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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing confidence or assurance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vert
    -0.75
    pmwiki
    -0.70
    sites
    -0.67
     UCHIJ
    -0.66
    mes
    -0.65
     grievances
    -0.62
    kay
    -0.61
    */(
    -0.61
    zie
    -0.60
     hitch
    -0.60
    POSITIVE LOGITS
    ially
    1.19
    iated
    0.94
    ively
    0.87
     enough
    0.84
    iably
    0.82
    ieth
    0.76
    worthiness
    0.75
    worthy
    0.72
    ius
    0.71
    iable
    0.71
    Act Density 0.039%

    No Known Activations