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

    Neuronpedia

    INDEX
    Explanations

    dialogues and conversational markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    speaker or dialogue labels (names in all caps or followed by a colon) indicating who is speaking.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Negative Logits
     WEATHER
    -0.63
    onacci
    -0.60
    NOPQRST
    -0.58
    cipitation
    -0.56
    ++
    -0.56
     "}";
    -0.55
     GenerationType
    -0.55
    出版年
    -0.54
     Roskov
    -0.53
     فريبيس
    -0.53
    POSITIVE LOGITS
     дописавши
    0.72
    Yeah
    0.70
     Yeah
    0.63
     Which
    0.62
    Which
    0.62
     kaynağından
    0.62
     yeah
    0.61
     Namely
    0.61
    Yes
    0.60
    That
    0.58
    Act Density 0.052%

    No Known Activations