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

    Neuronpedia

    INDEX
    Explanations

    references to smoking or its effects

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.75
    Cyfeiriadau
    -0.73
    Gön
    -0.70
    ApiModel
    -0.68
    ########.
    -0.68
    ValueStyle
    -0.68
    XtraEditors
    -0.66
    providedIn
    -0.66
    PARATUS
    -0.63
     nahilalakip
    -0.63
    POSITIVE LOGITS
    transQ
    0.45
     entanto
    0.45
    izarea
    0.42
    </b>
    0.42
     daarbij
    0.41
     specifically
    0.40
     numerus
    0.39
     totiž
    0.39
    mord
    0.39
    ";}
    0.39
    Act Density 0.422%

    No Known Activations