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

    Neuronpedia

    INDEX
    Explanations

    the word "gee" with various intensities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "ee" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥķãĤ©
    -0.83
    iques
    -0.77
    ainer
    -0.77
    ĸļ
    -0.70
    icken
    -0.69
    urgical
    -0.68
    icity
    -0.67
    icks
    -0.67
    iferation
    -0.67
    ãĤ¤ãĥĪ
    -0.66
    POSITIVE LOGITS
    pee
    1.23
    ples
    1.10
    zy
    1.09
    zer
    1.05
    ves
    1.04
    pees
    1.03
    vers
    1.03
    bles
    1.02
    bies
    1.01
    gee
    1.00
    Act Density 0.067%

    No Known Activations