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

    Neuronpedia

    INDEX
    Explanations

    the words containing "out" or "outs"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "out" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.95
    avorite
    -0.71
    itational
    -0.68
     misunder
    -0.67
    EStream
    -0.64
    interstitial
    -0.64
    ãĥŁ
    -0.60
    maxwell
    -0.60
     tyr
    -0.59
    oreal
    -0.59
    POSITIVE LOGITS
    dated
    1.07
    doors
    0.99
    raged
    0.97
    lier
    0.96
    door
    0.94
    stretched
    0.93
    lined
    0.93
    breaks
    0.93
    come
    0.92
    fitted
    0.92
    Act Density 0.045%

    No Known Activations