Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terminology related to legal offenses and their processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.24
     Monfieur
    -1.09
     Efq
    -1.08
     raiſ
    -1.07
     doubtnut
    -1.04
     leſs
    -1.04
     Forumite
    -1.03
     ſche
    -1.01
     myſelf
    -1.00
    ſelves
    -1.00
    POSITIVE LOGITS
     Off
    2.87
    Off
    2.53
     off
    2.48
    off
    2.29
     OFF
    2.27
    OFF
    2.07
    オフ
    1.57
     offender
    1.42
    offs
    1.40
     offs
    1.35
    Act Density 0.148%

    No Known Activations