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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or astonishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opath
    -0.77
    aker
    -0.75
    aldi
    -0.73
    atche
    -0.73
    odor
    -0.72
    oran
    -0.71
    reb
    -0.70
    ather
    -0.69
    ript
    -0.69
     ethic
    -0.68
    POSITIVE LOGITS
    ?!
    1.07
    ?:
    0.99
    ?,
    0.99
     Huh
    0.92
    .?
    0.90
    ??
    0.89
    ï¸ı
    0.87
    !?
    0.83
    @#
    0.82
    !!
    0.82
    Act Density 0.008%

    No Known Activations