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

    Neuronpedia

    INDEX
    Explanations

    references to proportions or fractions, particularly "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    })));
    -0.87
    ="#"><
    -0.87
     odkazy
    -0.84
    Bibliographie
    -0.81
     وتسجيلات
    -0.79
     Meksiku
    -0.77
     للاسماء
    -0.77
    ")));
    -0.77
    ://"
    -0.76
    بوابة
    -0.75
    POSITIVE LOGITS
     half
    2.32
     Half
    2.15
    half
    2.11
    Half
    2.09
     HALF
    2.04
    HALF
    1.81
     halves
    1.61
    半
    1.34
     metade
    1.31
     halve
    1.29
    Act Density 0.037%

    No Known Activations