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

    Neuronpedia

    INDEX
    Explanations

    references to various aspects or elements in a discussion or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dy
    -0.16
    nze
    -0.15
    esco
    -0.15
    sz
    -0.15
    rup
    -0.15
    DonaldTrump
    -0.15
    ses
    -0.14
    space
    -0.14
    rado
    -0.14
    ernels
    -0.14
    POSITIVE LOGITS
    pects
    0.17
    aland
    0.16
    aspect
    0.15
    ake
    0.15
    ioc
    0.15
    Uniform
    0.14
    alone
    0.14
     aspect
    0.14
    ihar
    0.14
    dns
    0.14
    Act Density 0.026%

    No Known Activations