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

    Neuronpedia

    INDEX
    Explanations

    events or actions that have occurred up to a certain point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a progression or status, particularly "so far."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovo
    -0.77
    uala
    -0.74
    urrent
    -0.70
    apixel
    -0.69
    vertising
    -0.69
    onut
    -0.68
    schild
    -0.67
    ycle
    -0.67
    psey
    -0.67
    ounce
    -0.67
    POSITIVE LOGITS
    thing
    0.80
    ghan
    0.79
    fetched
    0.78
     awa
    0.77
     away
    0.73
     Ahead
    0.71
    away
    0.70
    Range
    0.69
     ahead
    0.69
     beyond
    0.68
    Act Density 0.027%

    No Known Activations