon
Token ID2582
Feature activation+2.07e-01

Pos logit contributions
stab+0.131
achelor+0.119
RED+0.119
ifiable+0.117
 Brah+0.117
Neg logit contributions
amental-0.115
enders-0.114
vas-0.103
 vac-0.103
NJ-0.102
Token to
Token ID284
Feature activation-4.65e-03

Pos logit contributions
amental+0.134
enders+0.132
 vac+0.121
vas+0.120
NJ+0.119
Neg logit contributions
stab-0.156
RED-0.141
achelor-0.141
ifiable-0.139
 Brah-0.139
Token vac
Token ID6658
Feature activation+4.78e-01

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Tokenate
Token ID378
Feature activation-3.34e-02

Pos logit contributions
amental+0.322
enders+0.321
vas+0.292
NJ+0.291
 vac+0.291
Neg logit contributions
stab-0.345
achelor-0.311
RED-0.309
ifiable-0.307
 Brah-0.306
Token the
Token ID262
Feature activation-1.18e-02

Pos logit contributions
stab+0.024
achelor+0.022
RED+0.022
ifiable+0.022
 Brah+0.022
Neg logit contributions
amental-0.023
enders-0.022
vas-0.020
 vac-0.020
NJ-0.020
Token White
Token ID2635
Feature activation-1.54e-01

Pos logit contributions
stab+0.007
RED+0.006
achelor+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.009
enders-0.009
 vac-0.009
vas-0.009
 wax-0.009
Token House
Token ID2097
Feature activation-7.17e-02

Pos logit contributions
stab+0.101
achelor+0.090
RED+0.090
ifiable+0.089
 Brah+0.089
Neg logit contributions
amental-0.113
enders-0.113
vas-0.104
 vac-0.104
NJ-0.103
Token for
Token ID329
Feature activation-3.04e-02

Pos logit contributions
stab+0.053
achelor+0.048
RED+0.048
ifiable+0.048
 Brah+0.048
Neg logit contributions
amental-0.047
enders-0.047
vas-0.042
 vac-0.042
NJ-0.042
Token has
Token ID468
Feature activation-7.41e-02

Pos logit contributions
stab+0.033
achelor+0.030
RED+0.030
ifiable+0.029
 Brah+0.029
Neg logit contributions
amental-0.028
enders-0.028
vas-0.025
 vac-0.025
NJ-0.025
Token always
Token ID1464
Feature activation-1.05e-01

Pos logit contributions
stab+0.058
achelor+0.053
RED+0.053
ifiable+0.052
 Brah+0.052
Neg logit contributions
amental-0.045
enders-0.045
vas-0.041
 vac-0.040
NJ-0.040
Token been
Token ID587
Feature activation+6.63e-02

Pos logit contributions
stab+0.086
achelor+0.079
RED+0.079
ifiable+0.078
 Brah+0.078
Neg logit contributions
amental-0.060
enders-0.060
vas-0.053
NJ-0.053
 vac-0.053
Token non
Token ID1729
Feature activation+6.23e-02

Pos logit contributions
amental+0.043
enders+0.043
vas+0.039
 vac+0.039
NJ+0.039
Neg logit contributions
stab-0.050
RED-0.045
achelor-0.045
ifiable-0.044
 Brah-0.044
Token-
Token ID12
Feature activation-9.93e-03

Pos logit contributions
amental+0.041
enders+0.040
NJ+0.037
 vac+0.037
vas+0.036
Neg logit contributions
stab-0.046
RED-0.042
achelor-0.042
ifiable-0.042
 Brah-0.041
Tokenexistent
Token ID32786
Feature activation+4.61e-01

Pos logit contributions
stab+0.013
RED+0.012
ifiable+0.012
achelor+0.012
 Brah+0.012
Neg logit contributions
amental-0.001
enders-0.001
 vac-0.001
eper-0.001
vas-0.001
Token,
Token ID11
Feature activation+5.94e-03

Pos logit contributions
amental+0.301
enders+0.298
vas+0.271
 vac+0.271
NJ+0.269
Neg logit contributions
stab-0.344
achelor-0.311
RED-0.311
ifiable-0.308
 Brah-0.307
Token but
Token ID475
Feature activation+1.30e-01

Pos logit contributions
amental+0.004
enders+0.004
vas+0.003
 vac+0.003
NJ+0.003
Neg logit contributions
stab-0.005
RED-0.004
achelor-0.004
ifiable-0.004
 Brah-0.004
Token the
Token ID262
Feature activation+4.65e-03

Pos logit contributions
amental+0.092
enders+0.091
 vac+0.084
vas+0.083
NJ+0.083
Neg logit contributions
stab-0.090
achelor-0.081
RED-0.080
ifiable-0.079
 Brah-0.079
Token allegations
Token ID7636
Feature activation+7.76e-02

Pos logit contributions
amental+0.003
enders+0.003
vas+0.003
 vac+0.003
NJ+0.003
Neg logit contributions
stab-0.003
RED-0.003
achelor-0.003
ifiable-0.003
 Brah-0.003
Token,
Token ID11
Feature activation+2.84e-03

Pos logit contributions
amental+0.052
enders+0.052
 vac+0.047
vas+0.047
 wax+0.047
Neg logit contributions
stab-0.057
achelor-0.051
RED-0.051
ifiable-0.050
 Brah-0.050
Token haunt
Token ID36334
Feature activation+6.17e-02

Pos logit contributions
stab+0.135
achelor+0.122
RED+0.122
ifiable+0.121
 Brah+0.120
Neg logit contributions
amental-0.125
enders-0.124
NJ-0.113
vas-0.113
 vac-0.112
Token Sullivan
Token ID18501
Feature activation-7.39e-02

Pos logit contributions
amental+0.045
enders+0.045
vas+0.042
 vac+0.041
NJ+0.041
Neg logit contributions
stab-0.041
RED-0.036
achelor-0.036
ifiable-0.036
 Brah-0.036
Token and
Token ID290
Feature activation+2.50e-03

Pos logit contributions
stab+0.055
achelor+0.050
RED+0.050
ifiable+0.049
 Brah+0.049
Neg logit contributions
amental-0.048
enders-0.048
vas-0.043
 vac-0.043
NJ-0.043
Token Ma
Token ID6669
Feature activation+1.75e-01

Pos logit contributions
amental+0.002
enders+0.002
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.002
RED-0.002
achelor-0.002
ifiable-0.002
 Brah-0.002
Tokenia
Token ID544
Feature activation-4.76e-02

Pos logit contributions
amental+0.096
enders+0.095
vas+0.085
 vac+0.084
NJ+0.084
Neg logit contributions
stab-0.149
RED-0.137
achelor-0.137
ifiable-0.136
 Brah-0.135
Tokenva
Token ID6862
Feature activation+4.57e-01

Pos logit contributions
stab+0.035
achelor+0.032
RED+0.032
ifiable+0.031
 Brah+0.031
Neg logit contributions
amental-0.032
enders-0.031
vas-0.029
 vac-0.029
NJ-0.028
Token.
Token ID13
Feature activation+1.71e-03

Pos logit contributions
amental+0.300
enders+0.298
vas+0.272
 vac+0.271
NJ+0.269
Neg logit contributions
stab-0.339
achelor-0.307
RED-0.307
ifiable-0.303
 Brah-0.302
Token They
Token ID1119
Feature activation-2.39e-02

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token have
Token ID423
Feature activation-4.92e-02

Pos logit contributions
stab+0.018
achelor+0.016
RED+0.016
ifiable+0.016
 Brah+0.016
Neg logit contributions
amental-0.015
enders-0.015
vas-0.014
 vac-0.014
NJ-0.014
Token been
Token ID587
Feature activation+6.94e-02

Pos logit contributions
stab+0.038
RED+0.035
achelor+0.035
ifiable+0.034
 Brah+0.034
Neg logit contributions
amental-0.031
enders-0.031
vas-0.028
NJ-0.027
 vac-0.027
Token diagnosed
Token ID14641
Feature activation-3.90e-02

Pos logit contributions
amental+0.045
enders+0.044
vas+0.040
 vac+0.040
NJ+0.040
Neg logit contributions
stab-0.052
achelor-0.047
RED-0.047
ifiable-0.047
 Brah-0.047
Token-
Token ID12
Feature activation-2.07e-02

Pos logit contributions
stab+0.107
RED+0.097
achelor+0.097
 Brah+0.095
ifiable+0.095
Neg logit contributions
amental-0.098
enders-0.097
 vac-0.089
vas-0.089
NJ-0.088
Tokenharm
Token ID29155
Feature activation-2.25e-01

Pos logit contributions
stab+0.011
achelor+0.010
RED+0.010
 Brah+0.010
ifiable+0.010
Neg logit contributions
amental-0.017
enders-0.017
vas-0.016
existent-0.016
 vac-0.016
Token."
Token ID526
Feature activation+5.83e-02

Pos logit contributions
stab+0.167
RED+0.151
achelor+0.151
 Brah+0.149
ifiable+0.149
Neg logit contributions
amental-0.147
enders-0.146
 vac-0.133
vas-0.132
 wax-0.131
Token Ma
Token ID6669
Feature activation+1.68e-01

Pos logit contributions
amental+0.039
enders+0.039
vas+0.036
 vac+0.036
NJ+0.036
Neg logit contributions
stab-0.042
achelor-0.038
RED-0.038
ifiable-0.037
 Brah-0.037
Tokenia
Token ID544
Feature activation-5.10e-02

Pos logit contributions
amental+0.118
enders+0.117
 vac+0.107
vas+0.107
NJ+0.107
Neg logit contributions
stab-0.116
achelor-0.104
RED-0.104
ifiable-0.104
 Brah-0.103
Tokenva
Token ID6862
Feature activation+4.54e-01

Pos logit contributions
stab+0.066
RED+0.062
achelor+0.062
ifiable+0.062
 Brah+0.062
Neg logit contributions
amental-0.006
enders-0.005
 vac-0.002
NJ-0.002
 expiration-0.002
Token,
Token ID11
Feature activation-4.01e-03

Pos logit contributions
amental+0.290
enders+0.288
vas+0.262
 vac+0.262
NJ+0.259
Neg logit contributions
stab-0.344
achelor-0.313
RED-0.313
ifiable-0.309
 Brah-0.307
Token a
Token ID257
Feature activation+3.42e-03

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.002
vas-0.002
NJ-0.002
Token former
Token ID1966
Feature activation+5.15e-02

Pos logit contributions
amental+0.002
enders+0.002
 vac+0.002
vas+0.002
NJ+0.002
Neg logit contributions
stab-0.002
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.002
Token policeman
Token ID32166
Feature activation-1.44e-01

Pos logit contributions
amental+0.035
enders+0.034
vas+0.031
 vac+0.031
NJ+0.031
Neg logit contributions
stab-0.037
achelor-0.034
RED-0.034
ifiable-0.033
 Brah-0.033
Token from
Token ID422
Feature activation-2.17e-02

Pos logit contributions
stab+0.108
achelor+0.098
RED+0.098
ifiable+0.097
 Brah+0.097
Neg logit contributions
amental-0.093
enders-0.092
vas-0.084
 vac-0.083
NJ-0.083
Token,
Token ID11
Feature activation-5.14e-03

Pos logit contributions
stab+0.044
achelor+0.040
RED+0.040
ifiable+0.039
 Brah+0.039
Neg logit contributions
amental-0.041
enders-0.040
vas-0.037
 vac-0.037
NJ-0.037
Token K
Token ID509
Feature activation-1.54e-02

Pos logit contributions
stab+0.004
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Tokenatic
Token ID1512
Feature activation+9.22e-02

Pos logit contributions
stab+0.012
achelor+0.010
RED+0.010
ifiable+0.010
 Brah+0.010
Neg logit contributions
amental-0.010
enders-0.010
vas-0.009
 vac-0.009
NJ-0.009
Tokena
Token ID64
Feature activation+8.58e-02

Pos logit contributions
amental+0.060
enders+0.059
vas+0.054
 vac+0.054
NJ+0.054
Neg logit contributions
stab-0.069
RED-0.063
achelor-0.063
ifiable-0.062
 Brah-0.062
Token Jane
Token ID12091
Feature activation+1.38e-01

Pos logit contributions
amental+0.057
enders+0.057
vas+0.052
 vac+0.052
NJ+0.051
Neg logit contributions
stab-0.063
achelor-0.057
RED-0.057
ifiable-0.056
 Brah-0.056
Tokenva
Token ID6862
Feature activation+4.53e-01

Pos logit contributions
amental+0.091
enders+0.090
vas+0.082
 vac+0.082
NJ+0.081
Neg logit contributions
stab-0.103
achelor-0.093
RED-0.093
ifiable-0.092
 Brah-0.092
Token in
Token ID287
Feature activation-5.64e-03

Pos logit contributions
amental+0.295
enders+0.293
vas+0.267
 vac+0.266
NJ+0.264
Neg logit contributions
stab-0.338
RED-0.306
achelor-0.306
ifiable-0.303
 Brah-0.302
Token front
Token ID2166
Feature activation+1.04e-01

Pos logit contributions
stab+0.004
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.003
 vac-0.003
NJ-0.003
Token ot
Token ID30972
Feature activation-1.56e-02

Pos logit contributions
amental+0.070
enders+0.069
vas+0.063
 vac+0.063
NJ+0.062
Neg logit contributions
stab-0.076
achelor-0.069
RED-0.069
ifiable-0.068
 Brah-0.068
Token the
Token ID262
Feature activation-3.42e-03

Pos logit contributions
stab+0.012
RED+0.010
achelor+0.010
ifiable+0.010
 Brah+0.010
Neg logit contributions
amental-0.010
enders-0.010
vas-0.009
 vac-0.009
NJ-0.009
Token Secret
Token ID3943
Feature activation+4.34e-02

Pos logit contributions
stab+0.003
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.002
 vac-0.002
NJ-0.002
Token arrest
Token ID3251
Feature activation-1.54e-02

Pos logit contributions
amental+0.005
enders+0.005
vas+0.005
NJ+0.005
 vac+0.005
Neg logit contributions
stab-0.008
achelor-0.008
RED-0.008
ifiable-0.008
 Brah-0.008
Token,
Token ID11
Feature activation-3.49e-04

Pos logit contributions
stab+0.011
achelor+0.010
RED+0.010
ifiable+0.010
 Brah+0.010
Neg logit contributions
amental-0.010
enders-0.010
vas-0.009
 vac-0.009
NJ-0.009
Token
Token ID447
Feature activation+4.84e-03

Pos logit contributions
stab+0.000
RED+0.000
achelor+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
NJ-0.000
Token
Token ID251
Feature activation+6.95e-03

Pos logit contributions
amental+0.003
enders+0.003
vas+0.003
 vac+0.003
NJ+0.003
Neg logit contributions
stab-0.003
achelor-0.003
RED-0.003
ifiable-0.003
 Brah-0.003
Token Jane
Token ID12091
Feature activation+1.38e-01

Pos logit contributions
amental+0.005
enders+0.005
vas+0.004
 vac+0.004
NJ+0.004
Neg logit contributions
stab-0.005
RED-0.005
achelor-0.005
ifiable-0.005
 Brah-0.005
Tokenva
Token ID6862
Feature activation+4.53e-01

Pos logit contributions
amental+0.015
enders+0.014
 vac+0.005
NJ+0.005
 expiration+0.005
Neg logit contributions
stab-0.179
achelor-0.169
RED-0.169
ifiable-0.168
 Brah-0.167
Token said
Token ID531
Feature activation-2.07e-02

Pos logit contributions
amental+0.268
enders+0.265
vas+0.239
 vac+0.238
NJ+0.237
Neg logit contributions
stab-0.366
achelor-0.334
RED-0.334
ifiable-0.330
 Brah-0.329
Token,
Token ID11
Feature activation-6.38e-03

Pos logit contributions
stab+0.015
achelor+0.014
RED+0.014
ifiable+0.014
 Brah+0.014
Neg logit contributions
amental-0.014
enders-0.013
vas-0.012
 vac-0.012
NJ-0.012
Token adding
Token ID4375
Feature activation-5.93e-03

Pos logit contributions
stab+0.005
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Token that
Token ID326
Feature activation+7.80e-03

Pos logit contributions
stab+0.004
RED+0.004
achelor+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Token the
Token ID262
Feature activation-3.34e-03

Pos logit contributions
amental+0.005
enders+0.005
vas+0.005
 vac+0.005
NJ+0.005
Neg logit contributions
stab-0.006
achelor-0.005
RED-0.005
ifiable-0.005
 Brah-0.005
Token Prosecutor
Token ID37478
Feature activation-6.28e-02

Pos logit contributions
amental+0.133
enders+0.132
vas+0.122
 vac+0.121
NJ+0.121
Neg logit contributions
stab-0.110
achelor-0.098
RED-0.098
 Brah-0.097
ifiable-0.096
Token K
Token ID509
Feature activation-1.73e-02

Pos logit contributions
stab+0.046
achelor+0.042
RED+0.042
ifiable+0.041
 Brah+0.041
Neg logit contributions
amental-0.042
enders-0.041
vas-0.038
 vac-0.038
NJ-0.037
Tokenatic
Token ID1512
Feature activation+8.71e-02

Pos logit contributions
stab+0.015
RED+0.014
achelor+0.014
 Brah+0.014
ifiable+0.014
Neg logit contributions
amental-0.009
enders-0.009
vas-0.008
 vac-0.008
NJ-0.008
Tokena
Token ID64
Feature activation+8.72e-02

Pos logit contributions
amental+0.046
enders+0.046
vas+0.041
 vac+0.041
NJ+0.040
Neg logit contributions
stab-0.075
achelor-0.069
RED-0.069
ifiable-0.069
 Brah-0.068
Token Jane
Token ID12091
Feature activation+1.34e-01

Pos logit contributions
amental+0.045
enders+0.045
vas+0.039
 vac+0.039
NJ+0.039
Neg logit contributions
stab-0.077
achelor-0.071
RED-0.070
 Brah-0.070
ifiable-0.070
Tokenva
Token ID6862
Feature activation+4.53e-01

Pos logit contributions
amental+0.012
enders+0.012
vas+0.004
 vac+0.004
NJ+0.003
Neg logit contributions
stab-0.175
achelor-0.166
RED-0.166
ifiable-0.165
 Brah-0.165
Token personally
Token ID7620
Feature activation+1.13e-01

Pos logit contributions
amental+0.287
enders+0.284
 vac+0.259
vas+0.258
NJ+0.256
Neg logit contributions
stab-0.345
achelor-0.314
RED-0.314
ifiable-0.311
 Brah-0.309
Token intervened
Token ID35018
Feature activation+1.06e-01

Pos logit contributions
amental+0.071
enders+0.070
 vac+0.064
vas+0.064
NJ+0.063
Neg logit contributions
stab-0.087
achelor-0.079
RED-0.079
ifiable-0.078
 Brah-0.078
Token at
Token ID379
Feature activation-1.31e-02

Pos logit contributions
amental+0.070
enders+0.069
vas+0.063
 vac+0.063
NJ+0.063
Neg logit contributions
stab-0.079
RED-0.071
achelor-0.071
ifiable-0.070
 Brah-0.070
Token the
Token ID262
Feature activation+3.57e-04

Pos logit contributions
stab+0.010
achelor+0.009
RED+0.009
ifiable+0.009
 Brah+0.009
Neg logit contributions
amental-0.009
enders-0.009
 vac-0.008
vas-0.008
NJ-0.008
Token B
Token ID347
Feature activation-3.93e-02

Pos logit contributions
amental+0.000
enders+0.000
vas+0.000
 vac+0.000
NJ+0.000
Neg logit contributions
stab-0.000
achelor-0.000
RED-0.000
ifiable-0.000
 Brah-0.000
Token.
Token ID13
Feature activation-6.14e-03

Pos logit contributions
stab+0.057
RED+0.051
achelor+0.051
ifiable+0.050
 Brah+0.050
Neg logit contributions
amental-0.060
enders-0.059
vas-0.054
 vac-0.054
NJ-0.054
Token Washington
Token ID2669
Feature activation-1.50e-01

Pos logit contributions
stab+0.005
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Token,
Token ID11
Feature activation-2.91e-03

Pos logit contributions
stab+0.113
RED+0.103
achelor+0.103
ifiable+0.101
 Brah+0.101
Neg logit contributions
amental-0.096
enders-0.095
 vac-0.086
vas-0.086
NJ-0.086
Token DC
Token ID6257
Feature activation-8.20e-02

Pos logit contributions
stab+0.002
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
NJ-0.002
 vac-0.002
vas-0.002
Token :
Token ID1058
Feature activation-2.44e-02

Pos logit contributions
stab+0.060
achelor+0.055
RED+0.054
 Brah+0.054
ifiable+0.054
Neg logit contributions
amental-0.054
enders-0.054
 vac-0.049
vas-0.049
NJ-0.049
Token Hemisphere
Token ID42811
Feature activation+4.50e-01

Pos logit contributions
stab+0.018
achelor+0.016
RED+0.016
ifiable+0.016
 Brah+0.016
Neg logit contributions
amental-0.017
enders-0.016
vas-0.015
 vac-0.015
NJ-0.015
Token Publishing
Token ID23499
Feature activation-4.89e-02

Pos logit contributions
amental+0.333
enders+0.330
vas+0.304
 vac+0.303
NJ+0.302
Neg logit contributions
stab-0.296
achelor-0.264
RED-0.264
ifiable-0.261
 Brah-0.260
Token.
Token ID764
Feature activation-1.18e-01

Pos logit contributions
stab+0.032
achelor+0.028
RED+0.028
ifiable+0.028
 Brah+0.028
Neg logit contributions
amental-0.037
enders-0.037
 vac-0.034
vas-0.034
NJ-0.034
Token
Token ID198
Feature activation+8.96e-03

Pos logit contributions
stab+0.087
RED+0.079
achelor+0.079
ifiable+0.078
 Brah+0.078
Neg logit contributions
amental-0.077
enders-0.077
vas-0.070
 vac-0.069
NJ-0.069
Token
Token ID198
Feature activation+5.92e-03

Pos logit contributions
amental+0.006
enders+0.006
vas+0.005
 vac+0.005
NJ+0.005
Neg logit contributions
stab-0.007
achelor-0.006
RED-0.006
ifiable-0.006
 Brah-0.006
TokenGoogle
Token ID11708
Feature activation-5.56e-02

Pos logit contributions
amental+0.004
enders+0.004
 vac+0.004
vas+0.004
eper+0.004
Neg logit contributions
stab-0.004
RED-0.004
achelor-0.004
ifiable-0.004
 Brah-0.003
Token Knowledge
Token ID20414
Feature activation+1.08e-01

Pos logit contributions
stab+0.008
achelor+0.007
RED+0.007
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.006
enders-0.006
vas-0.006
 vac-0.006
NJ-0.006
Token Sri
Token ID20872
Feature activation-2.63e-02

Pos logit contributions
amental+0.073
enders+0.072
vas+0.066
 vac+0.066
NJ+0.065
Neg logit contributions
stab-0.078
RED-0.070
achelor-0.070
ifiable-0.070
 Brah-0.070
Token Hay
Token ID9075
Feature activation-1.64e-01

Pos logit contributions
stab+0.019
RED+0.017
 Brah+0.017
achelor+0.017
ifiable+0.017
Neg logit contributions
amental-0.017
enders-0.017
 vac-0.016
NJ-0.016
 expiration-0.016
Tokenag
Token ID363
Feature activation-4.08e-02

Pos logit contributions
stab+0.121
RED+0.110
achelor+0.110
ifiable+0.109
 Brah+0.109
Neg logit contributions
amental-0.108
enders-0.107
vas-0.097
 vac-0.096
NJ-0.096
Tokenri
Token ID380
Feature activation-7.80e-02

Pos logit contributions
stab+0.030
RED+0.027
achelor+0.027
ifiable+0.027
 Brah+0.026
Neg logit contributions
amental-0.027
enders-0.027
vas-0.025
 vac-0.025
NJ-0.024
Tokenva
Token ID6862
Feature activation+4.49e-01

Pos logit contributions
stab+0.058
achelor+0.052
RED+0.052
ifiable+0.052
 Brah+0.051
Neg logit contributions
amental-0.051
enders-0.051
vas-0.046
 vac-0.046
NJ-0.046
Token have
Token ID423
Feature activation-5.44e-02

Pos logit contributions
amental+0.291
enders+0.289
vas+0.263
 vac+0.262
NJ+0.260
Neg logit contributions
stab-0.337
achelor-0.306
RED-0.305
ifiable-0.302
 Brah-0.300
Token se
Token ID384
Feature activation+1.63e-01

Pos logit contributions
stab+0.041
RED+0.037
achelor+0.037
ifiable+0.036
 Brah+0.036
Neg logit contributions
amental-0.036
enders-0.035
vas-0.032
 vac-0.032
NJ-0.032
Tokenperate
Token ID30052
Feature activation+1.54e-01

Pos logit contributions
amental+0.100
enders+0.100
vas+0.090
 vac+0.090
NJ+0.089
Neg logit contributions
stab-0.127
achelor-0.116
RED-0.116
ifiable-0.114
 Brah-0.114
Token shr
Token ID10157
Feature activation+6.36e-02

Pos logit contributions
amental+0.099
enders+0.098
vas+0.089
 vac+0.088
NJ+0.088
Neg logit contributions
stab-0.116
RED-0.106
achelor-0.106
ifiable-0.104
 Brah-0.104
Tokenines
Token ID1127
Feature activation+7.69e-02

Pos logit contributions
amental+0.036
enders+0.035
NJ+0.032
 vac+0.032
 expiration+0.032
Neg logit contributions
stab-0.053
achelor-0.049
RED-0.048
ifiable-0.048
 Brah-0.048
Token to
Token ID284
Feature activation+4.46e-03

Pos logit contributions
amental+0.049
enders+0.049
 vac+0.044
vas+0.044
NJ+0.044
Neg logit contributions
stab-0.056
RED-0.051
achelor-0.051
ifiable-0.050
 Brah-0.050
Token eight
Token ID3624
Feature activation-9.12e-02

Pos logit contributions
amental+0.003
enders+0.003
vas+0.003
 vac+0.003
NJ+0.003
Neg logit contributions
stab-0.003
RED-0.003
achelor-0.003
ifiable-0.003
 Brah-0.003
Token,
Token ID11
Feature activation-4.88e-03

Pos logit contributions
stab+0.072
achelor+0.066
RED+0.066
ifiable+0.065
 Brah+0.065
Neg logit contributions
amental-0.055
enders-0.055
vas-0.050
 vac-0.050
NJ-0.049
Token Ma
Token ID6669
Feature activation+1.62e-01

Pos logit contributions
stab+0.004
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.003
vas-0.003
NJ-0.003
Tokenia
Token ID544
Feature activation-5.28e-02

Pos logit contributions
amental+0.115
enders+0.114
 vac+0.104
vas+0.104
NJ+0.104
Neg logit contributions
stab-0.112
achelor-0.100
RED-0.100
ifiable-0.099
 Brah-0.099
Tokenva
Token ID6862
Feature activation+4.49e-01

Pos logit contributions
stab+0.068
RED+0.064
achelor+0.064
ifiable+0.064
 Brah+0.064
Neg logit contributions
amental-0.006
enders-0.005
 vac-0.002
NJ-0.002
 expiration-0.002
Token withdrew
Token ID25518
Feature activation-1.06e-01

Pos logit contributions
amental+0.284
enders+0.281
 vac+0.257
vas+0.256
NJ+0.253
Neg logit contributions
stab-0.344
achelor-0.313
RED-0.312
ifiable-0.309
 Brah-0.307
Token from
Token ID422
Feature activation-2.81e-02

Pos logit contributions
stab+0.077
achelor+0.070
RED+0.070
ifiable+0.069
 Brah+0.069
Neg logit contributions
amental-0.071
enders-0.071
 vac-0.064
vas-0.064
NJ-0.064
Token family
Token ID1641
Feature activation-1.76e-01

Pos logit contributions
stab+0.020
RED+0.018
achelor+0.018
ifiable+0.018
 Brah+0.018
Neg logit contributions
amental-0.019
enders-0.019
 vac-0.017
vas-0.017
NJ-0.017
Token and
Token ID290
Feature activation-6.66e-03

Pos logit contributions
stab+0.105
achelor+0.093
RED+0.093
ifiable+0.091
 Brah+0.091
Neg logit contributions
amental-0.141
enders-0.140
 vac-0.130
vas-0.130
NJ-0.129
Token friends
Token ID2460
Feature activation-1.04e-01

Pos logit contributions
stab+0.004
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.005
enders-0.005
vas-0.004
 vac-0.004
NJ-0.004
Token (@
Token ID4275
Feature activation+9.86e-02

Pos logit contributions
amental+0.057
enders+0.056
vas+0.049
 vac+0.049
NJ+0.049
Neg logit contributions
stab-0.098
achelor-0.090
RED-0.090
ifiable-0.089
 Brah-0.089
Tokenren
Token ID918
Feature activation+3.98e-02

Pos logit contributions
amental+0.059
enders+0.058
vas+0.053
 vac+0.052
NJ+0.052
Neg logit contributions
stab-0.079
achelor-0.072
RED-0.072
ifiable-0.071
 Brah-0.071
Tokenlav
Token ID18809
Feature activation-2.25e-01

Pos logit contributions
amental+0.025
enders+0.025
vas+0.023
 vac+0.023
NJ+0.023
Neg logit contributions
stab-0.030
RED-0.027
achelor-0.027
ifiable-0.027
 Brah-0.027
Tokeno
Token ID78
Feature activation+3.21e-01

Pos logit contributions
stab+0.230
achelor+0.214
ifiable+0.213
RED+0.213
 Brah+0.211
Neg logit contributions
amental-0.084
enders-0.082
 vac-0.070
NJ-0.069
vas-0.069
Tokeniet
Token ID1155
Feature activation+1.10e-01

Pos logit contributions
amental+0.161
enders+0.159
vas+0.141
 vac+0.140
NJ+0.139
Neg logit contributions
stab-0.287
achelor-0.265
RED-0.263
ifiable-0.263
 Brah-0.261
Tokenva
Token ID6862
Feature activation+4.49e-01

Pos logit contributions
amental+0.064
enders+0.063
 vac+0.057
vas+0.057
NJ+0.056
Neg logit contributions
stab-0.090
achelor-0.083
RED-0.082
ifiable-0.082
 Brah-0.081
Token)
Token ID8
Feature activation-1.72e-02

Pos logit contributions
amental+0.305
enders+0.302
vas+0.276
 vac+0.276
NJ+0.273
Neg logit contributions
stab-0.322
achelor-0.291
RED-0.291
ifiable-0.288
 Brah-0.287
Token June
Token ID2795
Feature activation+1.82e-01

Pos logit contributions
stab+0.016
achelor+0.014
RED+0.014
ifiable+0.014
 Brah+0.014
Neg logit contributions
amental-0.008
enders-0.008
vas-0.007
 vac-0.007
NJ-0.007
Token 12
Token ID1105
Feature activation-1.60e-01

Pos logit contributions
amental+0.128
enders+0.127
vas+0.117
 vac+0.116
NJ+0.116
Neg logit contributions
stab-0.127
achelor-0.114
RED-0.114
ifiable-0.112
 Brah-0.112
Token,
Token ID11
Feature activation-1.03e-02

Pos logit contributions
stab+0.120
achelor+0.109
RED+0.109
ifiable+0.108
 Brah+0.107
Neg logit contributions
amental-0.103
enders-0.102
vas-0.093
 vac-0.093
NJ-0.092
Token 2017
Token ID2177
Feature activation-4.78e-02

Pos logit contributions
stab+0.007
achelor+0.006
RED+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.008
enders-0.008
vas-0.007
 vac-0.007
NJ-0.007
Token (@
Token ID4275
Feature activation+1.03e-01

Pos logit contributions
amental+0.056
enders+0.055
vas+0.049
 vac+0.049
NJ+0.048
Neg logit contributions
stab-0.102
RED-0.094
achelor-0.094
ifiable-0.093
 Brah-0.093
Tokenren
Token ID918
Feature activation+4.71e-02

Pos logit contributions
amental+0.058
enders+0.058
vas+0.052
 vac+0.051
NJ+0.051
Neg logit contributions
stab-0.086
achelor-0.079
RED-0.078
 Brah-0.078
ifiable-0.078
Tokenlav
Token ID18809
Feature activation-2.24e-01

Pos logit contributions
amental+0.043
enders+0.043
vas+0.040
 vac+0.040
NJ+0.040
Neg logit contributions
stab-0.023
achelor-0.020
RED-0.020
ifiable-0.019
 Brah-0.019
Tokeno
Token ID78
Feature activation+3.21e-01

Pos logit contributions
stab+0.257
achelor+0.240
RED+0.240
ifiable+0.240
 Brah+0.238
Neg logit contributions
amental-0.056
enders-0.055
 vac-0.042
vas-0.041
NJ-0.041
Tokeniet
Token ID1155
Feature activation+1.18e-01

Pos logit contributions
amental+0.158
enders+0.157
vas+0.138
 vac+0.137
NJ+0.136
Neg logit contributions
stab-0.290
achelor-0.267
RED-0.267
ifiable-0.265
 Brah-0.264
Tokenva
Token ID6862
Feature activation+4.49e-01

Pos logit contributions
amental+0.013
enders+0.012
NJ+0.005
 vac+0.005
 wax+0.004
Neg logit contributions
stab-0.152
RED-0.143
achelor-0.143
ifiable-0.143
 Brah-0.142
Token)
Token ID8
Feature activation-1.31e-02

Pos logit contributions
amental+0.305
enders+0.302
vas+0.275
 vac+0.275
NJ+0.273
Neg logit contributions
stab-0.323
RED-0.291
achelor-0.291
ifiable-0.288
 Brah-0.288
Token June
Token ID2795
Feature activation+1.79e-01

Pos logit contributions
stab+0.013
achelor+0.012
RED+0.012
ifiable+0.012
 Brah+0.012
Neg logit contributions
amental-0.006
enders-0.006
vas-0.005
 vac-0.005
NJ-0.005
Token 12
Token ID1105
Feature activation-1.56e-01

Pos logit contributions
amental+0.147
enders+0.146
vas+0.136
 vac+0.136
NJ+0.135
Neg logit contributions
stab-0.102
achelor-0.090
RED-0.090
ifiable-0.089
 Brah-0.088
Token,
Token ID11
Feature activation-7.94e-03

Pos logit contributions
stab+0.116
RED+0.105
achelor+0.105
ifiable+0.104
 Brah+0.103
Neg logit contributions
amental-0.102
enders-0.101
vas-0.092
 vac-0.092
NJ-0.091
Token 2017
Token ID2177
Feature activation-5.25e-02

Pos logit contributions
stab+0.005
RED+0.005
achelor+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.006
enders-0.006
vas-0.005
 vac-0.005
NJ-0.005
Token like
Token ID588
Feature activation+6.86e-02

Pos logit contributions
stab+0.046
achelor+0.041
RED+0.041
ifiable+0.041
 Brah+0.041
Neg logit contributions
amental-0.038
enders-0.038
vas-0.034
 vac-0.034
NJ-0.034
Token to
Token ID284
Feature activation-5.52e-03

Pos logit contributions
amental+0.047
enders+0.047
vas+0.043
 vac+0.043
NJ+0.043
Neg logit contributions
stab-0.049
achelor-0.044
RED-0.044
ifiable-0.043
 Brah-0.043
Token resolve
Token ID10568
Feature activation-4.97e-02

Pos logit contributions
stab+0.004
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
 vac-0.003
vas-0.003
NJ-0.003
Token non
Token ID1729
Feature activation+5.00e-02

Pos logit contributions
stab+0.037
RED+0.034
achelor+0.034
ifiable+0.033
 Brah+0.033
Neg logit contributions
amental-0.032
enders-0.032
vas-0.029
 vac-0.029
NJ-0.029
Token-
Token ID12
Feature activation-2.59e-02

Pos logit contributions
amental+0.034
enders+0.033
vas+0.030
 vac+0.030
NJ+0.030
Neg logit contributions
stab-0.036
RED-0.033
achelor-0.033
ifiable-0.032
 Brah-0.032
Tokenexistent
Token ID32786
Feature activation+4.48e-01

Pos logit contributions
stab+0.022
RED+0.020
achelor+0.020
ifiable+0.019
 Brah+0.019
Neg logit contributions
amental-0.015
enders-0.015
 vac-0.013
vas-0.013
 wax-0.013
Token domains
Token ID18209
Feature activation-1.18e-01

Pos logit contributions
amental+0.274
enders+0.272
vas+0.245
 vac+0.244
NJ+0.243
Neg logit contributions
stab-0.353
RED-0.321
achelor-0.321
ifiable-0.318
 Brah-0.318
Token to
Token ID284
Feature activation-4.64e-03

Pos logit contributions
stab+0.086
RED+0.078
achelor+0.078
ifiable+0.077
 Brah+0.077
Neg logit contributions
amental-0.078
enders-0.077
vas-0.071
NJ-0.070
 vac-0.070
Token search
Token ID2989
Feature activation+2.94e-02

Pos logit contributions
stab+0.003
RED+0.003
achelor+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
amental+0.019
enders+0.018
vas+0.017
 vac+0.016
NJ+0.016
Neg logit contributions
stab-0.023
RED-0.021
achelor-0.020
ifiable-0.020
 Brah-0.020
Tokend
Token ID67
Feature activation-2.68e-01

Pos logit contributions
stab+0.010
achelor+0.009
RED+0.009
ifiable+0.009
 Brah+0.009
Neg logit contributions
amental-0.008
enders-0.008
vas-0.008
 vac-0.008
NJ-0.008
Token of
Token ID286
Feature activation-1.01e-02

Pos logit contributions
amental+0.051
enders+0.051
vas+0.046
 vac+0.046
NJ+0.046
Neg logit contributions
stab-0.053
RED-0.048
achelor-0.047
ifiable-0.047
 Brah-0.047
Token democracy
Token ID7996
Feature activation+1.27e-01

Pos logit contributions
stab+0.007
RED+0.006
achelor+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.007
enders-0.007
NJ-0.006
vas-0.006
 vac-0.006
Token in
Token ID287
Feature activation-1.98e-03

Pos logit contributions
amental+0.085
enders+0.084
vas+0.077
NJ+0.077
 vac+0.076
Neg logit contributions
stab-0.093
achelor-0.084
RED-0.084
ifiable-0.083
 Brah-0.083
Token the
Token ID262
Feature activation+6.46e-04

Pos logit contributions
stab+0.002
RED+0.001
achelor+0.001
 Brah+0.001
ifiable+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
NJ-0.001
 vac-0.001
Token Western
Token ID4885
Feature activation-8.05e-03

Pos logit contributions
amental+0.000
enders+0.000
vas+0.000
NJ+0.000
 vac+0.000
Neg logit contributions
stab-0.000
RED-0.000
achelor-0.000
 Brah-0.000
ifiable-0.000
Token Hemisphere
Token ID42811
Feature activation+4.47e-01

Pos logit contributions
stab+0.008
RED+0.008
achelor+0.008
 Brah+0.008
ifiable+0.008
Neg logit contributions
amental-0.003
enders-0.003
vas-0.002
NJ-0.002
 vac-0.002
Token
Token ID447
Feature activation-6.68e-04

Pos logit contributions
amental+0.295
enders+0.293
vas+0.267
 vac+0.266
NJ+0.265
Neg logit contributions
stab-0.329
RED-0.297
achelor-0.297
ifiable-0.294
 Brah-0.294
Token
Token ID247
Feature activation+1.71e-03

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
NJ-0.000
Tokens
Token ID82
Feature activation-2.03e-02

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
RED-0.001
achelor-0.001
ifiable-0.001
 Brah-0.001
Token only
Token ID691
Feature activation-9.97e-03

Pos logit contributions
stab+0.014
RED+0.013
achelor+0.013
ifiable+0.012
 Brah+0.012
Neg logit contributions
amental-0.014
enders-0.014
vas-0.013
NJ-0.013
 vac-0.013
Token one
Token ID530
Feature activation+9.29e-02

Pos logit contributions
stab+0.007
RED+0.006
achelor+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.007
enders-0.007
NJ-0.006
vas-0.006
 vac-0.006
TokenThe
Token ID464
Feature activation+2.64e-02

Pos logit contributions
amental+0.000
enders+0.000
vas+0.000
 vac+0.000
NJ+0.000
Neg logit contributions
stab-0.000
achelor-0.000
RED-0.000
ifiable-0.000
 Brah-0.000
Token fourth
Token ID5544
Feature activation-7.62e-02

Pos logit contributions
amental+0.017
enders+0.017
vas+0.016
 vac+0.016
NJ+0.015
Neg logit contributions
stab-0.020
achelor-0.018
RED-0.018
ifiable-0.018
 Brah-0.017
Token big
Token ID1263
Feature activation-1.81e-01

Pos logit contributions
stab+0.053
RED+0.048
achelor+0.048
ifiable+0.047
 Brah+0.047
Neg logit contributions
amental-0.053
enders-0.053
vas-0.049
 vac-0.049
NJ-0.048
Token Project
Token ID4935
Feature activation-9.54e-03

Pos logit contributions
stab+0.129
RED+0.117
achelor+0.117
ifiable+0.115
 Brah+0.115
Neg logit contributions
amental-0.123
enders-0.123
vas-0.112
 vac-0.112
NJ-0.111
Token DI
Token ID14766
Feature activation+1.09e-01

Pos logit contributions
stab+0.007
achelor+0.006
RED+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.006
enders-0.006
vas-0.006
 vac-0.006
NJ-0.006
Tokenva
Token ID6862
Feature activation+4.46e-01

Pos logit contributions
amental+0.067
enders+0.066
vas+0.060
 vac+0.060
NJ+0.059
Neg logit contributions
stab-0.086
RED-0.078
achelor-0.078
ifiable-0.077
 Brah-0.077
Token X
Token ID1395
Feature activation+1.51e-01

Pos logit contributions
amental+0.276
enders+0.274
vas+0.247
 vac+0.247
NJ+0.245
Neg logit contributions
stab-0.348
RED-0.317
achelor-0.317
ifiable-0.313
 Brah-0.313
Token update
Token ID4296
Feature activation-1.09e-01

Pos logit contributions
amental+0.102
enders+0.102
vas+0.093
 vac+0.093
NJ+0.092
Neg logit contributions
stab-0.109
achelor-0.098
RED-0.098
ifiable-0.097
 Brah-0.097
Token is
Token ID318
Feature activation-2.41e-04

Pos logit contributions
stab+0.082
RED+0.075
achelor+0.075
ifiable+0.074
 Brah+0.074
Neg logit contributions
amental-0.071
enders-0.070
vas-0.064
 vac-0.064
NJ-0.063
Token in
Token ID287
Feature activation-1.36e-02

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
NJ-0.000
Token.
Token ID13
Feature activation-7.87e-03

Pos logit contributions
stab+0.010
achelor+0.009
RED+0.009
ifiable+0.009
 Brah+0.009
Neg logit contributions
amental-0.009
enders-0.009
vas-0.008
 vac-0.008
NJ-0.008
Tokening
Token ID278
Feature activation+2.68e-01

Pos logit contributions
stab+0.123
RED+0.114
achelor+0.114
ifiable+0.114
 Brah+0.114
Neg logit contributions
amental-0.033
enders-0.032
vas-0.025
 vac-0.025
NJ-0.025
Token and
Token ID290
Feature activation-6.23e-03

Pos logit contributions
amental+0.174
enders+0.172
vas+0.156
 vac+0.156
NJ+0.155
Neg logit contributions
stab-0.201
achelor-0.182
RED-0.181
ifiable-0.180
 Brah-0.180
Token obstruct
Token ID26520
Feature activation-4.63e-02

Pos logit contributions
stab+0.004
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Tokening
Token ID278
Feature activation+2.73e-01

Pos logit contributions
stab+0.051
achelor+0.048
RED+0.048
ifiable+0.048
 Brah+0.048
Neg logit contributions
amental-0.013
enders-0.013
vas-0.010
 vac-0.010
NJ-0.010
Token Jane
Token ID12091
Feature activation+1.34e-01

Pos logit contributions
amental+0.180
enders+0.178
vas+0.162
 vac+0.161
NJ+0.161
Neg logit contributions
stab-0.202
achelor-0.182
RED-0.182
ifiable-0.181
 Brah-0.181
Tokenva
Token ID6862
Feature activation+4.45e-01

Pos logit contributions
amental+0.017
enders+0.016
 vac+0.008
NJ+0.008
vas+0.008
Neg logit contributions
stab-0.171
achelor-0.161
RED-0.161
ifiable-0.160
 Brah-0.160
Token
Token ID447
Feature activation-3.88e-04

Pos logit contributions
amental+0.278
enders+0.276
 vac+0.250
vas+0.250
NJ+0.248
Neg logit contributions
stab-0.343
achelor-0.312
RED-0.312
ifiable-0.309
 Brah-0.308
Token
Token ID247
Feature activation-1.04e-03

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
NJ-0.000
Tokens
Token ID82
Feature activation-1.99e-02

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token special
Token ID2041
Feature activation+1.02e-01

Pos logit contributions
stab+0.015
achelor+0.013
RED+0.013
ifiable+0.013
 Brah+0.013
Neg logit contributions
amental-0.013
enders-0.013
 vac-0.012
vas-0.012
NJ-0.012
Token prosecution
Token ID12580
Feature activation+5.36e-03

Pos logit contributions
amental+0.069
enders+0.068
 vac+0.063
vas+0.063
NJ+0.062
Neg logit contributions
stab-0.073
achelor-0.066
RED-0.066
 Brah-0.065
ifiable-0.065
Token author
Token ID1772
Feature activation-1.01e-01

Pos logit contributions
stab+0.003
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.003
enders-0.003
vas-0.002
 vac-0.002
NJ-0.002
Token of
Token ID286
Feature activation-9.92e-03

Pos logit contributions
stab+0.074
achelor+0.067
RED+0.066
ifiable+0.066
 Brah+0.066
Neg logit contributions
amental-0.068
enders-0.068
vas-0.062
 vac-0.062
NJ-0.061
Token a
Token ID257
Feature activation+7.71e-03

Pos logit contributions
stab+0.007
RED+0.006
achelor+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.007
enders-0.007
vas-0.006
 vac-0.006
NJ-0.006
Token study
Token ID2050
Feature activation-7.44e-02

Pos logit contributions
amental+0.006
enders+0.006
 vac+0.005
vas+0.005
 wax+0.005
Neg logit contributions
stab-0.005
achelor-0.005
RED-0.005
ifiable-0.004
 Brah-0.004
Token of
Token ID286
Feature activation-8.72e-03

Pos logit contributions
stab+0.056
achelor+0.051
RED+0.051
ifiable+0.050
 Brah+0.050
Neg logit contributions
amental-0.048
enders-0.048
vas-0.043
 vac-0.043
NJ-0.043
Token Brah
Token ID36415
Feature activation-5.35e-01

Pos logit contributions
stab+0.005
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.007
enders-0.007
vas-0.007
 vac-0.007
NJ-0.007
Tokenms
Token ID907
Feature activation-2.31e-01

Pos logit contributions
stab+0.226
achelor+0.187
RED+0.186
 Brah+0.184
ifiable+0.184
Neg logit contributions
amental-0.523
enders-0.517
 vac-0.488
NJ-0.487
 expiration-0.486
Token,
Token ID11
Feature activation-4.75e-03

Pos logit contributions
stab+0.177
achelor+0.161
RED+0.161
ifiable+0.159
 Brah+0.159
Neg logit contributions
amental-0.146
enders-0.145
vas-0.131
 vac-0.131
NJ-0.130
Token dismiss
Token ID6735
Feature activation-1.93e-02

Pos logit contributions
stab+0.004
RED+0.003
achelor+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Tokenes
Token ID274
Feature activation-1.15e-01

Pos logit contributions
stab+0.012
RED+0.010
achelor+0.010
ifiable+0.010
 Brah+0.010
Neg logit contributions
amental-0.015
enders-0.015
 vac-0.014
vas-0.014
NJ-0.014
Token the
Token ID262
Feature activation-3.60e-05

Pos logit contributions
stab+0.085
RED+0.077
achelor+0.077
ifiable+0.076
 Brah+0.075
Neg logit contributions
amental-0.076
enders-0.075
 vac-0.068
vas-0.068
NJ-0.068
Token as
Token ID355
Feature activation-3.47e-02

Pos logit contributions
stab+0.152
RED+0.136
achelor+0.136
 Brah+0.135
ifiable+0.135
Neg logit contributions
amental-0.151
enders-0.150
vas-0.137
 vac-0.137
NJ-0.136
Token true
Token ID2081
Feature activation-2.51e-02

Pos logit contributions
stab+0.027
achelor+0.024
RED+0.024
ifiable+0.024
 Brah+0.024
Neg logit contributions
amental-0.022
enders-0.021
vas-0.019
 vac-0.019
NJ-0.019
Token the
Token ID262
Feature activation-2.56e-03

Pos logit contributions
stab+0.018
achelor+0.017
RED+0.017
 Brah+0.016
ifiable+0.016
Neg logit contributions
amental-0.017
enders-0.017
vas-0.015
 vac-0.015
NJ-0.015
Token allegation
Token ID24389
Feature activation-4.50e-02

Pos logit contributions
stab+0.002
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.001
 vac-0.001
NJ-0.001
Token that
Token ID326
Feature activation-1.05e-02

Pos logit contributions
stab+0.034
achelor+0.031
RED+0.031
ifiable+0.030
 Brah+0.030
Neg logit contributions
amental-0.029
enders-0.029
 vac-0.026
vas-0.026
NJ-0.026
Token Brah
Token ID36415
Feature activation-5.35e-01

Pos logit contributions
stab+0.004
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.010
enders-0.010
vas-0.010
 vac-0.010
NJ-0.010
Tokenms
Token ID907
Feature activation-2.33e-01

Pos logit contributions
stab+0.227
achelor+0.188
RED+0.187
 Brah+0.186
ifiable+0.185
Neg logit contributions
amental-0.521
enders-0.516
 vac-0.486
NJ-0.485
 expiration-0.484
Token slaughtered
Token ID33850
Feature activation-1.34e-01

Pos logit contributions
stab+0.177
RED+0.160
achelor+0.160
ifiable+0.159
 Brah+0.159
Neg logit contributions
amental-0.149
enders-0.148
vas-0.134
 vac-0.134
NJ-0.133
Token fel
Token ID10756
Feature activation+6.11e-02

Pos logit contributions
stab+0.100
achelor+0.091
RED+0.091
ifiable+0.090
 Brah+0.089
Neg logit contributions
amental-0.087
enders-0.086
vas-0.078
 vac-0.078
NJ-0.078
Tokenines
Token ID1127
Feature activation+7.51e-02

Pos logit contributions
amental+0.033
enders+0.032
vas+0.029
 vac+0.029
NJ+0.029
Neg logit contributions
stab-0.053
RED-0.048
achelor-0.048
 Brah-0.048
ifiable-0.048
Token,
Token ID11
Feature activation-6.48e-03

Pos logit contributions
amental+0.049
enders+0.049
vas+0.044
 vac+0.044
NJ+0.044
Neg logit contributions
stab-0.056
achelor-0.051
RED-0.051
ifiable-0.050
 Brah-0.050
Token explains
Token ID6688
Feature activation-1.93e-02

Pos logit contributions
amental+0.055
enders+0.054
vas+0.049
 vac+0.049
NJ+0.049
Neg logit contributions
stab-0.063
RED-0.057
achelor-0.057
ifiable-0.057
 Brah-0.056
Token that
Token ID326
Feature activation+1.90e-03

Pos logit contributions
stab+0.014
RED+0.013
achelor+0.013
ifiable+0.013
 Brah+0.013
Neg logit contributions
amental-0.013
enders-0.012
vas-0.011
 vac-0.011
NJ-0.011
Token Wagner
Token ID26451
Feature activation-7.87e-02

Pos logit contributions
amental+0.002
enders+0.002
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token never
Token ID1239
Feature activation+8.85e-02

Pos logit contributions
stab+0.060
RED+0.055
achelor+0.055
ifiable+0.054
 Brah+0.054
Neg logit contributions
amental-0.050
enders-0.049
vas-0.045
 vac-0.045
NJ-0.044
Token visited
Token ID8672
Feature activation+8.16e-02

Pos logit contributions
amental+0.056
enders+0.055
vas+0.050
 vac+0.050
NJ+0.050
Neg logit contributions
stab-0.068
achelor-0.062
RED-0.061
ifiable-0.061
 Brah-0.061
Token Brah
Token ID36415
Feature activation-5.33e-01

Pos logit contributions
amental+0.071
enders+0.071
 vac+0.066
vas+0.066
NJ+0.066
Neg logit contributions
stab-0.043
achelor-0.037
RED-0.037
ifiable-0.036
 Brah-0.036
Tokenms
Token ID907
Feature activation-2.37e-01

Pos logit contributions
stab+0.229
achelor+0.190
RED+0.190
ifiable+0.187
 Brah+0.186
Neg logit contributions
amental-0.517
enders-0.512
 vac-0.482
NJ-0.481
vas-0.481
Token's
Token ID338
Feature activation+5.65e-02

Pos logit contributions
stab+0.187
achelor+0.170
RED+0.170
ifiable+0.169
 Brah+0.168
Neg logit contributions
amental-0.144
enders-0.142
vas-0.129
 vac-0.128
NJ-0.127
Token flat
Token ID6228
Feature activation-2.17e-01

Pos logit contributions
amental+0.043
enders+0.042
 vac+0.039
vas+0.039
 wax+0.039
Neg logit contributions
stab-0.036
achelor-0.032
RED-0.032
ifiable-0.032
 Brah-0.032
Token,
Token ID11
Feature activation-7.30e-03

Pos logit contributions
stab+0.162
RED+0.146
achelor+0.146
ifiable+0.145
 Brah+0.145
Neg logit contributions
amental-0.141
enders-0.140
vas-0.127
 vac-0.127
NJ-0.126
Token so
Token ID523
Feature activation-5.15e-02

Pos logit contributions
stab+0.005
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.005
enders-0.005
vas-0.004
 vac-0.004
NJ-0.004
Token<|endoftext|>
Token ID50256
Feature activation-1.77e-01

Pos logit contributions
amental+0.002
enders+0.002
vas+0.002
 vac+0.002
NJ+0.002
Neg logit contributions
stab-0.002
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.002
TokenJ
Token ID41
Feature activation+1.76e-01

Pos logit contributions
stab+0.131
achelor+0.118
RED+0.118
ifiable+0.117
 Brah+0.117
Neg logit contributions
amental-0.117
enders-0.116
vas-0.106
 vac-0.105
NJ-0.105
Tokenoh
Token ID1219
Feature activation-1.83e-01

Pos logit contributions
amental+0.123
enders+0.123
vas+0.112
NJ+0.112
 vac+0.111
Neg logit contributions
stab-0.123
RED-0.111
achelor-0.110
ifiable-0.110
 Brah-0.109
Tokenann
Token ID1236
Feature activation+9.39e-02

Pos logit contributions
stab+0.151
achelor+0.138
RED+0.138
ifiable+0.137
 Brah+0.136
Neg logit contributions
amental-0.106
enders-0.105
vas-0.094
 vac-0.093
NJ-0.093
Tokenes
Token ID274
Feature activation-1.19e-01

Pos logit contributions
amental+0.071
enders+0.071
vas+0.065
 vac+0.065
NJ+0.065
Neg logit contributions
stab-0.060
RED-0.053
achelor-0.053
ifiable-0.052
 Brah-0.052
Token Brah
Token ID36415
Feature activation-5.33e-01

Pos logit contributions
stab+0.068
achelor+0.060
RED+0.060
ifiable+0.059
 Brah+0.058
Neg logit contributions
amental-0.098
enders-0.098
vas-0.091
 vac-0.091
NJ-0.090
Tokenms
Token ID907
Feature activation-2.40e-01

Pos logit contributions
stab+0.255
RED+0.218
achelor+0.218
ifiable+0.214
 Brah+0.211
Neg logit contributions
enders-0.491
amental-0.488
vas-0.458
NJ-0.453
 vac-0.453
Token,
Token ID11
Feature activation-9.85e-03

Pos logit contributions
stab+0.181
achelor+0.164
RED+0.164
ifiable+0.163
 Brah+0.162
Neg logit contributions
amental-0.155
enders-0.154
vas-0.139
 vac-0.139
NJ-0.138
Token be
Token ID307
Feature activation+1.96e-02

Pos logit contributions
stab+0.007
achelor+0.007
RED+0.007
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.007
enders-0.007
vas-0.006
 vac-0.006
NJ-0.006
Tokenwh
Token ID1929
Feature activation+2.05e-02

Pos logit contributions
amental+0.012
enders+0.012
vas+0.010
 vac+0.010
NJ+0.010
Neg logit contributions
stab-0.016
RED-0.014
achelor-0.014
 Brah-0.014
ifiable-0.014
Tokenis
Token ID271
Feature activation-2.48e-01

Pos logit contributions
amental+0.016
enders+0.016
vas+0.015
 vac+0.015
eper+0.015
Neg logit contributions
stab-0.013
RED-0.011
achelor-0.011
 Brah-0.011
ifiable-0.011
Token presumably
Token ID14572
Feature activation+3.62e-02

Pos logit contributions
stab+0.004
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
 vac-0.004
vas-0.004
 wax-0.004
Token have
Token ID423
Feature activation-5.62e-02

Pos logit contributions
amental+0.025
enders+0.025
 vac+0.023
vas+0.023
 wax+0.022
Neg logit contributions
stab-0.026
RED-0.023
achelor-0.023
ifiable-0.023
 Brah-0.023
Token to
Token ID284
Feature activation+4.17e-03

Pos logit contributions
stab+0.044
achelor+0.040
RED+0.040
ifiable+0.039
 Brah+0.039
Neg logit contributions
amental-0.035
enders-0.034
vas-0.031
 vac-0.031
NJ-0.031
Token have
Token ID423
Feature activation-5.69e-02

Pos logit contributions
amental+0.003
enders+0.003
 vac+0.003
vas+0.003
 wax+0.003
Neg logit contributions
stab-0.003
RED-0.003
achelor-0.003
ifiable-0.003
 Brah-0.003
Token given
Token ID1813
Feature activation+1.98e-01

Pos logit contributions
stab+0.045
RED+0.041
achelor+0.041
ifiable+0.041
 Brah+0.041
Neg logit contributions
amental-0.035
enders-0.034
vas-0.031
 vac-0.031
NJ-0.031
Token Brah
Token ID36415
Feature activation-5.31e-01

Pos logit contributions
amental+0.179
enders+0.178
 vac+0.166
vas+0.166
NJ+0.165
Neg logit contributions
stab-0.097
achelor-0.084
RED-0.084
ifiable-0.082
 Brah-0.080
Tokenms
Token ID907
Feature activation-2.27e-01

Pos logit contributions
stab+0.229
RED+0.190
achelor+0.190
ifiable+0.187
 Brah+0.187
Neg logit contributions
amental-0.515
enders-0.510
 vac-0.480
vas-0.479
NJ-0.478
Token the
Token ID262
Feature activation-4.16e-03

Pos logit contributions
stab+0.160
achelor+0.144
RED+0.144
ifiable+0.142
 Brah+0.142
Neg logit contributions
amental-0.157
enders-0.155
 vac-0.142
vas-0.142
NJ-0.141
Token bow
Token ID9563
Feature activation+1.38e-01

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.002
 wax-0.002
vas-0.002
Token in
Token ID287
Feature activation-6.26e-03

Pos logit contributions
amental+0.092
enders+0.091
vas+0.083
 vac+0.083
NJ+0.082
Neg logit contributions
stab-0.101
achelor-0.091
RED-0.091
ifiable-0.090
 Brah-0.090
Token person
Token ID1048
Feature activation+3.00e-02

Pos logit contributions
stab+0.005
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
 vac-0.004
vas-0.004
 wax-0.004
Token a
Token ID257
Feature activation+9.24e-03

Pos logit contributions
stab+0.081
achelor+0.074
RED+0.074
ifiable+0.073
 Brah+0.072
Neg logit contributions
amental-0.075
enders-0.075
 vac-0.068
vas-0.068
NJ-0.067
Token very
Token ID845
Feature activation+1.52e-02

Pos logit contributions
amental+0.006
enders+0.006
 vac+0.005
vas+0.005
NJ+0.005
Neg logit contributions
stab-0.007
achelor-0.006
RED-0.006
ifiable-0.006
 Brah-0.006
Token limited
Token ID3614
Feature activation+1.40e-01

Pos logit contributions
amental+0.010
enders+0.010
vas+0.009
NJ+0.009
eper+0.009
Neg logit contributions
stab-0.011
RED-0.010
achelor-0.010
 Brah-0.010
ifiable-0.010
Token time
Token ID640
Feature activation-5.48e-02

Pos logit contributions
amental+0.093
enders+0.092
 vac+0.084
vas+0.084
 wax+0.084
Neg logit contributions
stab-0.103
achelor-0.093
RED-0.093
ifiable-0.091
 Brah-0.091
Token for
Token ID329
Feature activation-1.33e-02

Pos logit contributions
stab+0.041
achelor+0.037
RED+0.037
ifiable+0.037
 Brah+0.037
Neg logit contributions
amental-0.035
enders-0.035
vas-0.032
 vac-0.031
NJ-0.031
Token Brah
Token ID36415
Feature activation-5.31e-01

Pos logit contributions
stab+0.008
achelor+0.007
RED+0.007
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.011
enders-0.011
 vac-0.010
vas-0.010
NJ-0.010
Tokenms
Token ID907
Feature activation-2.30e-01

Pos logit contributions
stab+0.229
RED+0.190
achelor+0.190
ifiable+0.187
 Brah+0.187
Neg logit contributions
amental-0.514
enders-0.509
 vac-0.479
vas-0.478
NJ-0.478
Token to
Token ID284
Feature activation+8.70e-03

Pos logit contributions
stab+0.175
achelor+0.159
RED+0.159
ifiable+0.157
 Brah+0.157
Neg logit contributions
amental-0.147
enders-0.146
vas-0.132
 vac-0.132
NJ-0.131
Token become
Token ID1716
Feature activation+1.24e-01

Pos logit contributions
amental+0.006
enders+0.006
 vac+0.005
vas+0.005
 wax+0.005
Neg logit contributions
stab-0.006
achelor-0.006
RED-0.006
ifiable-0.006
 Brah-0.006
Token an
Token ID281
Feature activation-5.29e-02

Pos logit contributions
amental+0.082
enders+0.081
 vac+0.074
vas+0.074
 wax+0.074
Neg logit contributions
stab-0.090
achelor-0.082
RED-0.082
ifiable-0.081
 Brah-0.080
Token expert
Token ID5887
Feature activation+1.28e-01

Pos logit contributions
stab+0.039
achelor+0.035
RED+0.035
 Brah+0.035
ifiable+0.035
Neg logit contributions
amental-0.035
enders-0.035
vas-0.032
 vac-0.032
NJ-0.032
Token.
Token ID13
Feature activation-9.77e-03

Pos logit contributions
stab+0.051
achelor+0.046
RED+0.046
ifiable+0.045
 Brah+0.045
Neg logit contributions
amental-0.045
enders-0.045
vas-0.041
 vac-0.041
NJ-0.040
Token Psycho
Token ID38955
Feature activation+7.52e-02

Pos logit contributions
stab+0.007
RED+0.006
achelor+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.007
enders-0.007
vas-0.006
 vac-0.006
NJ-0.006
Token was
Token ID373
Feature activation-1.62e-03

Pos logit contributions
amental+0.048
enders+0.048
vas+0.043
 vac+0.043
NJ+0.043
Neg logit contributions
stab-0.057
achelor-0.052
RED-0.052
ifiable-0.051
 Brah-0.051
Token a
Token ID257
Feature activation+2.70e-03

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token cert
Token ID5051
Feature activation+9.76e-02

Pos logit contributions
amental+0.002
enders+0.002
vas+0.002
 vac+0.002
NJ+0.002
Neg logit contributions
stab-0.002
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.002
Tokenifiable
Token ID16823
Feature activation-5.30e-01

Pos logit contributions
amental+0.102
enders+0.101
 vac+0.096
eper+0.095
vas+0.095
Neg logit contributions
stab-0.034
achelor-0.027
RED-0.027
 Brah-0.026
-0.024
Token smash
Token ID24273
Feature activation-2.94e-02

Pos logit contributions
stab+0.370
achelor+0.334
RED+0.333
 Brah+0.328
ifiable+0.328
Neg logit contributions
amental-0.371
enders-0.368
 vac-0.337
vas-0.337
NJ-0.335
Token,
Token ID11
Feature activation-4.39e-03

Pos logit contributions
stab+0.021
RED+0.019
achelor+0.019
ifiable+0.019
 Brah+0.019
Neg logit contributions
amental-0.020
enders-0.020
 vac-0.018
vas-0.018
NJ-0.018
Tokenand
Token ID392
Feature activation-8.06e-02

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.003
vas-0.003
NJ-0.003
Token he
Token ID339
Feature activation+4.83e-03

Pos logit contributions
stab+0.058
achelor+0.052
RED+0.052
ifiable+0.052
 Brah+0.052
Neg logit contributions
amental-0.055
enders-0.054
vas-0.049
 vac-0.049
NJ-0.049
Token ended
Token ID4444
Feature activation+2.76e-01

Pos logit contributions
amental+0.003
enders+0.003
vas+0.003
 vac+0.003
NJ+0.003
Neg logit contributions
stab-0.004
achelor-0.003
RED-0.003
ifiable-0.003
 Brah-0.003
Token to
Token ID284
Feature activation-1.67e-03

Pos logit contributions
amental+0.048
enders+0.047
vas+0.043
 vac+0.043
NJ+0.042
Neg logit contributions
stab-0.061
RED-0.055
achelor-0.055
 Brah-0.055
ifiable-0.055
Token Wagner
Token ID26451
Feature activation-7.01e-02

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token,
Token ID11
Feature activation-1.16e-02

Pos logit contributions
stab+0.054
achelor+0.049
RED+0.049
ifiable+0.048
 Brah+0.048
Neg logit contributions
amental-0.044
enders-0.044
vas-0.040
 vac-0.040
NJ-0.040
Token who
Token ID508
Feature activation+3.08e-02

Pos logit contributions
stab+0.005
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.011
enders-0.011
 vac-0.011
vas-0.011
NJ-0.010
Token disliked
Token ID43252
Feature activation-1.77e-01

Pos logit contributions
amental+0.019
enders+0.019
vas+0.017
 vac+0.017
NJ+0.017
Neg logit contributions
stab-0.024
achelor-0.022
RED-0.022
ifiable-0.021
 Brah-0.021
Token Brah
Token ID36415
Feature activation-5.30e-01

Pos logit contributions
stab+0.113
achelor+0.100
RED+0.100
ifiable+0.099
 Brah+0.099
Neg logit contributions
amental-0.135
enders-0.134
vas-0.123
 vac-0.123
NJ-0.123
Tokenms
Token ID907
Feature activation-2.41e-01

Pos logit contributions
stab+0.231
achelor+0.193
RED+0.193
ifiable+0.190
 Brah+0.189
Neg logit contributions
amental-0.510
enders-0.506
 vac-0.475
vas-0.475
NJ-0.474
Token,
Token ID11
Feature activation-6.38e-03

Pos logit contributions
stab+0.181
RED+0.164
achelor+0.164
ifiable+0.162
 Brah+0.162
Neg logit contributions
amental-0.155
enders-0.154
vas-0.140
 vac-0.139
NJ-0.139
Token he
Token ID339
Feature activation+7.28e-03

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.006
enders-0.006
 vac-0.006
vas-0.006
NJ-0.006
Token worked
Token ID3111
Feature activation-4.79e-03

Pos logit contributions
amental+0.005
enders+0.005
vas+0.004
 vac+0.004
NJ+0.004
Neg logit contributions
stab-0.005
RED-0.005
achelor-0.005
ifiable-0.005
 Brah-0.005
Token these
Token ID777
Feature activation+4.63e-02

Pos logit contributions
stab+0.004
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Token.
Token ID13
Feature activation-8.87e-03

Pos logit contributions
stab+0.018
achelor+0.016
RED+0.016
ifiable+0.016
 Brah+0.016
Neg logit contributions
amental-0.016
enders-0.016
vas-0.015
NJ-0.015
 vac-0.015
Token D
Token ID360
Feature activation-4.56e-02

Pos logit contributions
stab+0.007
achelor+0.006
RED+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.006
enders-0.006
vas-0.005
 vac-0.005
NJ-0.005
Tokenvor
Token ID20867
Feature activation+1.21e-01

Pos logit contributions
stab+0.041
achelor+0.038
RED+0.037
ifiable+0.037
 Brah+0.037
Neg logit contributions
amental-0.023
enders-0.023
 vac-0.020
vas-0.020
 expiration-0.020
Tokenak
Token ID461
Feature activation+8.03e-02

Pos logit contributions
amental+0.066
enders+0.065
 vac+0.058
NJ+0.058
vas+0.058
Neg logit contributions
stab-0.103
achelor-0.094
RED-0.094
ifiable-0.093
 Brah-0.093
Token and
Token ID290
Feature activation-6.58e-03

Pos logit contributions
amental+0.050
enders+0.049
vas+0.045
 vac+0.045
NJ+0.044
Neg logit contributions
stab-0.062
achelor-0.057
RED-0.057
ifiable-0.056
 Brah-0.056
Token Brah
Token ID36415
Feature activation-5.29e-01

Pos logit contributions
stab+0.004
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.005
enders-0.005
vas-0.005
 vac-0.005
NJ-0.005
Tokenms
Token ID907
Feature activation-2.35e-01

Pos logit contributions
stab+0.229
RED+0.190
achelor+0.190
 Brah+0.187
ifiable+0.187
Neg logit contributions
amental-0.512
enders-0.507
 vac-0.477
vas-0.476
NJ-0.476
Token met
Token ID1138
Feature activation-2.92e-02

Pos logit contributions
stab+0.180
achelor+0.164
RED+0.164
ifiable+0.162
 Brah+0.161
Neg logit contributions
amental-0.148
enders-0.147
vas-0.133
 vac-0.133
NJ-0.132
Token in
Token ID287
Feature activation-8.31e-03

Pos logit contributions
stab+0.022
achelor+0.020
RED+0.020
ifiable+0.020
 Brah+0.020
Neg logit contributions
amental-0.019
enders-0.019
vas-0.017
 vac-0.017
NJ-0.017
Token 1880
Token ID34865
Feature activation-1.44e-01

Pos logit contributions
stab+0.006
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.006
enders-0.006
 vac-0.005
vas-0.005
 wax-0.005
Token,
Token ID11
Feature activation+9.27e-04

Pos logit contributions
stab+0.108
achelor+0.098
RED+0.098
ifiable+0.097
 Brah+0.096
Neg logit contributions
amental-0.094
enders-0.093
vas-0.084
 vac-0.084
NJ-0.084
Token submit
Token ID9199
Feature activation-2.40e-02

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
 Brah+0.000
ifiable+0.000
Neg logit contributions
amental-0.000
enders-0.000
 vac-0.000
vas-0.000
 wax-0.000
Token the
Token ID262
Feature activation-3.28e-03

Pos logit contributions
stab+0.018
achelor+0.016
RED+0.016
ifiable+0.016
 Brah+0.016
Neg logit contributions
amental-0.016
enders-0.016
vas-0.014
 vac-0.014
NJ-0.014
Token required
Token ID2672
Feature activation-9.15e-02

Pos logit contributions
stab+0.002
RED+0.002
achelor+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
 vac-0.002
vas-0.002
NJ-0.002
Token and
Token ID290
Feature activation+5.37e-03

Pos logit contributions
stab+0.068
RED+0.061
achelor+0.061
ifiable+0.060
 Brah+0.060
Neg logit contributions
amental-0.060
enders-0.060
 vac-0.055
vas-0.055
NJ-0.054
Token ver
Token ID3326
Feature activation+8.29e-02

Pos logit contributions
amental+0.003
enders+0.003
vas+0.003
 vac+0.003
NJ+0.003
Neg logit contributions
stab-0.004
achelor-0.004
RED-0.004
ifiable-0.004
 Brah-0.004
Tokenifiable
Token ID16823
Feature activation-5.28e-01

Pos logit contributions
amental+0.108
enders+0.107
vas+0.102
 vac+0.102
eper+0.102
Neg logit contributions
stab-0.008
achelor-0.003
RED-0.002
 Brah-0.002
ifiable-0.000
Token registration
Token ID9352
Feature activation+1.03e-01

Pos logit contributions
stab+0.396
achelor+0.359
RED+0.359
ifiable+0.357
 Brah+0.356
Neg logit contributions
amental-0.342
enders-0.339
vas-0.308
 vac-0.306
NJ-0.305
Token information
Token ID1321
Feature activation-2.81e-02

Pos logit contributions
amental+0.067
enders+0.067
 vac+0.061
vas+0.061
NJ+0.060
Neg logit contributions
stab-0.076
achelor-0.069
RED-0.069
 Brah-0.068
ifiable-0.068
Token prior
Token ID3161
Feature activation+3.32e-02

Pos logit contributions
stab+0.021
achelor+0.019
RED+0.019
ifiable+0.018
 Brah+0.018
Neg logit contributions
amental-0.019
enders-0.019
vas-0.017
 vac-0.017
NJ-0.017
Token to
Token ID284
Feature activation+9.39e-03

Pos logit contributions
amental+0.022
enders+0.022
vas+0.020
 vac+0.020
NJ+0.020
Neg logit contributions
stab-0.025
achelor-0.022
RED-0.022
ifiable-0.022
 Brah-0.022
Token the
Token ID262
Feature activation+1.63e-05

Pos logit contributions
amental+0.006
enders+0.006
vas+0.006
NJ+0.006
 vac+0.006
Neg logit contributions
stab-0.007
achelor-0.006
RED-0.006
ifiable-0.006
 Brah-0.006
Tokenins
Token ID1040
Feature activation+1.59e-01

Pos logit contributions
stab+0.090
achelor+0.081
RED+0.081
ifiable+0.080
 Brah+0.080
Neg logit contributions
amental-0.083
enders-0.082
 vac-0.075
vas-0.075
NJ-0.074
Token,
Token ID11
Feature activation+1.24e-03

Pos logit contributions
amental+0.106
enders+0.105
vas+0.096
 vac+0.096
NJ+0.095
Neg logit contributions
stab-0.117
RED-0.106
achelor-0.106
ifiable-0.104
 Brah-0.103
Token editor
Token ID5464
Feature activation-5.72e-02

Pos logit contributions
amental+0.001
enders+0.001
 vac+0.001
vas+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token of
Token ID286
Feature activation-6.30e-03

Pos logit contributions
stab+0.042
achelor+0.038
RED+0.038
ifiable+0.037
 Brah+0.037
Neg logit contributions
amental-0.038
enders-0.038
vas-0.035
 vac-0.035
NJ-0.034
Token Johannes
Token ID38579
Feature activation-2.25e-02

Pos logit contributions
stab+0.005
RED+0.004
achelor+0.004
 Brah+0.004
ifiable+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Token Brah
Token ID36415
Feature activation-5.25e-01

Pos logit contributions
stab+0.008
achelor+0.006
RED+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.023
enders-0.023
vas-0.022
 vac-0.022
NJ-0.022
Tokenms
Token ID907
Feature activation-2.30e-01

Pos logit contributions
stab+0.233
achelor+0.196
RED+0.195
 Brah+0.193
ifiable+0.192
Neg logit contributions
amental-0.501
enders-0.498
 vac-0.468
vas-0.467
NJ-0.465
Token:
Token ID25
Feature activation+4.53e-02

Pos logit contributions
stab+0.178
achelor+0.162
RED+0.162
 Brah+0.161
ifiable+0.160
Neg logit contributions
amental-0.144
enders-0.142
vas-0.129
 vac-0.129
NJ-0.128
Token Life
Token ID5155
Feature activation-1.85e-01

Pos logit contributions
amental+0.030
enders+0.029
vas+0.027
 vac+0.027
NJ+0.027
Neg logit contributions
stab-0.034
achelor-0.030
RED-0.030
ifiable-0.030
 Brah-0.030
Token and
Token ID290
Feature activation+2.86e-03

Pos logit contributions
stab+0.139
achelor+0.126
RED+0.126
ifiable+0.125
 Brah+0.125
Neg logit contributions
amental-0.119
enders-0.118
vas-0.107
 vac-0.107
NJ-0.106
Token Letters
Token ID24501
Feature activation-1.91e-01

Pos logit contributions
amental+0.002
enders+0.002
vas+0.002
 vac+0.002
NJ+0.002
Neg logit contributions
stab-0.002
RED-0.002
achelor-0.002
 Brah-0.002
ifiable-0.002
Token that
Token ID326
Feature activation+5.73e-03

Pos logit contributions
amental+0.070
enders+0.070
vas+0.064
 vac+0.064
NJ+0.063
Neg logit contributions
stab-0.079
achelor-0.072
RED-0.072
ifiable-0.071
 Brah-0.070
Token in
Token ID287
Feature activation+2.06e-03

Pos logit contributions
amental+0.005
enders+0.005
 vac+0.005
vas+0.005
NJ+0.004
Neg logit contributions
stab-0.003
achelor-0.003
RED-0.003
ifiable-0.003
 Brah-0.003
Token 1893
Token ID48889
Feature activation-2.47e-01

Pos logit contributions
amental+0.002
enders+0.002
vas+0.001
 vac+0.001
 wax+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token -
Token ID532
Feature activation+1.54e-01

Pos logit contributions
stab+0.145
achelor+0.128
RED+0.128
ifiable+0.126
 Brah+0.123
Neg logit contributions
amental-0.201
enders-0.199
vas-0.185
 vac-0.185
NJ-0.184
Token when
Token ID618
Feature activation-1.15e-02

Pos logit contributions
amental+0.103
enders+0.102
vas+0.094
 vac+0.094
NJ+0.093
Neg logit contributions
stab-0.113
achelor-0.102
RED-0.102
ifiable-0.101
 Brah-0.099
Token Brah
Token ID36415
Feature activation-5.24e-01

Pos logit contributions
stab+0.006
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.010
enders-0.010
 vac-0.009
vas-0.009
NJ-0.009
Tokenms
Token ID907
Feature activation-2.31e-01

Pos logit contributions
stab+0.225
RED+0.187
achelor+0.187
ifiable+0.184
 Brah+0.184
Neg logit contributions
amental-0.508
enders-0.503
 vac-0.473
vas-0.472
NJ-0.472
Token was
Token ID373
Feature activation+8.87e-04

Pos logit contributions
stab+0.179
achelor+0.163
RED+0.163
 Brah+0.161
ifiable+0.161
Neg logit contributions
amental-0.143
enders-0.142
vas-0.128
 vac-0.128
NJ-0.128
Token still
Token ID991
Feature activation-1.83e-01

Pos logit contributions
amental+0.001
enders+0.001
 vac+0.001
vas+0.001
 wax+0.001
Neg logit contributions
stab-0.001
RED-0.001
achelor-0.001
ifiable-0.001
 Brah-0.001
Token alive
Token ID6776
Feature activation+6.34e-02

Pos logit contributions
stab+0.136
RED+0.123
achelor+0.123
ifiable+0.122
 Brah+0.121
Neg logit contributions
amental-0.120
enders-0.119
 vac-0.109
vas-0.109
NJ-0.108
Token -
Token ID532
Feature activation+1.60e-01

Pos logit contributions
amental+0.031
enders+0.030
vas+0.027
 vac+0.026
NJ+0.026
Neg logit contributions
stab-0.058
achelor-0.054
RED-0.054
ifiable-0.053
 Brah-0.053
Token 1996
Token ID8235
Feature activation-2.32e-01

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token,
Token ID11
Feature activation+2.02e-03

Pos logit contributions
stab+0.175
achelor+0.158
RED+0.158
ifiable+0.157
 Brah+0.156
Neg logit contributions
amental-0.150
enders-0.149
vas-0.135
 vac-0.135
NJ-0.134
Token which
Token ID543
Feature activation-4.52e-02

Pos logit contributions
amental+0.001
enders+0.001
 vac+0.001
vas+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token claims
Token ID3667
Feature activation+5.60e-02

Pos logit contributions
stab+0.034
achelor+0.031
RED+0.031
ifiable+0.031
 Brah+0.031
Neg logit contributions
amental-0.029
enders-0.029
vas-0.026
 vac-0.026
NJ-0.026
Token that
Token ID326
Feature activation-3.01e-04

Pos logit contributions
amental+0.039
enders+0.039
vas+0.035
 vac+0.035
NJ+0.035
Neg logit contributions
stab-0.039
achelor-0.035
RED-0.035
ifiable-0.035
 Brah-0.035
Token Brah
Token ID36415
Feature activation-5.24e-01

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
 vac-0.000
vas-0.000
NJ-0.000
Tokenms
Token ID907
Feature activation-2.33e-01

Pos logit contributions
stab+0.225
RED+0.187
achelor+0.187
ifiable+0.184
 Brah+0.183
Neg logit contributions
amental-0.508
enders-0.504
 vac-0.474
NJ-0.472
vas-0.472
Token began
Token ID2540
Feature activation+5.88e-02

Pos logit contributions
stab+0.172
RED+0.156
achelor+0.156
ifiable+0.154
 Brah+0.154
Neg logit contributions
amental-0.153
enders-0.152
vas-0.138
 vac-0.138
NJ-0.137
Token cat
Token ID3797
Feature activation-9.10e-02

Pos logit contributions
amental+0.041
enders+0.041
vas+0.037
NJ+0.037
 vac+0.037
Neg logit contributions
stab-0.041
RED-0.037
achelor-0.037
ifiable-0.037
 Brah-0.037
Token bag
Token ID6131
Feature activation+5.84e-02

Pos logit contributions
stab+0.066
achelor+0.059
ifiable+0.059
RED+0.059
 Brah+0.058
Neg logit contributions
amental-0.061
enders-0.061
NJ-0.056
vas-0.056
 vac-0.055
Tokenging
Token ID2667
Feature activation+2.48e-01

Pos logit contributions
amental+0.020
enders+0.020
vas+0.016
 vac+0.016
NJ+0.016
Neg logit contributions
stab-0.062
achelor-0.057
RED-0.057
ifiable-0.057
 Brah-0.057
Token marijuana
Token ID5727
Feature activation+2.16e-01

Pos logit contributions
stab+0.076
achelor+0.069
RED+0.069
ifiable+0.068
 Brah+0.068
Neg logit contributions
amental-0.070
enders-0.070
vas-0.063
 vac-0.063
NJ-0.063
Token.
Token ID13
Feature activation-1.55e-03

Pos logit contributions
amental+0.134
enders+0.133
vas+0.120
 vac+0.120
NJ+0.119
Neg logit contributions
stab-0.168
achelor-0.153
RED-0.153
ifiable-0.151
 Brah-0.151
Token
Token ID198
Feature activation+6.79e-03

Pos logit contributions
stab+0.001
RED+0.001
achelor+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token
Token ID198
Feature activation+1.23e-03

Pos logit contributions
amental+0.004
enders+0.004
vas+0.004
 vac+0.004
NJ+0.004
Neg logit contributions
stab-0.005
RED-0.005
achelor-0.005
ifiable-0.005
 Brah-0.005
TokenH
Token ID39
Feature activation-1.45e-01

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
RED-0.001
achelor-0.001
ifiable-0.001
 Brah-0.001
Tokenemp
Token ID45787
Feature activation-5.23e-01

Pos logit contributions
stab+0.018
achelor+0.008
RED+0.008
ifiable+0.007
 Brah+0.006
Neg logit contributions
amental-0.184
enders-0.183
 vac-0.175
vas-0.175
NJ-0.174
Token Supporters
Token ID39995
Feature activation-1.85e-01

Pos logit contributions
stab+0.388
RED+0.351
achelor+0.351
ifiable+0.347
 Brah+0.347
Neg logit contributions
amental-0.344
enders-0.340
vas-0.310
 vac-0.309
NJ-0.307
Token State
Token ID1812
Feature activation-1.81e-01

Pos logit contributions
stab+0.134
RED+0.121
achelor+0.120
ifiable+0.119
 Brah+0.119
Neg logit contributions
amental-0.125
enders-0.124
vas-0.113
 vac-0.113
NJ-0.112
Token Senators
Token ID22195
Feature activation-2.10e-01

Pos logit contributions
stab+0.127
RED+0.114
achelor+0.114
ifiable+0.113
 Brah+0.113
Neg logit contributions
amental-0.126
enders-0.125
vas-0.115
 vac-0.114
NJ-0.114
Token Russell
Token ID11563
Feature activation-3.23e-02

Pos logit contributions
stab+0.155
RED+0.140
achelor+0.140
ifiable+0.139
 Brah+0.139
Neg logit contributions
amental-0.138
enders-0.137
vas-0.124
 vac-0.124
NJ-0.123
Token Rud
Token ID17421
Feature activation-9.34e-02

Pos logit contributions
stab+0.023
achelor+0.020
RED+0.020
 Brah+0.020
ifiable+0.020
Neg logit contributions
amental-0.023
enders-0.022
vas-0.021
 vac-0.021
NJ-0.020
Token he
Token ID339
Feature activation+1.32e-02

Pos logit contributions
amental+0.002
enders+0.002
 vac+0.001
vas+0.001
NJ+0.001
Neg logit contributions
stab-0.002
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.001
Token notes
Token ID4710
Feature activation+3.73e-04

Pos logit contributions
amental+0.008
enders+0.008
vas+0.008
 vac+0.008
NJ+0.008
Neg logit contributions
stab-0.010
RED-0.009
achelor-0.009
ifiable-0.009
 Brah-0.009
Token that
Token ID326
Feature activation+2.67e-03

Pos logit contributions
amental+0.000
enders+0.000
 vac+0.000
vas+0.000
NJ+0.000
Neg logit contributions
stab-0.000
achelor-0.000
RED-0.000
ifiable-0.000
 Brah-0.000
Token stories
Token ID3923
Feature activation+9.09e-02

Pos logit contributions
amental+0.002
enders+0.002
 vac+0.002
vas+0.002
 wax+0.002
Neg logit contributions
stab-0.002
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.002
Token of
Token ID286
Feature activation-2.94e-03

Pos logit contributions
amental+0.059
enders+0.059
vas+0.053
 vac+0.053
NJ+0.053
Neg logit contributions
stab-0.068
RED-0.061
achelor-0.061
ifiable-0.061
 Brah-0.061
Token Brah
Token ID36415
Feature activation-5.23e-01

Pos logit contributions
stab+0.002
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.002
 vac-0.002
NJ-0.002
Tokenms
Token ID907
Feature activation-2.30e-01

Pos logit contributions
stab+0.226
RED+0.188
achelor+0.188
ifiable+0.185
 Brah+0.185
Neg logit contributions
amental-0.506
enders-0.501
 vac-0.471
vas-0.470
NJ-0.469
Token killing
Token ID5170
Feature activation-6.71e-02

Pos logit contributions
stab+0.168
achelor+0.152
RED+0.152
ifiable+0.150
 Brah+0.150
Neg logit contributions
amental-0.153
enders-0.152
vas-0.139
 vac-0.138
NJ-0.138
Token cats
Token ID11875
Feature activation+2.03e-01

Pos logit contributions
stab+0.056
RED+0.052
achelor+0.052
ifiable+0.051
 Brah+0.051
Neg logit contributions
amental-0.037
enders-0.037
vas-0.033
 vac-0.033
NJ-0.033
Token surface
Token ID4417
Feature activation+1.15e-02

Pos logit contributions
amental+0.130
enders+0.129
vas+0.117
 vac+0.117
NJ+0.116
Neg logit contributions
stab-0.154
achelor-0.139
RED-0.139
ifiable-0.138
 Brah-0.138
Token mainly
Token ID8384
Feature activation+5.43e-02

Pos logit contributions
amental+0.007
enders+0.007
vas+0.006
 vac+0.006
NJ+0.006
Neg logit contributions
stab-0.009
RED-0.008
achelor-0.008
ifiable-0.008
 Brah-0.008
Token groundwork
Token ID40641
Feature activation-1.55e-01

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.002
vas-0.002
 expiration-0.002
Token to
Token ID284
Feature activation+8.82e-03

Pos logit contributions
stab+0.114
achelor+0.103
RED+0.102
ifiable+0.101
 Brah+0.101
Neg logit contributions
amental-0.103
enders-0.102
vas-0.093
 vac-0.093
NJ-0.092
Token make
Token ID787
Feature activation+2.78e-02

Pos logit contributions
amental+0.006
enders+0.006
 vac+0.005
vas+0.005
 wax+0.005
Neg logit contributions
stab-0.007
achelor-0.006
RED-0.006
ifiable-0.006
 Brah-0.006
Token them
Token ID606
Feature activation+5.83e-02

Pos logit contributions
amental+0.018
enders+0.018
vas+0.016
 vac+0.016
NJ+0.016
Neg logit contributions
stab-0.021
RED-0.019
achelor-0.019
ifiable-0.019
 Brah-0.019
Token just
Token ID655
Feature activation+3.81e-02

Pos logit contributions
amental+0.039
enders+0.039
vas+0.035
 vac+0.035
NJ+0.035
Neg logit contributions
stab-0.043
achelor-0.039
RED-0.039
 Brah-0.038
ifiable-0.038
Tokenifiable
Token ID16823
Feature activation-5.18e-01

Pos logit contributions
amental+0.027
enders+0.027
vas+0.024
 vac+0.024
NJ+0.024
Neg logit contributions
stab-0.027
achelor-0.024
RED-0.024
ifiable-0.024
 Brah-0.023
Token.
Token ID13
Feature activation+1.01e-02

Pos logit contributions
stab+0.386
achelor+0.349
RED+0.348
ifiable+0.344
 Brah+0.344
Neg logit contributions
amental-0.339
enders-0.337
vas-0.306
 vac-0.305
NJ-0.304
Token Thanks
Token ID6930
Feature activation-3.28e-02

Pos logit contributions
amental+0.007
enders+0.007
vas+0.006
 vac+0.006
NJ+0.006
Neg logit contributions
stab-0.007
achelor-0.007
RED-0.007
ifiable-0.007
 Brah-0.007
Token for
Token ID329
Feature activation+2.53e-03

Pos logit contributions
stab+0.024
achelor+0.022
RED+0.022
ifiable+0.022
 Brah+0.022
Neg logit contributions
amental-0.022
enders-0.021
vas-0.020
 vac-0.019
NJ-0.019
Token your
Token ID534
Feature activation+8.81e-02

Pos logit contributions
amental+0.002
enders+0.002
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.002
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.002
Token time
Token ID640
Feature activation-2.93e-02

Pos logit contributions
amental+0.060
enders+0.060
 vac+0.055
vas+0.055
NJ+0.054
Neg logit contributions
stab-0.063
achelor-0.057
RED-0.057
ifiable-0.056
 Brah-0.056
Token,
Token ID11
Feature activation-1.12e-02

Pos logit contributions
stab+0.006
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.005
enders-0.005
vas-0.004
 vac-0.004
NJ-0.004
Token Brian
Token ID8403
Feature activation-2.41e-02

Pos logit contributions
stab+0.008
achelor+0.007
RED+0.007
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.007
enders-0.007
vas-0.007
 vac-0.007
NJ-0.007
Token Todd
Token ID14377
Feature activation+7.44e-02

Pos logit contributions
stab+0.014
RED+0.012
achelor+0.012
ifiable+0.012
 Brah+0.012
Neg logit contributions
amental-0.020
enders-0.020
vas-0.018
 vac-0.018
NJ-0.018
Token,
Token ID11
Feature activation-1.31e-02

Pos logit contributions
amental+0.048
enders+0.047
vas+0.043
 vac+0.043
NJ+0.042
Neg logit contributions
stab-0.056
RED-0.051
achelor-0.051
ifiable-0.051
 Brah-0.050
Token Jason
Token ID8982
Feature activation+1.24e-01

Pos logit contributions
stab+0.010
achelor+0.009
RED+0.009
ifiable+0.009
 Brah+0.009
Neg logit contributions
amental-0.009
enders-0.009
vas-0.008
 vac-0.008
NJ-0.008
Token Carroll
Token ID21298
Feature activation-5.10e-01

Pos logit contributions
amental+0.085
enders+0.084
vas+0.077
 vac+0.077
NJ+0.077
Neg logit contributions
stab-0.088
achelor-0.079
RED-0.079
 Brah-0.079
ifiable-0.079
Token,
Token ID11
Feature activation-6.51e-03

Pos logit contributions
stab+0.383
achelor+0.347
RED+0.346
ifiable+0.343
 Brah+0.342
Neg logit contributions
amental-0.331
enders-0.328
vas-0.298
 vac-0.297
NJ-0.296
Token Pete
Token ID17542
Feature activation+4.71e-02

Pos logit contributions
stab+0.005
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Token Ham
Token ID4345
Feature activation+8.76e-02

Pos logit contributions
amental+0.032
enders+0.032
vas+0.030
 vac+0.029
NJ+0.029
Neg logit contributions
stab-0.033
RED-0.030
achelor-0.030
ifiable-0.030
 Brah-0.029
Tokenby
Token ID1525
Feature activation-2.02e-01

Pos logit contributions
amental+0.055
enders+0.054
vas+0.049
 vac+0.049
NJ+0.048
Neg logit contributions
stab-0.068
RED-0.062
achelor-0.062
ifiable-0.061
 Brah-0.061
Token,
Token ID11
Feature activation-1.28e-02

Pos logit contributions
stab+0.153
RED+0.139
achelor+0.139
ifiable+0.138
 Brah+0.137
Neg logit contributions
amental-0.129
enders-0.128
vas-0.117
 vac-0.116
NJ-0.116
Token produced
Token ID4635
Feature activation+1.95e-01

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token by
Token ID416
Feature activation+7.28e-03

Pos logit contributions
amental+0.129
enders+0.128
vas+0.117
 vac+0.116
NJ+0.116
Neg logit contributions
stab-0.144
RED-0.130
achelor-0.130
ifiable-0.129
 Brah-0.129
Token Cub
Token ID7070
Feature activation+1.17e-01

Pos logit contributions
amental+0.005
enders+0.005
vas+0.004
 vac+0.004
NJ+0.004
Neg logit contributions
stab-0.005
achelor-0.005
RED-0.005
ifiable-0.005
 Brah-0.005
Tokenby
Token ID1525
Feature activation-1.90e-01

Pos logit contributions
amental+0.076
enders+0.076
vas+0.069
 vac+0.069
NJ+0.068
Neg logit contributions
stab-0.087
RED-0.079
achelor-0.079
ifiable-0.078
 Brah-0.078
Token Bro
Token ID2806
Feature activation-2.64e-01

Pos logit contributions
stab+0.143
achelor+0.130
RED+0.130
ifiable+0.129
 Brah+0.128
Neg logit contributions
amental-0.122
enders-0.121
vas-0.110
 vac-0.110
NJ-0.109
Tokenccoli
Token ID34544
Feature activation-5.10e-01

Pos logit contributions
stab+0.066
RED+0.050
achelor+0.049
ifiable+0.047
 Brah+0.047
Neg logit contributions
amental-0.302
enders-0.301
vas-0.286
 vac-0.285
eper-0.284
Token or
Token ID393
Feature activation-4.92e-02

Pos logit contributions
stab+0.385
achelor+0.348
RED+0.348
ifiable+0.345
 Brah+0.344
Neg logit contributions
amental-0.329
enders-0.326
vas-0.296
 vac-0.295
NJ-0.294
Token the
Token ID262
Feature activation+2.18e-03

Pos logit contributions
stab+0.035
achelor+0.032
RED+0.032
ifiable+0.032
 Brah+0.032
Neg logit contributions
amental-0.033
enders-0.033
vas-0.030
 vac-0.030
NJ-0.030
Token Bro
Token ID2806
Feature activation-2.65e-01

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.002
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Tokenccoli
Token ID34544
Feature activation-5.06e-01

Pos logit contributions
stab+0.049
RED+0.033
achelor+0.031
ifiable+0.030
 Brah+0.029
Neg logit contributions
amental-0.320
enders-0.320
vas-0.305
 vac-0.303
NJ-0.302
Token family
Token ID1641
Feature activation-1.77e-01

Pos logit contributions
stab+0.351
achelor+0.316
RED+0.316
ifiable+0.312
 Brah+0.311
Neg logit contributions
amental-0.356
enders-0.354
vas-0.324
 vac-0.324
NJ-0.322
Token Bro
Token ID2806
Feature activation-2.64e-01

Pos logit contributions
stab+0.143
achelor+0.130
RED+0.130
ifiable+0.129
 Brah+0.128
Neg logit contributions
amental-0.122
enders-0.121
vas-0.110
 vac-0.110
NJ-0.109
Tokenccoli
Token ID34544
Feature activation-5.10e-01

Pos logit contributions
stab+0.066
RED+0.050
achelor+0.049
ifiable+0.047
 Brah+0.047
Neg logit contributions
amental-0.302
enders-0.301
vas-0.286
 vac-0.285
eper-0.284
Token or
Token ID393
Feature activation-4.92e-02

Pos logit contributions
stab+0.385
achelor+0.348
RED+0.348
ifiable+0.345
 Brah+0.344
Neg logit contributions
amental-0.329
enders-0.326
vas-0.296
 vac-0.295
NJ-0.294
Token the
Token ID262
Feature activation+2.18e-03

Pos logit contributions
stab+0.035
achelor+0.032
RED+0.032
ifiable+0.032
 Brah+0.032
Neg logit contributions
amental-0.033
enders-0.033
vas-0.030
 vac-0.030
NJ-0.030
Token Bro
Token ID2806
Feature activation-2.65e-01

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.002
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Tokenccoli
Token ID34544
Feature activation-5.06e-01

Pos logit contributions
stab+0.049
RED+0.033
achelor+0.031
ifiable+0.030
 Brah+0.029
Neg logit contributions
amental-0.320
enders-0.320
vas-0.305
 vac-0.303
NJ-0.302
Token family
Token ID1641
Feature activation-1.77e-01

Pos logit contributions
stab+0.351
achelor+0.316
RED+0.316
ifiable+0.312
 Brah+0.311
Neg logit contributions
amental-0.356
enders-0.354
vas-0.324
 vac-0.324
NJ-0.322
Token (
Token ID357
Feature activation+7.61e-02

Pos logit contributions
stab+0.132
achelor+0.120
RED+0.120
ifiable+0.119
 Brah+0.118
Neg logit contributions
amental-0.115
enders-0.114
vas-0.104
 vac-0.103
NJ-0.103
TokenE
Token ID36
Feature activation+4.29e-02

Pos logit contributions
amental+0.051
enders+0.051
vas+0.047
 vac+0.046
NJ+0.046
Neg logit contributions
stab-0.055
achelor-0.050
RED-0.050
ifiable-0.049
 Brah-0.049
Tokenon
Token ID261
Feature activation-2.60e-01

Pos logit contributions
amental+0.029
enders+0.029
vas+0.026
 vac+0.026
NJ+0.026
Neg logit contributions
stab-0.031
achelor-0.028
RED-0.028
ifiable-0.028
 Brah-0.028
Token Productions
Token ID25315
Feature activation+2.25e-01

Pos logit contributions
stab+0.193
achelor+0.175
RED+0.174
ifiable+0.172
 Brah+0.172
Neg logit contributions
amental-0.172
enders-0.170
vas-0.155
 vac-0.155
NJ-0.154
Token he
Token ID339
Feature activation+7.07e-03

Pos logit contributions
stab+0.102
achelor+0.092
RED+0.092
ifiable+0.091
 Brah+0.091
Neg logit contributions
amental-0.093
enders-0.092
vas-0.084
 vac-0.084
NJ-0.083
Token met
Token ID1138
Feature activation-2.46e-02

Pos logit contributions
amental+0.004
enders+0.004
vas+0.004
 vac+0.004
NJ+0.004
Neg logit contributions
stab-0.005
achelor-0.005
RED-0.005
ifiable-0.005
 Brah-0.005
Token Cub
Token ID7070
Feature activation+1.07e-01

Pos logit contributions
stab+0.018
achelor+0.016
RED+0.016
ifiable+0.016
 Brah+0.016
Neg logit contributions
amental-0.016
enders-0.016
vas-0.015
 vac-0.015
NJ-0.014
Tokenby
Token ID1525
Feature activation-1.86e-01

Pos logit contributions
amental+0.091
enders+0.091
vas+0.084
 vac+0.084
eper+0.083
Neg logit contributions
stab-0.059
RED-0.052
achelor-0.052
 Brah-0.051
ifiable-0.050
Token Bro
Token ID2806
Feature activation-2.63e-01

Pos logit contributions
stab+0.120
RED+0.107
achelor+0.107
ifiable+0.106
 Brah+0.105
Neg logit contributions
amental-0.139
enders-0.138
 vac-0.128
vas-0.128
NJ-0.127
Tokenccoli
Token ID34544
Feature activation-5.01e-01

Pos logit contributions
stab+0.042
RED+0.027
achelor+0.024
 Brah+0.024
ifiable+0.021
Neg logit contributions
amental-0.324
enders-0.323
vas-0.309
 vac-0.307
eper-0.306
Token:
Token ID25
Feature activation+4.03e-02

Pos logit contributions
stab+0.377
achelor+0.342
RED+0.342
ifiable+0.339
 Brah+0.338
Neg logit contributions
amental-0.322
enders-0.320
vas-0.290
 vac-0.290
NJ-0.288
Token-----
Token ID30934
Feature activation-1.93e-01

Pos logit contributions
amental+0.026
enders+0.026
vas+0.024
 vac+0.024
NJ+0.024
Neg logit contributions
stab-0.030
achelor-0.027
RED-0.027
ifiable-0.027
 Brah-0.027
Token 1954
Token ID24718
Feature activation-8.37e-02

Pos logit contributions
stab+0.141
achelor+0.127
RED+0.127
ifiable+0.126
 Brah+0.125
Neg logit contributions
amental-0.129
enders-0.128
vas-0.116
 vac-0.116
NJ-0.116
Token:
Token ID25
Feature activation+4.35e-02

Pos logit contributions
stab+0.063
achelor+0.057
RED+0.057
ifiable+0.057
 Brah+0.056
Neg logit contributions
amental-0.054
enders-0.054
vas-0.049
 vac-0.049
NJ-0.048
Token "
Token ID366
Feature activation-7.75e-02

Pos logit contributions
amental+0.029
enders+0.029
vas+0.026
 vac+0.026
NJ+0.026
Neg logit contributions
stab-0.032
achelor-0.029
RED-0.029
ifiable-0.029
 Brah-0.028
Token sometimes
Token ID3360
Feature activation-1.45e-02

Pos logit contributions
stab+0.005
RED+0.005
achelor+0.005
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Token Archie
Token ID43459
Feature activation-8.66e-02

Pos logit contributions
stab+0.011
achelor+0.010
RED+0.010
ifiable+0.010
 Brah+0.010
Neg logit contributions
amental-0.009
enders-0.009
vas-0.008
 vac-0.008
NJ-0.008
Token would
Token ID561
Feature activation-2.96e-03

Pos logit contributions
stab+0.064
achelor+0.058
RED+0.058
ifiable+0.058
 Brah+0.057
Neg logit contributions
amental-0.057
enders-0.056
vas-0.051
 vac-0.051
NJ-0.051
Token take
Token ID1011
Feature activation+6.59e-02

Pos logit contributions
stab+0.002
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.002
 vac-0.002
NJ-0.002
Token the
Token ID262
Feature activation-2.57e-03

Pos logit contributions
amental+0.042
enders+0.041
vas+0.037
 vac+0.037
NJ+0.037
Neg logit contributions
stab-0.051
achelor-0.046
RED-0.046
ifiable-0.045
 Brah-0.045
Token session
Token ID6246
Feature activation+3.31e-01

Pos logit contributions
stab+0.002
RED+0.002
achelor+0.002
 Brah+0.002
ifiable+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.001
 vac-0.001
NJ-0.001
Token.
Token ID13
Feature activation-7.61e-03

Pos logit contributions
amental+0.220
enders+0.217
vas+0.198
NJ+0.198
 vac+0.196
Neg logit contributions
stab-0.243
RED-0.219
achelor-0.219
ifiable-0.217
 Brah-0.217
Token You
Token ID921
Feature activation-5.12e-02

Pos logit contributions
stab+0.005
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.005
enders-0.005
vas-0.005
 vac-0.005
NJ-0.005
Token wouldn
Token ID3636
Feature activation+1.24e-01

Pos logit contributions
stab+0.038
RED+0.035
achelor+0.035
 Brah+0.034
ifiable+0.034
Neg logit contributions
amental-0.033
enders-0.033
vas-0.030
NJ-0.030
existent-0.030
Token't
Token ID470
Feature activation-1.03e-01

Pos logit contributions
amental+0.098
enders+0.097
vas+0.090
 vac+0.090
NJ+0.089
Neg logit contributions
stab-0.076
RED-0.067
achelor-0.067
ifiable-0.066
 Brah-0.066
Token ever
Token ID1683
Feature activation-8.66e-02

Pos logit contributions
stab+0.077
achelor+0.069
RED+0.069
ifiable+0.069
 Brah+0.069
Neg logit contributions
amental-0.068
enders-0.067
vas-0.061
NJ-0.061
 vac-0.061
Token.
Token ID13
Feature activation-2.06e-03

Pos logit contributions
stab+0.187
RED+0.169
achelor+0.169
ifiable+0.168
 Brah+0.167
Neg logit contributions
amental-0.166
enders-0.164
vas-0.149
 vac-0.149
NJ-0.148
Token
Token ID198
Feature activation+9.42e-03

Pos logit contributions
stab+0.001
RED+0.001
achelor+0.001
 Brah+0.001
ifiable+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token
Token ID198
Feature activation-4.51e-04

Pos logit contributions
amental+0.006
enders+0.006
vas+0.006
 vac+0.006
NJ+0.006
Neg logit contributions
stab-0.007
RED-0.006
achelor-0.006
ifiable-0.006
 Brah-0.006
TokenR
Token ID49
Feature activation-1.25e-01

Pos logit contributions
stab+0.000
RED+0.000
achelor+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
 vac-0.000
vas-0.000
 wax-0.000
Tokenough
Token ID619
Feature activation+2.74e-02

Pos logit contributions
stab+0.098
achelor+0.089
RED+0.089
ifiable+0.088
 Brah+0.088
Neg logit contributions
amental-0.076
enders-0.075
 vac-0.068
vas-0.068
 wax-0.068
Tokenly
Token ID306
Feature activation+2.81e-01

Pos logit contributions
amental+0.009
enders+0.009
vas+0.008
 vac+0.008
NJ+0.008
Neg logit contributions
stab-0.029
RED-0.027
achelor-0.027
ifiable-0.027
 Brah-0.027
Token 18
Token ID1248
Feature activation-1.54e-01

Pos logit contributions
amental+0.180
enders+0.178
vas+0.162
 vac+0.161
NJ+0.160
Neg logit contributions
stab-0.213
achelor-0.193
RED-0.193
ifiable-0.192
 Brah-0.191
Token million
Token ID1510
Feature activation-4.10e-02

Pos logit contributions
stab+0.105
achelor+0.094
RED+0.094
ifiable+0.093
 Brah+0.093
Neg logit contributions
amental-0.110
enders-0.109
vas-0.100
 vac-0.100
NJ-0.099
Token people
Token ID661
Feature activation-3.27e-02

Pos logit contributions
stab+0.029
RED+0.026
achelor+0.026
ifiable+0.026
 Brah+0.026
Neg logit contributions
amental-0.028
enders-0.028
vas-0.025
NJ-0.025
 vac-0.025
Token eligible
Token ID8867
Feature activation-1.67e-01

Pos logit contributions
stab+0.024
achelor+0.022
RED+0.022
ifiable+0.022
 Brah+0.022
Neg logit contributions
amental-0.021
enders-0.021
vas-0.019
 vac-0.019
NJ-0.019
Token for
Token ID329
Feature activation-2.08e-02

Pos logit contributions
stab+0.121
achelor+0.109
RED+0.109
ifiable+0.108
 Brah+0.108
Neg logit contributions
amental-0.113
enders-0.112
vas-0.102
 vac-0.102
NJ-0.102
Token images
Token ID4263
Feature activation+7.23e-02

Pos logit contributions
amental+0.003
enders+0.003
vas+0.002
 vac+0.002
NJ+0.002
Neg logit contributions
stab-0.004
achelor-0.003
RED-0.003
ifiable-0.003
 Brah-0.003
Token directory
Token ID8619
Feature activation-7.75e-03

Pos logit contributions
amental+0.049
enders+0.048
 vac+0.044
vas+0.044
NJ+0.044
Neg logit contributions
stab-0.052
achelor-0.047
RED-0.047
 Brah-0.047
ifiable-0.047
Token")
Token ID4943
Feature activation-4.33e-02

Pos logit contributions
stab+0.006
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.005
enders-0.005
vas-0.005
 vac-0.005
NJ-0.005
Token args
Token ID26498
Feature activation+1.21e-01

Pos logit contributions
stab+0.033
achelor+0.030
RED+0.030
ifiable+0.030
 Brah+0.030
Neg logit contributions
amental-0.027
enders-0.027
vas-0.025
 vac-0.025
NJ-0.024
Token =
Token ID796
Feature activation+1.11e-03

Pos logit contributions
amental+0.076
enders+0.076
vas+0.069
 vac+0.068
NJ+0.068
Neg logit contributions
stab-0.092
achelor-0.084
RED-0.084
 Brah-0.083
ifiable-0.083
Token v
Token ID410
Feature activation+2.47e-01

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Tokenars
Token ID945
Feature activation-3.82e-02

Pos logit contributions
amental+0.172
enders+0.169
 vac+0.155
vas+0.155
NJ+0.155
Neg logit contributions
stab-0.175
achelor-0.157
RED-0.157
ifiable-0.155
 Brah-0.154
Token(
Token ID7
Feature activation+2.63e-02

Pos logit contributions
stab+0.029
achelor+0.026
RED+0.026
ifiable+0.026
 Brah+0.026
Neg logit contributions
amental-0.025
enders-0.025
vas-0.022
 vac-0.022
NJ-0.022
Tokenap
Token ID499
Feature activation+1.14e-01

Pos logit contributions
amental+0.017
enders+0.017
vas+0.015
 vac+0.015
NJ+0.015
Neg logit contributions
stab-0.020
achelor-0.018
RED-0.018
ifiable-0.018
 Brah-0.018
Token.
Token ID13
Feature activation-4.46e-03

Pos logit contributions
amental+0.075
enders+0.075
vas+0.068
 vac+0.068
NJ+0.067
Neg logit contributions
stab-0.084
RED-0.076
achelor-0.076
ifiable-0.075
 Brah-0.075
Tokenparse
Token ID29572
Feature activation+1.12e-01

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Token in
Token ID287
Feature activation-3.49e-03

Pos logit contributions
stab+0.077
RED+0.069
achelor+0.069
 Brah+0.069
ifiable+0.069
Neg logit contributions
amental-0.070
enders-0.069
vas-0.063
NJ-0.062
eper-0.062
Token and
Token ID290
Feature activation-4.50e-03

Pos logit contributions
stab+0.003
RED+0.002
achelor+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.002
 vac-0.002
NJ-0.002
Token out
Token ID503
Feature activation+6.61e-02

Pos logit contributions
stab+0.004
RED+0.003
achelor+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.002
vas-0.002
NJ-0.002
Token of
Token ID286
Feature activation-1.40e-02

Pos logit contributions
amental+0.045
enders+0.044
vas+0.040
 vac+0.040
NJ+0.040
Neg logit contributions
stab-0.048
RED-0.043
achelor-0.043
ifiable-0.043
 Brah-0.043
Token Lib
Token ID7980
Feature activation+1.79e-01

Pos logit contributions
stab+0.010
RED+0.009
achelor+0.009
 Brah+0.009
ifiable+0.009
Neg logit contributions
amental-0.009
enders-0.009
vas-0.008
NJ-0.008
 vac-0.008
Tokeno
Token ID78
Feature activation+3.28e-01

Pos logit contributions
amental+0.043
enders+0.042
vas+0.032
 vac+0.031
NJ+0.031
Neg logit contributions
stab-0.207
achelor-0.194
RED-0.194
ifiable-0.193
 Brah-0.193
Token last
Token ID938
Feature activation-2.41e-02

Pos logit contributions
amental+0.218
enders+0.216
vas+0.197
 vac+0.197
NJ+0.196
Neg logit contributions
stab-0.241
achelor-0.218
RED-0.218
ifiable-0.215
 Brah-0.215
Token year
Token ID614
Feature activation-2.89e-02

Pos logit contributions
stab+0.017
achelor+0.015
RED+0.015
ifiable+0.015
 Brah+0.015
Neg logit contributions
amental-0.017
enders-0.017
vas-0.015
 vac-0.015
NJ-0.015
Token.
Token ID13
Feature activation-1.06e-03

Pos logit contributions
stab+0.021
achelor+0.019
RED+0.019
ifiable+0.019
 Brah+0.019
Neg logit contributions
amental-0.019
enders-0.019
vas-0.017
 vac-0.017
NJ-0.017
Token
Token ID198
Feature activation+6.09e-03

Pos logit contributions
stab+0.001
RED+0.001
achelor+0.001
 Brah+0.001
ifiable+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token
Token ID198
Feature activation+1.78e-03

Pos logit contributions
amental+0.004
enders+0.004
vas+0.004
 vac+0.004
NJ+0.004
Neg logit contributions
stab-0.005
RED-0.004
achelor-0.004
ifiable-0.004
 Brah-0.004
Token one
Token ID530
Feature activation+9.62e-02

Pos logit contributions
amental+0.011
enders+0.011
vas+0.010
 vac+0.010
NJ+0.010
Neg logit contributions
stab-0.012
achelor-0.011
RED-0.011
ifiable-0.011
 Brah-0.011
Token of
Token ID286
Feature activation-7.13e-03

Pos logit contributions
amental+0.064
enders+0.064
vas+0.058
 vac+0.058
NJ+0.058
Neg logit contributions
stab-0.070
achelor-0.063
RED-0.063
ifiable-0.063
 Brah-0.062
Token the
Token ID262
Feature activation+4.79e-03

Pos logit contributions
stab+0.005
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.005
enders-0.005
 vac-0.004
vas-0.004
NJ-0.004
Token most
Token ID749
Feature activation-4.86e-02

Pos logit contributions
amental+0.004
enders+0.004
 vac+0.003
vas+0.003
NJ+0.003
Neg logit contributions
stab-0.003
achelor-0.003
RED-0.003
ifiable-0.003
 Brah-0.003
Token skill
Token ID5032
Feature activation+1.20e-01

Pos logit contributions
stab+0.038
RED+0.034
achelor+0.034
ifiable+0.034
 Brah+0.034
Neg logit contributions
amental-0.030
enders-0.030
vas-0.027
 vac-0.027
NJ-0.027
Tokenfully
Token ID2759
Feature activation+3.09e-01

Pos logit contributions
enders+0.041
amental+0.041
vas+0.034
NJ+0.034
 vac+0.033
Neg logit contributions
stab-0.126
achelor-0.117
ifiable-0.117
RED-0.117
 Brah-0.116
Token-
Token ID12
Feature activation-1.92e-02

Pos logit contributions
amental+0.200
enders+0.198
vas+0.181
 vac+0.180
NJ+0.179
Neg logit contributions
stab-0.232
achelor-0.210
RED-0.210
ifiable-0.207
 Brah-0.207
Tokenl
Token ID75
Feature activation+1.17e-01

Pos logit contributions
stab+0.013
RED+0.012
achelor+0.012
ifiable+0.012
 Brah+0.012
Neg logit contributions
amental-0.014
enders-0.014
vas-0.012
 vac-0.012
NJ-0.012
Tokeniked
Token ID17951
Feature activation+3.86e-02

Pos logit contributions
amental+0.064
enders+0.064
vas+0.057
 vac+0.056
NJ+0.056
Neg logit contributions
stab-0.100
RED-0.091
achelor-0.091
 Brah-0.090
ifiable-0.090
Token media
Token ID2056
Feature activation-6.30e-02

Pos logit contributions
amental+0.025
enders+0.025
vas+0.023
 vac+0.023
NJ+0.022
Neg logit contributions
stab-0.029
achelor-0.026
RED-0.026
ifiable-0.026
 Brah-0.026
Token centers
Token ID10399
Feature activation-4.76e-02

Pos logit contributions
stab+0.048
achelor+0.044
RED+0.044
ifiable+0.043
 Brah+0.043
Neg logit contributions
amental-0.040
enders-0.040
 vac-0.036
vas-0.036
eper-0.035
Token Policy
Token ID7820
Feature activation-5.75e-02

Pos logit contributions
amental+0.022
enders+0.022
vas+0.020
 vac+0.020
NJ+0.020
Neg logit contributions
stab-0.026
achelor-0.024
RED-0.024
ifiable-0.023
 Brah-0.023
Token Center
Token ID3337
Feature activation-7.34e-02

Pos logit contributions
stab+0.036
achelor+0.033
RED+0.032
ifiable+0.032
 Brah+0.032
Neg logit contributions
amental-0.044
enders-0.043
vas-0.040
 vac-0.040
eper-0.040
Token based
Token ID1912
Feature activation+1.57e-02

Pos logit contributions
stab+0.054
RED+0.048
achelor+0.048
ifiable+0.048
 Brah+0.048
Neg logit contributions
amental-0.049
enders-0.049
vas-0.044
 vac-0.044
eper-0.044
Token in
Token ID287
Feature activation-1.24e-03

Pos logit contributions
amental+0.010
enders+0.010
vas+0.009
 vac+0.009
NJ+0.009
Neg logit contributions
stab-0.012
RED-0.011
achelor-0.011
ifiable-0.010
 Brah-0.010
Token Washington
Token ID2669
Feature activation-1.37e-01

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token.
Token ID13
Feature activation-1.77e-03

Pos logit contributions
stab+0.101
RED+0.091
achelor+0.091
ifiable+0.090
 Brah+0.090
Neg logit contributions
amental-0.091
enders-0.090
vas-0.082
 vac-0.082
NJ-0.082
Token<|endoftext|>
Token ID50256
Feature activation-1.65e-01

Pos logit contributions
stab+0.001
RED+0.001
achelor+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
TokenAs
Token ID1722
Feature activation+3.50e-02

Pos logit contributions
stab+0.122
achelor+0.110
RED+0.110
ifiable+0.109
 Brah+0.109
Neg logit contributions
amental-0.109
enders-0.109
vas-0.099
 vac-0.098
NJ-0.098
Token a
Token ID257
Feature activation+1.29e-02

Pos logit contributions
amental+0.023
enders+0.023
vas+0.021
 vac+0.021
NJ+0.021
Neg logit contributions
stab-0.025
achelor-0.023
RED-0.023
ifiable-0.023
 Brah-0.023
Token pub
Token ID2240
Feature activation-1.16e-01

Pos logit contributions
amental+0.008
enders+0.008
vas+0.008
 vac+0.008
NJ+0.008
Neg logit contributions
stab-0.010
achelor-0.009
RED-0.009
ifiable-0.009
 Brah-0.009
Token storm
Token ID6388
Feature activation-1.05e-01

Pos logit contributions
stab+0.085
achelor+0.077
RED+0.077
ifiable+0.076
 Brah+0.076
Neg logit contributions
amental-0.077
enders-0.077
vas-0.070
 vac-0.070
NJ-0.069
Token paths
Token ID13532
Feature activation-2.32e-01

Pos logit contributions
stab+0.006
RED+0.005
achelor+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.011
enders-0.011
vas-0.010
 vac-0.010
NJ-0.010
Token.
Token ID13
Feature activation-7.80e-03

Pos logit contributions
stab+0.165
RED+0.148
achelor+0.148
ifiable+0.147
 Brah+0.147
Neg logit contributions
amental-0.160
enders-0.158
vas-0.144
 vac-0.144
NJ-0.143
Tokenlist
Token ID4868
Feature activation+3.31e-02

Pos logit contributions
stab+0.006
RED+0.006
achelor+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.005
enders-0.005
vas-0.004
 vac-0.004
NJ-0.004
Token_
Token ID62
Feature activation-9.95e-02

Pos logit contributions
amental+0.025
enders+0.025
 vac+0.023
vas+0.023
NJ+0.023
Neg logit contributions
stab-0.021
RED-0.019
achelor-0.019
ifiable-0.019
 Brah-0.019
Tokenimages
Token ID17566
Feature activation+1.20e-01

Pos logit contributions
stab+0.088
RED+0.081
achelor+0.081
ifiable+0.081
 Brah+0.080
Neg logit contributions
amental-0.051
enders-0.050
 vac-0.045
NJ-0.044
vas-0.044
Token(
Token ID7
Feature activation+2.17e-02

Pos logit contributions
amental+0.077
enders+0.076
 vac+0.069
vas+0.069
 expiration+0.069
Neg logit contributions
stab-0.092
RED-0.083
ifiable-0.082
achelor-0.082
 Brah-0.082
Tokenargs
Token ID22046
Feature activation+3.78e-02

Pos logit contributions
amental+0.013
enders+0.013
vas+0.011
 vac+0.011
NJ+0.011
Neg logit contributions
stab-0.017
RED-0.016
achelor-0.016
ifiable-0.016
 Brah-0.016
Token["
Token ID14692
Feature activation-7.83e-02

Pos logit contributions
amental+0.028
enders+0.028
vas+0.026
 vac+0.026
NJ+0.026
Neg logit contributions
stab-0.025
RED-0.022
achelor-0.022
ifiable-0.022
 Brah-0.022
Tokenimages
Token ID17566
Feature activation+1.17e-01

Pos logit contributions
stab+0.069
RED+0.063
ifiable+0.063
achelor+0.063
 Brah+0.062
Neg logit contributions
amental-0.041
enders-0.040
 vac-0.036
NJ-0.035
 expiration-0.035
Token"]
Token ID8973
Feature activation+6.71e-02

Pos logit contributions
amental+0.064
enders+0.063
 vac+0.057
vas+0.057
NJ+0.056
Neg logit contributions
stab-0.100
RED-0.091
achelor-0.091
ifiable-0.091
 Brah-0.090
Token):
Token ID2599
Feature activation+9.47e-02

Pos logit contributions
amental+0.038
enders+0.037
vas+0.033
 vac+0.033
NJ+0.033
Neg logit contributions
stab-0.057
RED-0.052
achelor-0.052
ifiable-0.051
 Brah-0.051
Token]
Token ID60
Feature activation+7.00e-02

Pos logit contributions
amental+0.047
enders+0.046
vas+0.041
 vac+0.041
NJ+0.041
Neg logit contributions
stab-0.074
RED-0.068
achelor-0.068
 Brah-0.067
ifiable-0.067
Token What
Token ID1867
Feature activation+3.55e-02

Pos logit contributions
amental+0.046
enders+0.046
 vac+0.041
vas+0.041
eper+0.041
Neg logit contributions
stab-0.052
RED-0.047
achelor-0.047
 Brah-0.047
ifiable-0.046
Token kind
Token ID1611
Feature activation-5.76e-02

Pos logit contributions
amental+0.023
enders+0.023
vas+0.021
 vac+0.021
NJ+0.021
Neg logit contributions
stab-0.027
achelor-0.024
RED-0.024
ifiable-0.024
 Brah-0.024
Token of
Token ID286
Feature activation-9.18e-03

Pos logit contributions
stab+0.042
RED+0.037
achelor+0.037
ifiable+0.037
 Brah+0.037
Neg logit contributions
amental-0.039
enders-0.039
vas-0.035
 vac-0.035
NJ-0.035
Token projects
Token ID4493
Feature activation-5.00e-03

Pos logit contributions
stab+0.007
RED+0.006
achelor+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.006
enders-0.006
vas-0.005
NJ-0.005
 vac-0.005
Token are
Token ID389
Feature activation+1.54e-02

Pos logit contributions
stab+0.004
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Token done
Token ID1760
Feature activation-1.85e-01

Pos logit contributions
amental+0.011
enders+0.011
vas+0.010
 vac+0.010
NJ+0.010
Neg logit contributions
stab-0.011
RED-0.010
achelor-0.010
ifiable-0.010
 Brah-0.009
Token with
Token ID351
Feature activation+1.37e-02

Pos logit contributions
stab+0.136
RED+0.123
achelor+0.123
ifiable+0.122
 Brah+0.122
Neg logit contributions
amental-0.123
enders-0.122
vas-0.111
NJ-0.110
 vac-0.110
Token Te
Token ID1665
Feature activation+5.22e-02

Pos logit contributions
amental+0.009
enders+0.009
vas+0.008
NJ+0.008
eper+0.008
Neg logit contributions
stab-0.010
RED-0.009
achelor-0.009
ifiable-0.009
 Brah-0.009
Tokenens
Token ID641
Feature activation+1.07e-01

Pos logit contributions
amental+0.028
enders+0.027
 vac+0.024
 expiration+0.024
 jug+0.024
Neg logit contributions
stab-0.046
achelor-0.042
RED-0.042
ifiable-0.041
 Brah-0.041
Tokeny
Token ID88
Feature activation+1.07e-02

Pos logit contributions
amental+0.067
enders+0.066
vas+0.060
 vac+0.060
NJ+0.059
Neg logit contributions
stab-0.084
achelor-0.076
RED-0.076
ifiable-0.075
 Brah-0.075
Token more
Token ID517
Feature activation+9.98e-03

Pos logit contributions
stab+0.004
RED+0.003
achelor+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Token observers
Token ID17984
Feature activation+1.20e-01

Pos logit contributions
amental+0.007
enders+0.007
vas+0.006
 vac+0.006
NJ+0.006
Neg logit contributions
stab-0.007
RED-0.007
achelor-0.007
ifiable-0.007
 Brah-0.007
Token,
Token ID11
Feature activation+1.88e-04

Pos logit contributions
amental+0.080
enders+0.079
vas+0.072
NJ+0.072
existent+0.072
Neg logit contributions
stab-0.087
achelor-0.079
RED-0.079
ifiable-0.078
 Brah-0.078
Token however
Token ID2158
Feature activation+2.11e-01

Pos logit contributions
amental+0.000
enders+0.000
vas+0.000
 vac+0.000
NJ+0.000
Neg logit contributions
stab-0.000
achelor-0.000
RED-0.000
ifiable-0.000
 Brah-0.000
Token,
Token ID11
Feature activation-4.06e-04

Pos logit contributions
amental+0.141
enders+0.140
vas+0.127
NJ+0.126
 vac+0.126
Neg logit contributions
stab-0.155
RED-0.139
achelor-0.139
ifiable-0.139
 Brah-0.138
Token believe
Token ID1975
Feature activation+1.47e-01

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
NJ-0.000
existent-0.000
Token that
Token ID326
Feature activation+1.51e-02

Pos logit contributions
amental+0.098
enders+0.097
vas+0.089
NJ+0.088
 vac+0.088
Neg logit contributions
stab-0.107
RED-0.096
achelor-0.096
ifiable-0.096
 Brah-0.095
Token excessive
Token ID13181
Feature activation+2.07e-01

Pos logit contributions
amental+0.010
enders+0.010
vas+0.009
NJ+0.009
 vac+0.009
Neg logit contributions
stab-0.011
RED-0.010
achelor-0.010
ifiable-0.010
 Brah-0.010
Token speculation
Token ID13367
Feature activation-7.22e-02

Pos logit contributions
amental+0.130
enders+0.129
vas+0.117
 vac+0.116
NJ+0.116
Neg logit contributions
stab-0.159
RED-0.145
achelor-0.145
ifiable-0.144
 Brah-0.143
Token in
Token ID287
Feature activation+1.82e-02

Pos logit contributions
stab+0.054
RED+0.049
achelor+0.049
ifiable+0.048
 Brah+0.048
Neg logit contributions
amental-0.047
enders-0.047
vas-0.043
 vac-0.042
NJ-0.042
Token the
Token ID262
Feature activation+2.39e-02

Pos logit contributions
amental+0.011
enders+0.011
vas+0.010
NJ+0.010
 vac+0.010
Neg logit contributions
stab-0.014
RED-0.013
ifiable-0.013
achelor-0.013
 Brah-0.013
Token the
Token ID262
Feature activation-4.35e-03

Pos logit contributions
amental+0.060
enders+0.059
vas+0.054
 vac+0.054
NJ+0.054
Neg logit contributions
stab-0.066
RED-0.060
achelor-0.059
ifiable-0.059
 Brah-0.059
Token children
Token ID1751
Feature activation+2.14e-01

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.003
vas-0.003
 wax-0.003
Token.'
Token ID2637
Feature activation+1.89e-02

Pos logit contributions
amental+0.140
enders+0.139
vas+0.127
NJ+0.126
 vac+0.126
Neg logit contributions
stab-0.159
achelor-0.144
RED-0.143
ifiable-0.142
 Brah-0.142
Token
Token ID198
Feature activation-8.13e-03

Pos logit contributions
amental+0.012
enders+0.012
vas+0.011
 vac+0.011
NJ+0.011
Neg logit contributions
stab-0.014
achelor-0.013
RED-0.013
ifiable-0.013
 Brah-0.013
Token
Token ID198
Feature activation-1.78e-03

Pos logit contributions
stab+0.006
RED+0.005
achelor+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.005
enders-0.005
 vac-0.005
vas-0.005
NJ-0.005
TokenT
Token ID51
Feature activation+3.38e-02

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Tokenori
Token ID10145
Feature activation+5.43e-02

Pos logit contributions
amental+0.019
enders+0.019
vas+0.017
 vac+0.017
NJ+0.017
Neg logit contributions
stab-0.028
RED-0.026
achelor-0.026
 Brah-0.026
ifiable-0.026
Token posted
Token ID4481
Feature activation+1.48e-01

Pos logit contributions
amental+0.033
enders+0.033
vas+0.030
 vac+0.030
NJ+0.030
Neg logit contributions
stab-0.043
achelor-0.039
RED-0.039
ifiable-0.038
 Brah-0.038
Token this
Token ID428
Feature activation-3.60e-03

Pos logit contributions
amental+0.096
enders+0.095
 vac+0.086
vas+0.086
NJ+0.086
Neg logit contributions
stab-0.111
achelor-0.100
RED-0.100
ifiable-0.099
 Brah-0.099
Token cryptic
Token ID47774
Feature activation-1.24e-02

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
 vac-0.002
vas-0.002
NJ-0.002
Token message
Token ID3275
Feature activation+4.60e-02

Pos logit contributions
stab+0.010
achelor+0.009
RED+0.009
ifiable+0.009
 Brah+0.009
Neg logit contributions
amental-0.008
enders-0.008
vas-0.007
 vac-0.007
NJ-0.007
Tokens
Token ID82
Feature activation-1.35e-02

Pos logit contributions
amental+0.006
enders+0.006
vas+0.006
 vac+0.006
NJ+0.006
Neg logit contributions
stab-0.007
achelor-0.006
RED-0.006
ifiable-0.006
 Brah-0.006
Token a
Token ID257
Feature activation+8.65e-03

Pos logit contributions
stab+0.010
achelor+0.009
RED+0.009
ifiable+0.009
 Brah+0.009
Neg logit contributions
amental-0.009
enders-0.009
vas-0.008
 vac-0.008
NJ-0.008
Token simple
Token ID2829
Feature activation+1.04e-01

Pos logit contributions
amental+0.006
enders+0.006
vas+0.005
 vac+0.005
NJ+0.005
Neg logit contributions
stab-0.006
achelor-0.006
RED-0.006
ifiable-0.006
 Brah-0.006
Token case
Token ID1339
Feature activation-5.75e-02

Pos logit contributions
amental+0.067
enders+0.067
 vac+0.061
vas+0.060
NJ+0.060
Neg logit contributions
stab-0.079
achelor-0.071
RED-0.071
 Brah-0.070
ifiable-0.070
Token of
Token ID286
Feature activation-1.17e-02

Pos logit contributions
stab+0.041
achelor+0.037
RED+0.037
ifiable+0.037
 Brah+0.037
Neg logit contributions
amental-0.039
enders-0.039
vas-0.035
 vac-0.035
NJ-0.035
Token economic
Token ID3034
Feature activation-1.09e-01

Pos logit contributions
stab+0.009
RED+0.008
achelor+0.008
ifiable+0.008
 Brah+0.008
Neg logit contributions
amental-0.008
enders-0.008
 vac-0.007
vas-0.007
NJ-0.007
Token logic
Token ID9156
Feature activation-9.99e-02

Pos logit contributions
stab+0.077
achelor+0.069
RED+0.069
ifiable+0.068
 Brah+0.068
Neg logit contributions
amental-0.075
enders-0.075
 vac-0.068
vas-0.068
NJ-0.068
Token.
Token ID13
Feature activation-4.39e-03

Pos logit contributions
stab+0.074
achelor+0.067
RED+0.067
ifiable+0.067
 Brah+0.066
Neg logit contributions
amental-0.065
enders-0.065
vas-0.059
 vac-0.059
NJ-0.058
Token In
Token ID554
Feature activation+1.88e-02

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Token order
Token ID1502
Feature activation+1.22e-02

Pos logit contributions
amental+0.013
enders+0.012
vas+0.011
 vac+0.011
NJ+0.011
Neg logit contributions
stab-0.014
RED-0.012
achelor-0.012
ifiable-0.012
 Brah-0.012
Token to
Token ID284
Feature activation+6.36e-03

Pos logit contributions
amental+0.008
enders+0.008
vas+0.007
 vac+0.007
NJ+0.007
Neg logit contributions
stab-0.009
achelor-0.008
RED-0.008
ifiable-0.008
 Brah-0.008
Tokenly
Token ID306
Feature activation+2.72e-01

Pos logit contributions
stab+0.126
achelor+0.117
RED+0.117
ifiable+0.117
 Brah+0.117
Neg logit contributions
amental-0.031
enders-0.031
vas-0.024
 vac-0.024
NJ-0.024
Token or
Token ID393
Feature activation-4.58e-02

Pos logit contributions
amental+0.193
enders+0.191
 vac+0.177
vas+0.175
 wax+0.175
Neg logit contributions
stab-0.188
RED-0.169
achelor-0.169
ifiable-0.166
 Brah-0.165
Token un
Token ID555
Feature activation-6.12e-02

Pos logit contributions
stab+0.032
achelor+0.029
RED+0.029
ifiable+0.028
 Brah+0.028
Neg logit contributions
amental-0.032
enders-0.032
vas-0.029
 vac-0.029
NJ-0.029
Tokengener
Token ID8612
Feature activation+1.06e-02

Pos logit contributions
stab+0.048
achelor+0.044
RED+0.044
ifiable+0.044
 Brah+0.043
Neg logit contributions
amental-0.037
enders-0.037
vas-0.033
 vac-0.033
NJ-0.033
Tokenous
Token ID516
Feature activation+1.24e-01

Pos logit contributions
amental+0.005
enders+0.005
vas+0.005
 vac+0.005
NJ+0.005
Neg logit contributions
stab-0.009
achelor-0.009
RED-0.009
ifiable-0.009
 Brah-0.009
Token criticism
Token ID7734
Feature activation-8.60e-02

Pos logit contributions
amental+0.089
enders+0.088
 vac+0.081
vas+0.081
 wax+0.080
Neg logit contributions
stab-0.085
RED-0.076
achelor-0.076
ifiable-0.074
 Brah-0.074
Token,
Token ID11
Feature activation-6.49e-03

Pos logit contributions
stab+0.063
achelor+0.057
RED+0.057
ifiable+0.057
 Brah+0.057
Neg logit contributions
amental-0.057
enders-0.056
 vac-0.051
vas-0.051
NJ-0.051
Token ridicule
Token ID38364
Feature activation-3.14e-02

Pos logit contributions
stab+0.005
RED+0.004
achelor+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.004
enders-0.004
 vac-0.004
vas-0.004
NJ-0.004
Token,
Token ID11
Feature activation-4.87e-03

Pos logit contributions
stab+0.023
achelor+0.021
RED+0.021
ifiable+0.021
 Brah+0.021
Neg logit contributions
amental-0.021
enders-0.020
vas-0.019
 vac-0.019
NJ-0.018
Token or
Token ID393
Feature activation-4.28e-02

Pos logit contributions
stab+0.004
RED+0.003
achelor+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.003
vas-0.003
 wax-0.003
Token satire
Token ID35704
Feature activation+2.19e-02

Pos logit contributions
stab+0.030
RED+0.027
achelor+0.027
ifiable+0.026
 Brah+0.026
Neg logit contributions
amental-0.030
enders-0.030
 vac-0.027
vas-0.027
NJ-0.027
Token Presidential
Token ID17471
Feature activation-1.42e-01

Pos logit contributions
stab+0.001
achelor+0.001
RED+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token spokesman
Token ID6523
Feature activation-1.77e-02

Pos logit contributions
stab+0.097
RED+0.087
achelor+0.087
ifiable+0.086
 Brah+0.085
Neg logit contributions
amental-0.102
enders-0.101
 vac-0.093
vas-0.093
NJ-0.092
Token Ye
Token ID11609
Feature activation-6.45e-02

Pos logit contributions
stab+0.013
achelor+0.012
RED+0.012
ifiable+0.012
 Brah+0.012
Neg logit contributions
amental-0.012
enders-0.012
vas-0.011
 vac-0.011
NJ-0.010
Token H
Token ID367
Feature activation-1.03e-01

Pos logit contributions
stab+0.046
RED+0.041
achelor+0.041
ifiable+0.041
 Brah+0.041
Neg logit contributions
amental-0.044
enders-0.044
vas-0.040
 vac-0.040
NJ-0.040
Tokent
Token ID83
Feature activation+2.94e-03

Pos logit contributions
stab+0.077
achelor+0.069
RED+0.069
ifiable+0.069
 Brah+0.069
Neg logit contributions
amental-0.067
enders-0.066
 vac-0.061
NJ-0.060
vas-0.060
Tokenut
Token ID315
Feature activation-4.56e-02

Pos logit contributions
amental+0.002
enders+0.002
vas+0.002
 vac+0.002
NJ+0.002
Neg logit contributions
stab-0.002
achelor-0.002
RED-0.002
ifiable-0.002
 Brah-0.002
Token told
Token ID1297
Feature activation+1.37e-01

Pos logit contributions
stab+0.034
achelor+0.031
RED+0.031
ifiable+0.030
 Brah+0.030
Neg logit contributions
amental-0.030
enders-0.029
vas-0.027
 vac-0.027
NJ-0.027
Token me
Token ID502
Feature activation-2.14e-02

Pos logit contributions
amental+0.094
enders+0.093
vas+0.085
 vac+0.085
NJ+0.085
Neg logit contributions
stab-0.097
RED-0.088
achelor-0.088
ifiable-0.087
 Brah-0.087
Token their
Token ID511
Feature activation-9.04e-03

Pos logit contributions
stab+0.016
achelor+0.015
RED+0.014
ifiable+0.014
 Brah+0.014
Neg logit contributions
amental-0.014
enders-0.014
vas-0.013
 vac-0.013
NJ-0.012
Token actions
Token ID4028
Feature activation-4.41e-02

Pos logit contributions
stab+0.006
achelor+0.006
RED+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.006
enders-0.006
vas-0.006
 vac-0.006
NJ-0.006
Token had
Token ID550
Feature activation+1.17e-02

Pos logit contributions
stab+0.034
RED+0.031
achelor+0.031
 Brah+0.030
ifiable+0.030
Neg logit contributions
amental-0.028
enders-0.027
 vac-0.025
vas-0.025
 wax-0.025
Token you
Token ID345
Feature activation-2.97e-02

Pos logit contributions
stab+0.003
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
 vac-0.002
vas-0.002
NJ-0.002
Token held
Token ID2714
Feature activation+9.70e-02

Pos logit contributions
stab+0.022
achelor+0.020
RED+0.020
ifiable+0.020
 Brah+0.020
Neg logit contributions
amental-0.019
enders-0.019
vas-0.017
 vac-0.017
NJ-0.017
Token.
Token ID13
Feature activation-8.20e-03

Pos logit contributions
amental+0.064
enders+0.063
vas+0.058
NJ+0.057
 vac+0.057
Neg logit contributions
stab-0.072
RED-0.065
achelor-0.065
ifiable-0.064
 Brah-0.064
Token
Token ID198
Feature activation+2.88e-03

Pos logit contributions
stab+0.006
achelor+0.005
RED+0.005
ifiable+0.005
 Brah+0.005
Neg logit contributions
amental-0.006
enders-0.005
vas-0.005
 vac-0.005
NJ-0.005
Token
Token ID198
Feature activation-3.73e-03

Pos logit contributions
amental+0.002
enders+0.002
vas+0.002
 vac+0.002
NJ+0.002
Neg logit contributions
stab-0.002
RED-0.002
achelor-0.002
ifiable-0.002
 Brah-0.002
TokenEn
Token ID4834
Feature activation-4.41e-02

Pos logit contributions
stab+0.003
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.002
NJ-0.002
 vac-0.002
Tokenlight
Token ID2971
Feature activation+2.93e-01

Pos logit contributions
stab+0.036
achelor+0.033
RED+0.033
ifiable+0.033
 Brah+0.033
Neg logit contributions
amental-0.026
enders-0.025
 vac-0.023
vas-0.023
NJ-0.023
Tokenenment
Token ID23242
Feature activation-3.36e-02

Pos logit contributions
amental+0.181
enders+0.179
vas+0.162
 vac+0.162
NJ+0.161
Neg logit contributions
stab-0.228
RED-0.208
achelor-0.207
ifiable-0.206
 Brah-0.205
Token is
Token ID318
Feature activation-1.28e-05

Pos logit contributions
stab+0.025
achelor+0.023
RED+0.023
ifiable+0.022
 Brah+0.022
Neg logit contributions
amental-0.022
enders-0.022
vas-0.020
 vac-0.020
NJ-0.020
Token like
Token ID588
Feature activation+7.51e-02

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
NJ-0.000
Token that
Token ID326
Feature activation-6.31e-03

Pos logit contributions
amental+0.050
enders+0.050
 vac+0.045
vas+0.045
NJ+0.045
Neg logit contributions
stab-0.055
achelor-0.050
RED-0.050
ifiable-0.049
 Brah-0.049
Token an
Token ID281
Feature activation-5.29e-02

Pos logit contributions
amental+0.013
enders+0.013
 vac+0.012
vas+0.012
NJ+0.012
Neg logit contributions
stab-0.015
achelor-0.013
RED-0.013
ifiable-0.013
 Brah-0.013
Token interview
Token ID2720
Feature activation-1.28e-01

Pos logit contributions
stab+0.032
RED+0.028
achelor+0.028
ifiable+0.028
 Brah+0.028
Neg logit contributions
amental-0.042
enders-0.042
vas-0.039
 vac-0.039
NJ-0.038
Token with
Token ID351
Feature activation+1.38e-02

Pos logit contributions
stab+0.095
achelor+0.086
RED+0.086
ifiable+0.086
 Brah+0.085
Neg logit contributions
amental-0.083
enders-0.082
vas-0.075
 vac-0.074
NJ-0.074
Token legendary
Token ID13273
Feature activation-3.41e-02

Pos logit contributions
amental+0.009
enders+0.009
 vac+0.008
vas+0.008
NJ+0.008
Neg logit contributions
stab-0.010
achelor-0.009
RED-0.009
ifiable-0.009
 Brah-0.009
Token Michigan
Token ID7055
Feature activation+1.15e-01

Pos logit contributions
stab+0.025
achelor+0.023
RED+0.023
ifiable+0.023
 Brah+0.023
Neg logit contributions
amental-0.023
enders-0.022
vas-0.020
 vac-0.020
NJ-0.020
Token State
Token ID1812
Feature activation-1.78e-01

Pos logit contributions
amental+0.076
enders+0.076
 vac+0.069
vas+0.069
NJ+0.069
Neg logit contributions
stab-0.084
RED-0.076
achelor-0.076
ifiable-0.075
 Brah-0.074
Token basketball
Token ID9669
Feature activation+8.52e-02

Pos logit contributions
stab+0.127
RED+0.115
achelor+0.115
ifiable+0.113
 Brah+0.112
Neg logit contributions
amental-0.122
enders-0.121
 vac-0.111
vas-0.111
 wax-0.109
Token coach
Token ID3985
Feature activation+1.22e-02

Pos logit contributions
amental+0.055
enders+0.054
vas+0.049
 vac+0.049
NJ+0.049
Neg logit contributions
stab-0.064
RED-0.058
achelor-0.058
ifiable-0.058
 Brah-0.057
Token Tom
Token ID4186
Feature activation+1.45e-02

Pos logit contributions
amental+0.008
enders+0.008
 vac+0.007
vas+0.007
NJ+0.007
Neg logit contributions
stab-0.009
achelor-0.008
RED-0.008
ifiable-0.008
 Brah-0.008
Token I
Token ID314
Feature activation+5.92e-02

Pos logit contributions
amental+0.009
enders+0.009
vas+0.008
 vac+0.008
NJ+0.008
Neg logit contributions
stab-0.012
achelor-0.011
RED-0.011
ifiable-0.010
 Brah-0.010
Tokenzzo
Token ID47802
Feature activation+7.93e-02

Pos logit contributions
amental+0.030
enders+0.030
vas+0.026
 vac+0.026
eper+0.026
Neg logit contributions
stab-0.053
achelor-0.049
RED-0.049
ifiable-0.048
 Brah-0.048
Token trend
Token ID5182
Feature activation+6.36e-02

Pos logit contributions
stab+0.045
RED+0.041
achelor+0.040
ifiable+0.040
 Brah+0.040
Neg logit contributions
amental-0.038
enders-0.038
vas-0.035
 vac-0.035
NJ-0.034
Token for
Token ID329
Feature activation-1.18e-02

Pos logit contributions
amental+0.043
enders+0.043
vas+0.039
 vac+0.039
NJ+0.038
Neg logit contributions
stab-0.046
achelor-0.042
RED-0.042
ifiable-0.041
 Brah-0.041
Token teen
Token ID6036
Feature activation+1.81e-01

Pos logit contributions
stab+0.009
RED+0.008
achelor+0.008
ifiable+0.008
 Brah+0.008
Neg logit contributions
amental-0.007
enders-0.007
vas-0.006
 vac-0.006
NJ-0.006
Token girls
Token ID4813
Feature activation+6.12e-02

Pos logit contributions
amental+0.109
enders+0.108
NJ+0.097
eper+0.097
vas+0.097
Neg logit contributions
stab-0.144
RED-0.131
achelor-0.131
ifiable-0.131
 Brah-0.130
Token:
Token ID25
Feature activation+4.55e-02

Pos logit contributions
amental+0.040
enders+0.040
vas+0.036
 vac+0.036
NJ+0.036
Neg logit contributions
stab-0.045
achelor-0.041
RED-0.041
ifiable-0.041
 Brah-0.040
Token dressing
Token ID18544
Feature activation-2.83e-01

Pos logit contributions
amental+0.030
enders+0.030
vas+0.027
 vac+0.027
NJ+0.027
Neg logit contributions
stab-0.034
RED-0.030
achelor-0.030
ifiable-0.030
 Brah-0.030
Token up
Token ID510
Feature activation+1.19e-01

Pos logit contributions
stab+0.239
RED+0.219
achelor+0.218
ifiable+0.217
 Brah+0.217
Neg logit contributions
amental-0.158
enders-0.156
vas-0.139
NJ-0.138
 vac-0.137
Token like
Token ID588
Feature activation+8.63e-02

Pos logit contributions
amental+0.077
enders+0.076
vas+0.069
 vac+0.069
NJ+0.069
Neg logit contributions
stab-0.089
RED-0.081
achelor-0.081
ifiable-0.080
 Brah-0.080
Token dolls
Token ID36062
Feature activation+8.17e-02

Pos logit contributions
amental+0.054
enders+0.054
vas+0.048
 vac+0.048
NJ+0.048
Neg logit contributions
stab-0.067
achelor-0.061
RED-0.061
ifiable-0.060
 Brah-0.060
Token.
Token ID13
Feature activation-1.62e-03

Pos logit contributions
amental+0.053
enders+0.053
vas+0.048
 vac+0.048
NJ+0.047
Neg logit contributions
stab-0.061
RED-0.055
achelor-0.055
ifiable-0.055
 Brah-0.055
Token Why
Token ID4162
Feature activation-3.98e-02

Pos logit contributions
stab+0.001
RED+0.001
achelor+0.001
ifiable+0.001
 Brah+0.001
Neg logit contributions
amental-0.001
enders-0.001
vas-0.001
 vac-0.001
NJ-0.001
Token 68
Token ID8257
Feature activation-2.89e-04

Pos logit contributions
amental+0.011
enders+0.011
 vac+0.010
vas+0.010
NJ+0.010
Neg logit contributions
stab-0.012
achelor-0.011
RED-0.011
 Brah-0.010
ifiable-0.010
Token46
Token ID3510
Feature activation+7.70e-02

Pos logit contributions
stab+0.000
RED+0.000
achelor+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
eper-0.000
Token.
Token ID13
Feature activation-3.22e-03

Pos logit contributions
amental+0.052
enders+0.051
vas+0.047
 vac+0.047
NJ+0.046
Neg logit contributions
stab-0.056
achelor-0.051
RED-0.051
ifiable-0.050
 Brah-0.050
Token<|endoftext|>
Token ID50256
Feature activation-1.69e-01

Pos logit contributions
stab+0.003
RED+0.002
achelor+0.002
 Brah+0.002
ifiable+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.002
eper-0.002
 vac-0.002
Token(
Token ID7
Feature activation+3.39e-02

Pos logit contributions
stab+0.125
achelor+0.113
RED+0.113
ifiable+0.112
 Brah+0.112
Neg logit contributions
amental-0.112
enders-0.111
vas-0.101
 vac-0.101
NJ-0.101
TokenFIL
Token ID46700
Feature activation-3.15e-01

Pos logit contributions
amental+0.021
enders+0.021
vas+0.019
 vac+0.019
NJ+0.019
Neg logit contributions
stab-0.026
achelor-0.024
RED-0.023
ifiable-0.023
 Brah-0.023
TokenES
Token ID1546
Feature activation-2.13e-01

Pos logit contributions
stab+0.214
achelor+0.192
RED+0.191
ifiable+0.189
 Brah+0.189
Neg logit contributions
amental-0.227
enders-0.225
vas-0.207
 vac-0.206
NJ-0.205
Token)
Token ID8
Feature activation-1.03e-02

Pos logit contributions
stab+0.142
achelor+0.127
RED+0.126
ifiable+0.125
 Brah+0.125
Neg logit contributions
amental-0.155
enders-0.154
vas-0.142
 vac-0.142
NJ-0.141
TokenUS
Token ID2937
Feature activation-4.30e-02

Pos logit contributions
stab+0.008
achelor+0.007
RED+0.007
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.007
enders-0.007
vas-0.006
 vac-0.006
NJ-0.006
Token Treasury
Token ID13419
Feature activation+1.53e-03

Pos logit contributions
stab+0.029
achelor+0.026
RED+0.026
ifiable+0.026
 Brah+0.026
Neg logit contributions
amental-0.031
enders-0.030
vas-0.028
 vac-0.028
NJ-0.028
Token Secretary
Token ID4986
Feature activation-2.05e-02

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token select
Token ID2922
Feature activation-1.08e-01

Pos logit contributions
amental+0.064
enders+0.064
vas+0.058
 vac+0.058
NJ+0.058
Neg logit contributions
stab-0.069
RED-0.062
achelor-0.062
ifiable-0.061
 Brah-0.061
Token labs
Token ID27887
Feature activation-2.08e-02

Pos logit contributions
stab+0.077
achelor+0.070
RED+0.069
ifiable+0.069
 Brah+0.069
Neg logit contributions
amental-0.074
enders-0.073
vas-0.067
 vac-0.067
NJ-0.066
Token throughout
Token ID3690
Feature activation+9.48e-02

Pos logit contributions
stab+0.016
achelor+0.014
RED+0.014
ifiable+0.014
 Brah+0.014
Neg logit contributions
amental-0.014
enders-0.013
vas-0.012
 vac-0.012
NJ-0.012
Token the
Token ID262
Feature activation+1.21e-03

Pos logit contributions
amental+0.063
enders+0.062
vas+0.056
 vac+0.056
NJ+0.056
Neg logit contributions
stab-0.070
achelor-0.063
RED-0.063
ifiable-0.063
 Brah-0.063
Token United
Token ID1578
Feature activation-1.40e-02

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
RED-0.001
achelor-0.001
ifiable-0.001
 Brah-0.001
Token States
Token ID1829
Feature activation-2.95e-01

Pos logit contributions
stab+0.005
achelor+0.004
RED+0.004
ifiable+0.004
 Brah+0.004
Neg logit contributions
amental-0.014
enders-0.014
vas-0.013
 vac-0.013
NJ-0.013
Token,
Token ID11
Feature activation-4.03e-03

Pos logit contributions
stab+0.223
achelor+0.202
RED+0.201
ifiable+0.199
 Brah+0.199
Neg logit contributions
amental-0.190
enders-0.189
vas-0.171
 vac-0.171
NJ-0.170
Token including
Token ID1390
Feature activation+9.57e-02

Pos logit contributions
stab+0.003
RED+0.003
achelor+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.002
 vac-0.002
NJ-0.002
Token Puerto
Token ID15295
Feature activation+2.06e-01

Pos logit contributions
amental+0.062
enders+0.062
vas+0.056
 vac+0.056
NJ+0.056
Neg logit contributions
stab-0.071
achelor-0.065
RED-0.065
ifiable-0.064
 Brah-0.064
Token Rico
Token ID16707
Feature activation+9.83e-02

Pos logit contributions
amental+0.112
enders+0.111
vas+0.098
 vac+0.098
NJ+0.097
Neg logit contributions
stab-0.177
achelor-0.162
RED-0.162
ifiable-0.161
 Brah-0.161
Token,
Token ID11
Feature activation-7.92e-04

Pos logit contributions
amental+0.063
enders+0.062
 vac+0.057
vas+0.057
NJ+0.056
Neg logit contributions
stab-0.075
achelor-0.068
RED-0.068
ifiable-0.067
 Brah-0.067
Tokent
Token ID83
Feature activation-4.77e-04

Pos logit contributions
amental+0.001
enders+0.001
vas+0.001
 vac+0.001
NJ+0.001
Neg logit contributions
stab-0.001
achelor-0.001
RED-0.001
ifiable-0.001
 Brah-0.001
Token see
Token ID766
Feature activation-4.22e-03

Pos logit contributions
stab+0.000
achelor+0.000
RED+0.000
ifiable+0.000
 Brah+0.000
Neg logit contributions
amental-0.000
enders-0.000
vas-0.000
 vac-0.000
NJ-0.000
Token that
Token ID326
Feature activation-5.35e-03

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
 vac-0.002
vas-0.002
NJ-0.002
Token in
Token ID287
Feature activation-9.87e-03

Pos logit contributions
stab+0.004
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.004
enders-0.004
vas-0.003
 vac-0.003
NJ-0.003
Token the
Token ID262
Feature activation-4.38e-03

Pos logit contributions
stab+0.008
RED+0.007
achelor+0.007
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.006
enders-0.006
vas-0.005
 vac-0.005
NJ-0.005
Token States
Token ID1829
Feature activation-3.07e-01

Pos logit contributions
stab+0.003
achelor+0.003
RED+0.003
ifiable+0.003
 Brah+0.003
Neg logit contributions
amental-0.003
enders-0.003
vas-0.003
 vac-0.003
NJ-0.003
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
stab+0.224
achelor+0.203
RED+0.203
ifiable+0.200
 Brah+0.200
Neg logit contributions
amental-0.204
enders-0.203
vas-0.185
 vac-0.184
NJ-0.183
Token The
Token ID383
Feature activation+1.57e-02

Pos logit contributions
stab+0.008
achelor+0.007
RED+0.007
ifiable+0.007
 Brah+0.007
Neg logit contributions
amental-0.007
enders-0.007
vas-0.007
 vac-0.007
NJ-0.007
Token manager
Token ID4706
Feature activation-3.03e-02

Pos logit contributions
amental+0.011
enders+0.010
vas+0.010
 vac+0.010
NJ+0.009
Neg logit contributions
stab-0.011
achelor-0.010
RED-0.010
ifiable-0.010
 Brah-0.010
Token can
Token ID460
Feature activation+6.35e-03

Pos logit contributions
stab+0.023
achelor+0.021
RED+0.021
ifiable+0.021
 Brah+0.021
Neg logit contributions
amental-0.019
enders-0.019
vas-0.017
 vac-0.017
NJ-0.017
Token say
Token ID910
Feature activation+2.08e-02

Pos logit contributions
amental+0.004
enders+0.004
 vac+0.004
vas+0.004
 wax+0.004
Neg logit contributions
stab-0.005
achelor-0.004
RED-0.004
ifiable-0.004
 Brah-0.004
Token they
Token ID484
Feature activation-2.19e-02

Pos logit contributions
stab+0.018
achelor+0.016
RED+0.016
ifiable+0.016
 Brah+0.016
Neg logit contributions
amental-0.017
enders-0.017
vas-0.015
 vac-0.015
NJ-0.015
Token were
Token ID547
Feature activation+7.72e-03

Pos logit contributions
stab+0.017
RED+0.015
achelor+0.015
ifiable+0.015
 Brah+0.015
Neg logit contributions
amental-0.014
enders-0.014
 vac-0.013
vas-0.013
NJ-0.013
Token
Token ID564
Feature activation-9.32e-03

Pos logit contributions
amental+0.006
enders+0.005
 vac+0.005
vas+0.005
 wax+0.005
Neg logit contributions
stab-0.005
RED-0.005
achelor-0.005
 Brah-0.005
ifiable-0.005
Token
Token ID250
Feature activation-6.84e-03

Pos logit contributions
stab+0.006
achelor+0.006
RED+0.006
ifiable+0.006
 Brah+0.006
Neg logit contributions
amental-0.007
enders-0.006
vas-0.006
 vac-0.006
NJ-0.006
Tokens
Token ID82
Feature activation-2.12e-02

Pos logit contributions
stab+0.005
achelor+0.005
RED+0.005
 Brah+0.005
ifiable+0.005
Neg logit contributions
amental-0.004
enders-0.004
vas-0.004
 vac-0.004
NJ-0.004
Tokenomew
Token ID28030
Feature activation-2.96e-01

Pos logit contributions
stab+0.011
achelor+0.009
RED+0.009
ifiable+0.009
 Brah+0.009
Neg logit contributions
amental-0.019
enders-0.019
vas-0.018
 vac-0.018
NJ-0.017
Tokenhat
Token ID5183
Feature activation+3.83e-02

Pos logit contributions
stab+0.234
achelor+0.214
RED+0.212
ifiable+0.211
 Brah+0.210
Neg logit contributions
amental-0.179
enders-0.177
 vac-0.161
vas-0.160
NJ-0.159
Token satisfied
Token ID11378
Feature activation-8.06e-02

Pos logit contributions
amental+0.029
enders+0.029
vas+0.027
 vac+0.027
NJ+0.027
Neg logit contributions
stab-0.024
achelor-0.022
RED-0.022
ifiable-0.021
 Brah-0.021
Token.
Token ID13
Feature activation-7.88e-03

Pos logit contributions
stab+0.060
achelor+0.055
RED+0.054
ifiable+0.054
 Brah+0.054
Neg logit contributions
amental-0.053
enders-0.052
vas-0.047
 vac-0.047
NJ-0.047
Token
Token ID447
Feature activation-3.55e-03

Pos logit contributions
stab+0.006
RED+0.005
achelor+0.005
 Brah+0.005
ifiable+0.005
Neg logit contributions
amental-0.005
enders-0.005
vas-0.005
 vac-0.005
NJ-0.005
Token
Token ID251
Feature activation+6.41e-03

Pos logit contributions
stab+0.002
achelor+0.002
RED+0.002
ifiable+0.002
 Brah+0.002
Neg logit contributions
amental-0.002
enders-0.002
vas-0.002
 vac-0.002
NJ-0.002