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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in code-like text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leone
    -0.58
    出版年
    -0.56
     cucchiaio
    -0.53
    اذ
    -0.50
    Sai
    -0.49
     spoons
    -0.49
     Laj
    -0.49
    Hippo
    -0.47
    himu
    -0.47
     Hippo
    -0.47
    POSITIVE LOGITS
     Eight
    1.17
     eight
    1.14
    eight
    1.00
     Eighty
    0.99
     eighty
    0.99
     eighth
    0.95
    Eight
    0.94
     EIGHT
    0.92
     Eighth
    0.91
     oito
    0.87
    Act Density 0.210%

    No Known Activations