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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or surprise

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

    interjections and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.61
    intios
    -0.59
     ویکی‌پدی
    -0.55
    istoitu
    -0.54
    Vidite
    -0.53
     ddelweddau
    -0.52
    ніципалі
    -0.51
     Houſe
    -0.51
    󠁣
    -0.49
    AccessorTable
    -0.49
    POSITIVE LOGITS
    !
    0.57
    ...
    0.42
     says
    0.40
     Ternyata
    0.40
    Sorry
    0.40
    we
    0.39
     Says
    0.39
    ๆ
    0.39
    osh
    0.38
    !...
    0.38
    Act Density 0.026%

    No Known Activations