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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating responsibility or accountability for actions, especially in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bcryptjs
    -0.59
     Drapeau
    -0.58
    tdessen
    -0.53
    :✨
    -0.52
    SharedCtor
    -0.51
     scuole
    -0.50
     waarop
    -0.50
     متعلقه
    -0.49
    خابات
    -0.49
     necesariamente
    -0.48
    POSITIVE LOGITS
     responsible
    0.70
     blame
    0.69
    blame
    0.68
     authorship
    0.68
    responsible
    0.68
     responsibility
    0.65
     BoxDecoration
    0.64
    cataly
    0.64
     responsable
    0.64
    AnimationsModule
    0.59
    Act Density 0.387%

    No Known Activations