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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly those associated with leadership or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kla
    -0.17
    عاÙĨ
    -0.16
    apis
    -0.16
    uesta
    -0.15
    END
    -0.15
    ONA
    -0.14
    áp
    -0.14
    Millis
    -0.14
    _endpoint
    -0.13
     pair
    -0.13
    POSITIVE LOGITS
    utz
    0.20
    nu
    0.16
    ieren
    0.15
    lez
    0.15
    haf
    0.15
    ridged
    0.15
    ustom
    0.14
    GLOBALS
    0.14
    iggers
    0.14
    ADED
    0.14
    Act Density 0.010%

    No Known Activations