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

    Neuronpedia

    INDEX
    Explanations

    references to scientific methods and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikipédia
    -0.60
    oa̍t
    -0.55
    breit
    -0.45
    (['/
    -0.45
    anyway
    -0.43
    omeness
    -0.42
     menye
    -0.42
    leyici
    -0.41
    Anyways
    -0.40
    ropathy
    -0.38
    POSITIVE LOGITS
     مشين
    0.84
     Dabei
    0.76
    paravant
    0.73
     Specifically
    0.73
    Dabei
    0.69
    RTLR
    0.69
     betweenstory
    0.69
     darin
    0.69
     onPostExecute
    0.68
     includes
    0.68
    Act Density 0.789%

    No Known Activations