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

    Neuronpedia

    INDEX
    Explanations

    specific legal phrases and terms relevant to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.64
     and
    -0.53
     ins
    -0.45
    ...
    -0.41
    ."
    -0.41
     Bel
    -0.41
     --
    -0.40
     especially
    -0.40
    anama
    -0.40
    ....
    -0.39
    POSITIVE LOGITS
     autorytatywna
    1.15
     незавершена
    0.90
     itſelf
    0.81
     שוליים
    0.80
     nahilalakip
    0.79
     ModelExpression
    0.77
    OGND
    0.76
     uſed
    0.76
     unknownFields
    0.76
     تضيفلها
    0.73
    Act Density 0.246%

    No Known Activations