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

    Neuronpedia

    INDEX
    Explanations

    first occurrences or instances of events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or historic first occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riber
    -0.68
    sleep
    -0.68
    each
    -0.67
    plays
    -0.67
    ractor
    -0.67
    Ïī
    -0.64
    lag
    -0.64
    obby
    -0.64
    tics
    -0.63
    aths
    -0.63
    POSITIVE LOGITS
     foray
    1.05
     installment
    1.03
     thing
    0.97
     casualty
    0.97
     baseman
    0.96
     ever
    0.93
     responders
    0.92
     glimpse
    0.87
     indication
    0.86
     step
    0.83
    Act Density 0.070%

    No Known Activations