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

    Neuronpedia

    INDEX
    Explanations

    words related to confidence and assurance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confidence and trust levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.91
    sites
    -0.86
    HEAD
    -0.77
    Vert
    -0.74
    shows
    -0.73
    xon
    -0.71
    artifacts
    -0.67
    mentioned
    -0.67
    Kin
    -0.66
    apple
    -0.66
    POSITIVE LOGITS
    worthiness
    1.06
     confidence
    0.92
     assurance
    0.90
     intervals
    0.87
    iliate
    0.80
     dividend
    0.73
     confident
    0.73
     interval
    0.72
    worthy
    0.72
    irming
    0.71
    Act Density 0.019%

    No Known Activations