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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or processes that are about to take place

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate preparation or actions to take before a certain event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Offline
    -0.72
     Cosponsors
    -0.72
    ccording
    -0.70
     notwithstanding
    -0.68
     millenn
    -0.67
    bryce
    -0.65
    <?
    -0.63
     discrep
    -0.63
     contrasted
    -0.61
     Notwithstanding
    -0.60
    POSITIVE LOGITS
    isode
    0.80
    ividual
    0.75
    uberty
    0.72
    erno
    0.72
     anymore
    0.70
    eme
    0.69
    icter
    0.68
    irlf
    0.67
    shed
    0.66
     recomm
    0.65
    Act Density 0.221%

    No Known Activations