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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic or professional titles and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢай
    -0.16
    umnos
    -0.14
     Hod
    -0.14
    apult
    -0.14
    ctic
    -0.13
    Deque
    -0.13
    опÑĢоÑģ
    -0.13
    ield
    -0.13
    ilian
    -0.13
    orf
    -0.13
    POSITIVE LOGITS
    dom
    0.19
    Ĩ
    0.16
    uffles
    0.15
    cobra
    0.15
    ä¹±
    0.15
    so
    0.15
    cház
    0.14
    Äįe
    0.14
    isher
    0.14
    reesome
    0.14
    Act Density 0.016%

    No Known Activations