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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Obama."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the string "ama"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ting
    -0.90
    ted
    -0.86
    tle
    -0.78
    points
    -0.74
    lip
    -0.73
    ried
    -0.73
    inav
    -0.71
    ther
    -0.71
    working
    -0.70
    sheet
    -0.70
    POSITIVE LOGITS
    qua
    0.99
    ña
    0.95
    ñ
    0.95
    utra
    0.94
    ican
    0.90
    eus
    0.87
    ama
    0.84
    zzle
    0.82
    emn
    0.82
    é¾įåĸļ士
    0.81
    Act Density 0.021%

    No Known Activations