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

    Neuronpedia

    INDEX
    Explanations

    expressions of growth, progress, and positive achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gars
    -0.15
    ogs
    -0.15
    usra
    -0.15
     sav
    -0.14
    udded
    -0.14
     patch
    -0.14
    _patch
    -0.14
     rel
    -0.13
    hani
    -0.13
     +
    -0.13
    POSITIVE LOGITS
    uali
    0.16
    edata
    0.15
    .ReadOnly
    0.15
    vinc
    0.15
    ç«Ł
    0.14
    -gnu
    0.14
     cons
    0.14
    icons
    0.14
    ellipsis
    0.14
    upertino
    0.14
    Act Density 0.459%

    No Known Activations