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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names associated with individuals, particularly in academic or professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    коз
    -0.16
    cky
    -0.15
    ngo
    -0.15
    Ïģιά
    -0.15
    ÃŃas
    -0.15
    EDA
    -0.15
    illas
    -0.15
    tings
    -0.14
    flix
    -0.14
    action
    -0.14
    POSITIVE LOGITS
    zelf
    0.23
    ity
    0.18
    itä
    0.17
    Ùħار
    0.17
    Å¡Å¥
    0.17
    zsche
    0.17
    ele
    0.17
    annel
    0.16
    cé
    0.16
    cy
    0.16
    Act Density 0.334%

    No Known Activations