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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ěl
    -0.56
    Skocz
    -0.53
    [++
    -0.53
    必
    -0.53
     decisione
    -0.52
     couverts
    -0.51
    aarrggbb
    -0.51
    gnan
    -0.51
     mété
    -0.50
     umane
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.73
    awtextra
    0.68
    inghouse
    0.60
    KommentareTeilen
    0.60
    Zeneca
    0.59
    Carriera
    0.58
    〕
    0.58
    oa̍t
    0.57
     ویکی‌پدیا
    0.57
    󠁿
    0.57
    Act Density 0.109%

    No Known Activations