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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.84
     disambiguazione
    -0.80
    స్తు
    -0.79
     continúas
    -0.77
    GEBURTSDATUM
    -0.75
    دانشنامهٔ
    -0.72
    вік
    -0.71
    expandindo
    -0.71
    évaluateur
    -0.70
    estes
    -0.70
    POSITIVE LOGITS
     CURLOPT
    0.67
    álva
    0.62
     aanges
    0.60
    ็จ
    0.60
    føl
    0.59
    jącego
    0.59
    勿論
    0.58
    页面存档备份
    0.58
    󠁢
    0.58
     pudieran
    0.58
    Act Density 0.020%

    No Known Activations