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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and inquiries directed at the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å·
    -0.18
    thern
    -0.14
     meiden
    -0.14
    ãģĺãĤĥ
    -0.14
    jan
    -0.14
    orse
    -0.14
    ylan
    -0.14
    ymous
    -0.14
    ión
    -0.13
    icens
    -0.13
    POSITIVE LOGITS
    vester
    0.16
    FixedSize
    0.16
    梨
    0.15
    lep
    0.15
    endale
    0.14
    ãĥĮ
    0.13
    æĬķ注
    0.13
    ucer
    0.13
    Ļ¨
    0.13
    elas
    0.13
    Act Density 0.081%

    No Known Activations