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

    Neuronpedia

    INDEX
    Explanations

    legal terms and conditions in an agreement or legal document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    daj
    -0.60
     AssemblyCompany
    -0.60
     mostly
    -0.57
     now
    -0.56
     Ternyata
    -0.55
    mostly
    -0.54
    Mainly
    -0.54
    LayoutStyle
    -0.54
     ModelExpression
    -0.52
    Mostly
    -0.51
    POSITIVE LOGITS
     shall
    0.85
    shall
    0.78
     Any
    0.77
    Any
    0.76
     any
    0.75
     NSCoder
    0.72
     eventuali
    0.71
    任何人
    0.70
     failure
    0.70
    setVerticalGroup
    0.69
    Act Density 0.341%

    No Known Activations