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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ApplicationDbContext
    -0.15
    باØŃ
    -0.15
    iedo
    -0.15
    ymes
    -0.14
    oph
    -0.14
    491
    -0.14
    igu
    -0.14
    onas
    -0.13
    ÑĥÑĤи
    -0.13
    endor
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥį
    0.16
    lez
    0.15
    vez
    0.14
    .qml
    0.14
    voke
    0.14
     dames
    0.14
     Lage
    0.14
    reen
    0.14
     nomine
    0.13
    bulk
    0.13
    Act Density 0.007%

    No Known Activations