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

    Neuronpedia

    INDEX
    Explanations

    instances of slashes used for punctuation or notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHANT
    -0.13
    eres
    -0.13
    _LICENSE
    -0.12
    aze
    -0.12
    riz
    -0.12
    ľ
    -0.12
    Ĵáŀ
    -0.12
    Äł
    -0.12
    eddar
    -0.11
     sice
    -0.11
    POSITIVE LOGITS
    ients
    0.25
    /OR
    0.21
    ifice
    0.20
    /or
    0.18
    /-
    0.18
    \/\/
    0.17
    /=
    0.16
    ï¸ı
    0.15
    ucch
    0.15
    acles
    0.15
    Act Density 0.123%

    No Known Activations