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

    Neuronpedia

    INDEX
    Explanations

    phrases related to integration and interaction in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.69
     uſed
    -0.69
     purpoſe
    -0.66
     sphinx
    -0.66
     pleaſure
    -0.63
     Addis
    -0.63
     raiſ
    -0.61
     himſelf
    -0.61
     Atiku
    -0.60
     houſe
    -0.60
    POSITIVE LOGITS
     OF
    1.19
    .}(
    1.13
     Of
    1.09
    .)}
    1.08
     the
    1.02
    Of
    0.92
     of
    0.91
    */
    0.90
    "])
    0.89
    )]{
    0.88
    Act Density 1.577%

    No Known Activations