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

    Neuronpedia

    INDEX
    Explanations

    references to the alphabet and individual letters within it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akh
    -0.16
    лоÑĩ
    -0.15
     Lew
    -0.15
    pNet
    -0.14
     numbered
    -0.14
    /auto
    -0.14
    oil
    -0.14
     chorus
    -0.13
     gcd
    -0.13
    raq
    -0.13
    POSITIVE LOGITS
     letter
    0.33
     letters
    0.30
    letter
    0.28
    _letter
    0.27
    -letter
    0.27
    letters
    0.26
     Letter
    0.26
    Letter
    0.25
     LETTER
    0.24
     Letters
    0.24
    Act Density 0.097%

    No Known Activations