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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or terms related to a specified or particular context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BIL
    -0.80
    oil
    -0.78
    prints
    -0.77
    OIL
    -0.76
    IDS
    -0.76
    gu
    -0.76
    bane
    -0.75
    atis
    -0.75
    keepers
    -0.75
    adders
    -0.74
    POSITIVE LOGITS
     amount
    0.77
     quarter
    0.76
     mood
    0.75
     individual
    0.75
     location
    0.73
     week
    0.72
     tense
    0.71
     sized
    0.71
     timeframe
    0.71
     day
    0.70
    Act Density 8.622%

    No Known Activations