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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to analysis and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inkel
    -0.17
    ataka
    -0.17
    516
    -0.15
    INA
    -0.14
     spam
    -0.14
    ycz
    -0.14
     charter
    -0.13
    fusion
    -0.13
    utherford
    -0.13
    oni
    -0.13
    POSITIVE LOGITS
     Millet
    0.16
    quia
    0.16
    cola
    0.15
    olan
    0.15
    bras
    0.14
    elo
    0.14
    queda
    0.14
    ikel
    0.14
    -men
    0.14
     Hammond
    0.14
    Act Density 0.028%

    No Known Activations