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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and their references in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.67
     âmes
    -0.62
    ContentAsync
    -0.61
     polegadas
    -0.60
     pengar
    -0.59
     secoli
    -0.58
     obstante
    -0.58
    gulama
    -0.56
     abstrato
    -0.56
    \{\\
    -0.56
    POSITIVE LOGITS
    $_['
    0.67
    /***/
    0.65
     cherchés
    0.61
     his
    0.58
    inflater
    0.57
    Geplaatst
    0.57
     himself
    0.56
     dad
    0.54
    his
    0.54
    HtmlAttribute
    0.51
    Act Density 0.227%

    No Known Activations