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

    Neuronpedia

    INDEX
    Explanations

    instances where something has not yet happened

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "has yet to" indicating something that hasn't occurred or been completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rities
    -0.74
    stories
    -0.65
    equality
    -0.65
    ï
    -0.65
     Journals
    -0.64
    current
    -0.63
    warts
    -0.63
    gnu
    -0.61
     Gems
    -0.60
    pointers
    -0.60
    POSITIVE LOGITS
     surpassed
    0.75
     been
    0.73
     hesitated
    0.68
     succumb
    0.68
    icia
    0.67
     officially
    0.67
     undergone
    0.66
     definitively
    0.65
     ruled
    0.65
    ijn
    0.64
    Act Density 0.017%

    No Known Activations