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

    Neuronpedia

    INDEX
    Explanations

    exclamatory expressions and strong emotional language

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exting
    -0.77
     eleph
    -0.77
    senal
    -0.77
    aditional
    -0.72
     Skydragon
    -0.66
     oun
    -0.66
     pione
    -0.65
    ò
    -0.64
    ThumbnailImage
    -0.63
     citiz
    -0.63
    POSITIVE LOGITS
    Reward
    0.65
    ³³³
    0.63
    "}],"
    0.63
    âĶĢâĶĢâĶĢâĶĢ
    0.63
    ------
    0.62
    \":
    0.62
    ↵
    0.61
    Yep
    0.61
    Í
    0.60
    lol
    0.60
    Act Density 0.803%

    No Known Activations