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

    Neuronpedia

    INDEX
    Explanations

    dates and specific events or actions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey significant conclusions or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.62
    »Ĵ
    -0.59
     yells
    -0.58
    Dialogue
    -0.57
     brawl
    -0.57
     grit
    -0.57
     chron
    -0.55
    ounding
    -0.54
     pg
    -0.53
     bodily
    -0.53
    POSITIVE LOGITS
     However
    1.06
     But
    1.04
    but
    1.01
    However
    1.01
    But
    0.99
     Instead
    0.93
     Then
    0.89
    Instead
    0.87
     Now
    0.86
    until
    0.86
    Act Density 0.887%

    No Known Activations