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

    Neuronpedia

    INDEX
    Explanations

    expressions of authenticity and sincerity

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

    preceding adverbs like "truly" or "genuine"

    np_acts-logits-general · gemini-2.0-flash

    truth and genuineness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.73
    CloseOperation
    -0.71
    ients
    -0.70
    Билгалдахарш
    -0.69
    yntaxException
    -0.68
     ModelExpression
    -0.67
    pushFollow
    -0.66
    Smarty
    -0.65
    RectangleBorder
    -0.64
    InputBorder
    -0.63
    POSITIVE LOGITS
     truly
    0.74
     genuine
    0.72
    iramente
    0.70
    Truly
    0.64
     true
    0.61
     Truly
    0.61
     deep
    0.60
     prawdzi
    0.57
    truly
    0.57
     настоя
    0.55
    Act Density 0.125%

    No Known Activations