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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal actions and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OnInit
    -0.43
    setObjectName
    -0.43
    adaptiveStyles
    -0.42
    SharedDtor
    -0.37
    awakeFromNib
    -0.37
     informée
    -0.37
     iprot
    -0.36
     canal
    -0.36
     وتسجيلات
    -0.36
    smithy
    -0.36
    POSITIVE LOGITS
    conian
    0.55
     restrictive
    0.48
     unjustly
    0.47
     кара
    0.47
     unreasonably
    0.47
     imposed
    0.46
     cruelly
    0.45
     prohibiting
    0.45
     Targeting
    0.45
     stricter
    0.45
    Act Density 0.956%

    No Known Activations