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

    Neuronpedia

    INDEX
    Explanations

    mentions of extensive research or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ispers
    -0.19
    ses
    -0.18
    se
    -0.16
    heim
    -0.15
    ukkan
    -0.15
    bies
    -0.14
    lectric
    -0.14
    -call
    -0.14
    venes
    -0.14
    sworth
    -0.14
    POSITIVE LOGITS
     amounts
    0.24
    amount
    0.23
     amount
    0.20
    -scale
    0.18
     enough
    0.17
    ively
    0.17
    overlap
    0.17
    -ranging
    0.17
     Amount
    0.16
    -duty
    0.16
    Act Density 0.029%

    No Known Activations