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

    Neuronpedia

    INDEX
    Explanations

    dialogues and quotations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.62
     المعيارى
    -0.57
    Източници
    -0.55
    ".
    -0.51
    脚注の使い方
    -0.48
     StatelessWidget
    -0.48
     الحره
    -0.47
    ^{-}$
    -0.47
    ihnachten
    -0.46
     thai
    -0.46
    POSITIVE LOGITS
    Hey
    0.98
     Hey
    0.97
    Oh
    0.93
     Oh
    0.88
     hey
    0.80
    Hello
    0.75
    What
    0.75
    Sorry
    0.72
    HEY
    0.69
     What
    0.69
    Act Density 0.094%

    No Known Activations