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

    Neuronpedia

    INDEX
    Explanations

    words related to surprise or shock

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Runner
    -0.85
    aunder
    -0.72
    iatrics
    -0.72
     teasp
    -0.69
    trap
    -0.69
    eva
    -0.68
    ractor
    -0.68
    ettle
    -0.68
    alde
    -0.68
    ourage
    -0.67
    POSITIVE LOGITS
    products
    1.04
     nature
    0.79
     what
    0.75
     how
    0.73
     virtue
    0.71
    product
    0.66
     Sapp
    0.64
     sheer
    0.64
     whatever
    0.64
     these
    0.64
    Act Density 0.060%

    No Known Activations