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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    references to time or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.94
    Materials
    -0.73
     prospects
    -0.66
    _.
    -0.62
    iatures
    -0.59
    ();
    -0.59
     EDITION
    -0.58
     Dresden
    -0.58
     prospect
    -0.58
    Product
    -0.56
    POSITIVE LOGITS
     incorrectly
    0.84
     deficient
    0.79
    interrupted
    0.78
     ERROR
    0.78
     inconsistent
    0.75
     unfit
    0.74
     unsafe
    0.74
    reverse
    0.74
     incorrect
    0.74
    perfect
    0.74
    Act Density 1.073%

    No Known Activations