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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols from non-Latin scripts, particularly focusing on their frequency and arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PENS
    -0.71
    ########.
    -0.63
     Italijani
    -0.60
     DETERMIN
    -0.59
    okovic
    -0.59
     թվ
    -0.56
     sorte
    -0.56
    ё
    -0.56
     FIL
    -0.55
     sou
    -0.54
    POSITIVE LOGITS
     BorderRadius
    0.89
    Ārējās
    0.73
    அ
    0.67
    theilung
    0.67
    Czytaj
    0.66
    இ
    0.65
     അ
    0.64
     მ
    0.63
     MainAxisSize
    0.62
    polation
    0.62
    Act Density 0.011%

    No Known Activations