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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or" and related phrasing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aries
    -0.18
    lev
    -0.18
    UNET
    -0.15
    nt
    -0.15
     Jarvis
    -0.15
    izar
    -0.15
    ln
    -0.14
    oid
    -0.14
    ency
    -0.14
    Variable
    -0.14
    POSITIVE LOGITS
    /OR
    0.15
    phan
    0.14
     vice
    0.14
    _|
    0.14
    acket
    0.14
    oard
    0.14
    hra
    0.14
    drs
    0.14
    eneg
    0.14
    DataURL
    0.14
    Act Density 0.008%

    No Known Activations