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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving numerical values and thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holm
    -0.15
    åIJĽ
    -0.14
    hee
    -0.14
     aff
    -0.14
    urgeon
    -0.14
     zemi
    -0.14
    itzer
    -0.14
    iting
    -0.13
    stone
    -0.13
     ham
    -0.13
    POSITIVE LOGITS
    uzzi
    0.18
    hang
    0.17
    ange
    0.16
     certain
    0.15
    ä¸Ģå®ļ
    0.15
    äºİ
    0.15
    anda
    0.15
     threshold
    0.15
    ëĿ¼ìĿ¸
    0.14
    quin
    0.14
    Act Density 0.202%

    No Known Activations