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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.95
     Paglinawan
    -0.80
    liceerd
    -0.72
    хьтан
    -0.69
     חיצוניים
    -0.69
    WriteLiteral
    -0.67
     незавершена
    -0.67
    Cordialement
    -0.66
    itsubishi
    -0.63
     '\\;'
    -0.63
    POSITIVE LOGITS
    اصله
    0.53
    Diweddarwch
    0.53
     évidence
    0.49
     sacks
    0.48
     Persönlichkeit
    0.47
    ModelState
    0.47
    RequestMapping
    0.47
    èces
    0.46
    sort
    0.46
     crusher
    0.45
    Act Density 0.105%

    No Known Activations