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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shadow
    -0.15
     Grass
    -0.14
    let
    -0.14
    ier
    -0.14
    ikut
    -0.13
    ARSE
    -0.13
    isine
    -0.13
    oha
    -0.13
     unb
    -0.13
     muj
    -0.13
    POSITIVE LOGITS
    ramer
    0.16
     mie
    0.15
    aya
    0.15
    readcr
    0.15
    éģķ
    0.14
     Kramer
    0.14
    DMI
    0.14
    -floating
    0.13
     Å¡ÃŃ
    0.13
     ô
    0.13
    Act Density 0.011%

    No Known Activations