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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics related to serious societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favorably
    -1.06
     favor
    -0.99
     favored
    -0.93
     honors
    -0.90
     subsidized
    -0.89
     favoring
    -0.88
     favors
    -0.87
     willfully
    -0.85
     caliber
    -0.84
     flavors
    -0.83
    POSITIVE LOGITS
    However
    1.60
    Labour
    1.57
    Speaking
    1.54
    Scotland
    1.49
    BBC
    1.48
    Shape
    1.43
    Scroll
    1.43
    Mr
    1.41
    Professor
    1.41
    Writing
    1.41
    Act Density 0.414%

    No Known Activations