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

    Neuronpedia

    INDEX
    Explanations

    names, particularly those of historical or prominent figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leak
    -0.17
    aper
    -0.16
    íķŃ
    -0.15
    ÑĥÑĢа
    -0.15
    ãĥ¼ãĤ
    -0.15
    ãĥ¨
    -0.15
    æ©
    -0.14
     reint
    -0.14
    ãĥ§
    -0.14
    .ColumnHeader
    -0.14
    POSITIVE LOGITS
    isses
    0.17
    avage
    0.16
    ogg
    0.15
    erville
    0.15
    itter
    0.15
    amp
    0.15
    atk
    0.15
    leh
    0.14
    altar
    0.14
    ritis
    0.14
    Act Density 0.030%

    No Known Activations