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

    Neuronpedia

    INDEX
    Explanations

    numbers in a specific range indicated by hyphens

    oai_token-act-pair · gpt-3.5-turbo

    negative values or references to losses in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Boone
    -0.91
     Dickinson
    -0.89
    ulhu
    -0.89
     Yelp
    -0.88
     Lovecraft
    -0.87
     Burr
    -0.85
     Scrib
    -0.84
     Whitman
    -0.84
     Jefferson
    -0.80
     Indiana
    -0.79
    POSITIVE LOGITS
    backed
    1.07
    turned
    1.04
    based
    1.03
    linked
    1.02
    shaped
    1.02
    organ
    1.01
    colour
    0.97
    equipped
    0.97
    ridden
    0.96
    shoot
    0.96
    Act Density 0.256%

    No Known Activations