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

    Neuronpedia

    INDEX
    Explanations

    large numerical quantities and statistics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    apses
    -0.59
     trave
    -0.56
    AppData
    -0.54
    apsed
    -0.52
    WARE
    -0.52
    apers
    -0.52
     clicks
    -0.51
    cash
    -0.50
    DATA
    -0.49
    OFF
    -0.49
    POSITIVE LOGITS
     327
    0.80
     310
    0.80
     231
    0.79
     328
    0.78
     360
    0.77
     670
    0.77
     230
    0.76
     350
    0.76
     343
    0.76
     352
    0.76
    Act Density 0.138%

    No Known Activations