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

    Neuronpedia

    INDEX
    Explanations

    mathematical structures and formatting in aligned equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betreft
    -0.64
     specialty
    -0.60
    őben
    -0.56
     specialize
    -0.55
     specialization
    -0.55
    ッケージ
    -0.55
    gruß
    -0.54
    kaŭ
    -0.54
     Special
    -0.54
     czeko
    -0.53
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.76
     sus
    0.71
    كويكب
    0.67
    eseorang
    0.67
     Wikimedijinoj
    0.66
     Administrativna
    0.63
     betweenstory
    0.63
    UTRAL
    0.62
     tưởng
    0.62
    EndGlobalSection
    0.62
    Act Density 0.070%

    No Known Activations