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

    Neuronpedia

    INDEX
    Explanations

    number sequences

    oai_token-act-pair · gpt-3.5-turbo

    numeric identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mast
    -0.73
    istically
    -0.73
    drawn
    -0.72
    stro
    -0.69
    board
    -0.69
    sterdam
    -0.69
    hol
    -0.69
    icial
    -0.67
    esville
    -0.67
    distance
    -0.66
    POSITIVE LOGITS
    ãĥ´ãĤ¡
    0.82
    ãĥķ
    0.82
    703
    0.76
     partName
    0.75
    qqa
    0.75
    uration
    0.75
    806
    0.74
    646
    0.74
    692
    0.73
    602
    0.73
    Act Density 0.073%

    No Known Activations