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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific word, likely "Swing"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sw" and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.69
    EStream
    -0.69
    66666666
    -0.68
     theater
    -0.66
     withholding
    -0.64
    代
    -0.64
    cised
    -0.64
     partial
    -0.64
     cigarettes
    -0.64
    vre
    -0.62
    POSITIVE LOGITS
    addle
    1.10
    inton
    1.08
    imming
    1.05
    indle
    1.05
    immer
    1.04
    ollen
    1.03
    artz
    1.03
    ifty
    1.03
    allows
    0.99
    allow
    0.99
    Act Density 0.005%

    No Known Activations