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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing legal obligations and evidence

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

    Followed by "is not" or similar negative phrases

    np_acts-logits-general · gemini-2.0-flash

    there is no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مراجع
    -0.45
    WHEREAS
    -0.44
    ագրություններ
    -0.43
     esboço
    -0.43
    nth
    -0.41
    くると
    -0.41
     aqu
    -0.41
    pflich
    -0.41
     Slayer
    -0.40
    Ooooo
    -0.40
    POSITIVE LOGITS
     صوتيه
    0.75
     المعيارى
    0.75
    expandindo
    0.75
    ьаж
    0.72
     ujednoznacz
    0.71
     الاطلاع
    0.66
     verrez
    0.65
    CardContent
    0.63
    الحياه
    0.63
    ArrowToggle
    0.62
    Act Density 0.406%

    No Known Activations