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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and specific abbreviations used in data and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sign
    -0.51
     itse
    -0.51
     general
    -0.51
     pres
    -0.49
    appro
    -0.47
    bege
    -0.47
    prä
    -0.47
     kun
    -0.45
     исто
    -0.45
     internal
    -0.45
    POSITIVE LOGITS
    ########.
    0.88
    PYX
    0.83
    expandindo
    0.81
     disambiguazione
    0.79
     Administrativna
    0.79
    DrawerLayout
    0.79
    Pautan
    0.76
     Majefty
    0.76
    ⓘ
    0.75
    MLLoader
    0.75
    Act Density 0.359%

    No Known Activations