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

    Neuronpedia

    INDEX
    Explanations

    uses of quotation marks and apostrophes

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

    quote marks followed by subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bourhood
    -0.35
    UnsafeEnabled
    -0.34
     arquitectura
    -0.34
    Vapour
    -0.34
     cristianismo
    -0.34
    humour
    -0.34
     MainAxisSize
    -0.34
     zdravot
    -0.33
     Gesundheits
    -0.33
    æv
    -0.32
    POSITIVE LOGITS
    ⓧ
    0.61
    rawDesc
    0.57
     poffible
    0.56
     aDecoder
    0.56
    tric
    0.54
     tric
    0.54
    allible
    0.53
     vic
    0.52
    ValueStyle
    0.52
    idlertid
    0.52
    Act Density 0.009%

    No Known Activations