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

    Neuronpedia

    INDEX
    Explanations

    the presence of comment endings in code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AsUp
    -0.73
     blanches
    -0.71
     Whitehead
    -0.65
     noires
    -0.64
    logy
    -0.63
     Marqu
    -0.63
     negras
    -0.63
    BooleanField
    -0.62
    ậc
    -0.61
    vlád
    -0.60
    POSITIVE LOGITS
    awtextra
    0.85
    MessageTagHelper
    0.85
    strptime
    0.83
     */
    0.82
     Garvey
    0.81
    ussis
    0.79
    findpost
    0.75
     Parc
    0.73
    </u>
    0.73
    оз
    0.70
    Act Density 0.014%

    No Known Activations