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

    Neuronpedia

    INDEX
    Explanations

    emotions and reactions related to events or situations, such as disbelief, horror, relief, amazement, and indignation

    oai_token-act-pair · gpt-3.5-turbo

    emotions related to disbelief, horror, and surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lav
    -0.73
    oln
    -0.70
    ulia
    -0.69
    users
    -0.67
    aceutical
    -0.65
     Fighters
    -0.61
    orie
    -0.61
    roots
    -0.61
    illary
    -0.59
    nice
    -0.59
    POSITIVE LOGITS
     disbelief
    1.11
     recalling
    0.99
     amaz
    0.97
     wondering
    0.95
     incred
    0.95
     exclaim
    0.91
     realizing
    0.90
     helpless
    0.88
     laughter
    0.88
     knowing
    0.84
    Act Density 0.204%

    No Known Activations