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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "possibly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eries
    -0.83
    elson
    -0.78
    lins
    -0.77
    raint
    -0.76
    board
    -0.76
    raged
    -0.74
    oren
    -0.74
    oven
    -0.74
    yer
    -0.74
    rend
    -0.74
    POSITIVE LOGITS
     someday
    0.78
     infer
    0.78
     mistaken
    0.75
     jeopard
    0.74
     misunder
    0.74
     contam
    0.74
     conclud
    0.73
     forgiven
    0.71
    interstitial
    0.71
     hint
    0.71
    Act Density 0.018%

    No Known Activations