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

    Neuronpedia

    INDEX
    Explanations

    references to beneficial effects or outcomes

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    scriptcase
    -0.73
    azgo
    -0.72
    __*/
    -0.66
    migrationBuilder
    -0.65
    Parity
    -0.63
    QMetaType
    -0.63
     advantages
    -0.63
     sportback
    -0.63
    WritableDatabase
    -0.61
     advantage
    -0.61
    POSITIVE LOGITS
     beneficial
    2.11
     Beneficial
    2.02
    benef
    0.96
    Benef
    0.82
     BENEF
    0.76
     benefic
    0.73
    icial
    0.65
     béné
    0.63
     detrimental
    0.57
    contentLoaded
    0.56
    Act Density 0.001%

    No Known Activations