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

    Neuronpedia

    INDEX
    Explanations

    references to legal definitions or legal terminology

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    Context
    -1.15
    ctx
    -1.06
    getContext
    -0.95
     ctx
    -0.85
    Ctx
    -0.83
    RuleContext
    -0.77
    CONTEXT
    -0.68
    context
    -0.68
     getContext
    -0.66
    CTX
    -0.63
    POSITIVE LOGITS
    unately
    0.62
     context
    0.61
    ViewChild
    0.60
     itſelf
    0.58
     fince
    0.58
     discussione
    0.56
     UPM
    0.56
     contexte
    0.54
     Jefus
    0.54
     excludes
    0.53
    Act Density 0.005%

    No Known Activations