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

    Neuronpedia

    INDEX
    Explanations

    references to body-related terms and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /latest
    -0.17
    erie
    -0.17
    ion
    -0.16
    stagram
    -0.14
    liž
    -0.14
    anium
    -0.14
    enberg
    -0.14
    nen
    -0.14
    lej
    -0.14
    ery
    -0.14
    POSITIVE LOGITS
    guards
    0.26
    guard
    0.23
    wide
    0.19
    builders
    0.18
    weight
    0.18
    oley
    0.18
     politic
    0.17
    builder
    0.17
    é¨ĵ
    0.17
    eo
    0.16
    Act Density 0.046%

    No Known Activations