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

    Neuronpedia

    INDEX
    Explanations

    adjectives conveying certainty or strength, such as "indisputable", "unequivocal", "unquestionably"

    oai_token-act-pair · gpt-3.5-turbo

    words indicating certainty or undeniable truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.70
     Hunting
    -0.69
     Solitaire
    -0.68
     dust
    -0.67
     Wolves
    -0.64
     baths
    -0.62
     Slug
    -0.62
     Stru
    -0.62
     Dust
    -0.62
     brainstorm
    -0.61
    POSITIVE LOGITS
    uously
    1.14
    ensibly
    1.07
    herent
    1.07
    inately
    1.06
    uably
    1.05
    resent
    1.03
    ensible
    1.03
    aturally
    1.02
    ibly
    1.01
    putable
    1.00
    Act Density 0.050%

    No Known Activations