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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their relationship to the surrounding text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipar
    -0.17
    wa
    -0.17
    ÑĮ
    -0.15
    onte
    -0.15
    cope
    -0.15
    inte
    -0.15
    urgence
    -0.14
    utilus
    -0.14
     wa
    -0.14
     Euras
    -0.14
    POSITIVE LOGITS
    Exited
    0.15
    olean
    0.14
    ause
    0.14
    Statics
    0.14
    Authenticated
    0.14
    LOCKS
    0.13
    .inflate
    0.13
    vertisement
    0.13
    Ïĥαν
    0.13
    ÑģÑĤика
    0.13
    Act Density 0.244%

    No Known Activations