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

    Neuronpedia

    INDEX
    Explanations

    random combinations of characters with occasional Swedish words

    oai_token-act-pair · gpt-3.5-turbo

    linguistic patterns and elements related to the letter 'n'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukong
    -0.78
     convol
    -0.77
    yip
    -0.70
    ãĥĻ
    -0.68
     rook
    -0.66
    VW
    -0.63
    女
    -0.63
    caps
    -0.61
     clicks
    -0.61
     BCC
    -0.60
    POSITIVE LOGITS
    én
    0.85
    ó
    0.77
     Ãī
    0.77
    Ã
    0.77
     Ãĸ
    0.77
    ée
    0.77
     Ã
    0.76
    iste
    0.76
    é
    0.75
    Ä
    0.75
    Act Density 0.131%

    No Known Activations