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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain periods, indicating complete thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emble
    -0.17
    elles
    -0.17
    unic
    -0.16
    FFE
    -0.15
    rica
    -0.15
    azı
    -0.14
    bos
    -0.14
    ["@
    -0.14
     utter
    -0.14
    UIL
    -0.14
    POSITIVE LOGITS
    ickets
    0.15
    legate
    0.14
    tog
    0.14
    roduced
    0.13
     <*>
    0.13
    .predicate
    0.13
     /**<
    0.13
    _grp
    0.13
    ITA
    0.13
    OUSE
    0.13
    Act Density 0.099%

    No Known Activations