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

    Neuronpedia

    INDEX
    Explanations

    words related to countries or territories

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "men" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VICE
    -0.82
    RAY
    -0.74
     Pwr
    -0.71
    Dog
    -0.70
    ENC
    -0.70
    BILL
    -0.69
    NEY
    -0.67
    GRE
    -0.65
    TOP
    -0.63
    Berry
    -0.63
    POSITIVE LOGITS
    opausal
    1.21
    uscript
    1.06
    endez
    0.98
    gling
    0.97
    stru
    0.95
    thren
    0.94
    士
    0.93
    volent
    0.91
    istan
    0.90
    emen
    0.84
    Act Density 0.019%

    No Known Activations