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

    Neuronpedia

    INDEX
    Explanations

    references to a central or organizing concept within a system or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NING
    -0.17
    ned
    -0.17
    izers
    -0.15
    .toolbox
    -0.15
    enticate
    -0.15
    èīĩ
    -0.15
    UrlParser
    -0.15
    tainment
    -0.15
    uper
    -0.15
    chwitz
    -0.14
    POSITIVE LOGITS
    bing
    0.27
    spot
    0.21
    bers
    0.21
    ungi
    0.20
    lot
    0.20
    bs
    0.20
    let
    0.20
     Hub
    0.19
    bed
    0.19
    ris
    0.18
    Act Density 0.009%

    No Known Activations