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

    Neuronpedia

    INDEX
    Explanations

    references to linguistic systems and alphabets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     verb
    -0.16
     verbs
    -0.16
    esi
    -0.15
     synonyms
    -0.15
     comma
    -0.14
    Themes
    -0.14
    indy
    -0.14
    keyword
    -0.14
    comma
    -0.14
     term
    -0.14
    POSITIVE LOGITS
     пиÑģÑĮмен
    0.20
     writing
    0.19
     letters
    0.19
     written
    0.18
     Writing
    0.18
     orth
    0.18
    abcdefghijklmnopqrstuvwxyz
    0.17
    Writing
    0.17
     Write
    0.17
     alphabet
    0.17
    Act Density 0.070%

    No Known Activations