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

    Neuronpedia

    INDEX
    Explanations

    the concept of "facts" or factual statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.72
    ArgsConstructor
    -0.70
    SourceChecksum
    -0.70
    NameInMap
    -0.68
     endforeach
    -0.66
    PathVariable
    -0.66
    oa̍t
    -0.65
    GeneratedValue
    -0.64
     glaub
    -0.64
    Personendaten
    -0.63
    POSITIVE LOGITS
    menuStrip
    0.65
    ्यालय
    0.56
    ations
    0.53
    doa
    0.52
     PMS
    0.50
    Anima
    0.50
    alve
    0.50
     langu
    0.50
     Marquette
    0.50
     Mart
    0.50
    Act Density 0.010%

    No Known Activations