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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.18
    ehler
    -0.17
     Recorded
    -0.16
     McKenzie
    -0.15
    648
    -0.15
    iska
    -0.15
    ắng
    -0.15
    apot
    -0.15
    ñana
    -0.14
    Ïģα
    -0.14
    POSITIVE LOGITS
    еви
    0.15
    oard
    0.15
    orex
    0.15
    elen
    0.15
    urr
    0.14
    edia
    0.14
    .require
    0.14
    Ñıк
    0.14
    SEO
    0.14
    rust
    0.13
    Act Density 0.254%

    No Known Activations