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

    Neuronpedia

    INDEX
    Explanations

    words related to decisions being made

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "made"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sit
    -0.69
     ding
    -0.66
     decaying
    -0.66
     rotting
    -0.61
     stripes
    -0.60
     peppers
    -0.58
     bos
    -0.58
     wit
    -0.58
     grou
    -0.57
     striped
    -0.57
    POSITIVE LOGITS
    emort
    0.94
     sure
    0.86
    ensibly
    0.82
    gements
    0.79
    itives
    0.78
    urate
    0.78
    ezvous
    0.77
    awaru
    0.76
    oji
    0.76
    vious
    0.76
    Act Density 0.045%

    No Known Activations