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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "used" is followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "used" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignt
    -0.77
    bitious
    -0.67
     undertaking
    -0.67
    antle
    -0.65
    merce
    -0.65
     defic
    -0.64
     4090
    -0.64
    mire
    -0.62
    llah
    -0.62
    Draft
    -0.62
    POSITIVE LOGITS
    fully
    1.03
    FUL
    0.94
    fulness
    0.85
     condoms
    0.82
     sparing
    0.82
    ãĥ¼ãĥĨãĤ£
    0.71
     borrowed
    0.70
    ful
    0.65
     techniques
    0.64
     extensively
    0.63
    Act Density 0.075%

    No Known Activations