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

    Neuronpedia

    INDEX
    Explanations

    elements related to fonts and their rendering in digital typography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ขา
    -0.78
    eqn
    -0.78
    上
    -0.76
    дца
    -0.75
    upy
    -0.75
    ペン
    -0.75
    ชา
    -0.75
      
    -0.73
    ณา
    -0.72
    ‌ی
    -0.72
    POSITIVE LOGITS
    s
    2.58
    ات
    1.20
    sah
    1.09
    ים
    1.08
    ی
    1.02
    ︎
    1.02
    sted
    1.00
    ся
    0.92
    sth
    0.91
    sly
    0.91
    Act Density 1.422%

    No Known Activations