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

    Neuronpedia

    INDEX
    Explanations

    questions or queries beginning with "What."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    getic
    -0.16
    -0.16
    jem
    -0.15
    ól
    -0.15
    OKIE
    -0.14
    VICES
    -0.14
    111
    -0.14
    uze
    -0.14
    ishments
    -0.14
    unda
    -0.14
    POSITIVE LOGITS
    soever
    0.23
    teg
    0.18
    arton
    0.18
    SOEVER
    0.17
    reme
    0.15
    Fld
    0.15
    npos
    0.14
    resh
    0.14
    xis
    0.14
    еление
    0.14
    Act Density 0.058%

    No Known Activations