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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "confidence"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confidence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.92
    sites
    -0.81
    shows
    -0.76
    xon
    -0.73
    HEAD
    -0.68
    ĻĤ
    -0.67
    oxide
    -0.66
    á½
    -0.65
    dos
    -0.65
    Vert
    -0.65
    POSITIVE LOGITS
    worthiness
    1.12
     assurance
    0.87
     intervals
    0.85
     confidence
    0.84
    iliate
    0.83
    worthy
    0.78
    lessly
    0.77
     interval
    0.72
    fulness
    0.71
    full
    0.70
    Act Density 0.018%

    No Known Activations