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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings or precautions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the token "Ca."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.87
     GOODMAN
    -0.80
    geist
    -0.79
    mble
    -0.77
    PDATE
    -0.75
    eering
    -0.75
    lings
    -0.71
    hof
    -0.71
    pocket
    -0.70
    bucks
    -0.70
    POSITIVE LOGITS
    esar
    1.31
    ption
    1.21
    ution
    1.04
    UTION
    0.95
    utes
    0.88
    utical
    0.83
    usa
    0.81
    idences
    0.81
    ursions
    0.79
    ibo
    0.79
    Act Density 0.019%

    No Known Activations