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

    Neuronpedia

    INDEX
    Explanations

    sequences of colons and other symbols that might denote code or structured programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.18
    ongs
    -0.16
    fos
    -0.15
    .LookAndFeel
    -0.15
    ints
    -0.15
    igg
    -0.15
    ãĤ¢
    -0.14
    oretical
    -0.14
    ãĥŀ
    -0.14
    ãĤ¢ãĥĭãĥ¡
    -0.14
    POSITIVE LOGITS
    osate
    0.16
    ìļ±
    0.15
    npos
    0.14
    tte
    0.14
    анка
    0.14
    ayette
    0.14
    rosse
    0.14
    YLeaf
    0.14
    endale
    0.13
    å¦Ļ
    0.13
    Act Density 0.012%

    No Known Activations