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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a lack of or minimal presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.55
     препратки
    -0.48
    uchtigkeit
    -0.45
    atguigu
    -0.44
    ַי
    -0.43
    udahan
    -0.43
     *((
    -0.43
     podró
    -0.43
     périph
    -0.42
    TagMode
    -0.42
    POSITIVE LOGITS
     zero
    1.29
     completely
    1.25
     nonexistent
    1.17
     entirely
    1.14
     ZERO
    1.11
     totally
    1.07
    zero
    1.03
     Completely
    1.02
    completely
    1.02
    ゼロ
    0.99
    Act Density 0.610%

    No Known Activations