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

    Neuronpedia

    INDEX
    Explanations

    words related to trust and assurance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "confidence."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.88
    xon
    -0.75
    oxide
    -0.72
    Vert
    -0.72
    HEAD
    -0.72
    sites
    -0.71
    dos
    -0.70
    Kin
    -0.68
    shows
    -0.66
    ESH
    -0.66
    POSITIVE LOGITS
    worthiness
    1.26
     intervals
    0.91
    lessly
    0.87
    iliate
    0.83
    worthy
    0.81
     assurance
    0.79
     interval
    0.78
    fulness
    0.76
    lessness
    0.75
     confidence
    0.72
    Act Density 0.024%

    No Known Activations