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

    Neuronpedia

    INDEX
    Explanations

    words that begin with the prefix 'un-' indicating negation or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.51
     vectoriales
    -0.48
     autorytatywna
    -0.47
     Gedanke
    -0.45
     Schicksal
    -0.45
    ácara
    -0.44
    JvmStatic
    -0.44
     cervello
    -0.42
     magasiner
    -0.42
    发表于
    -0.41
    POSITIVE LOGITS
     un
    2.59
     Un
    2.48
    Un
    2.28
     unre
    2.03
     uns
    2.02
    un
    1.99
     Uns
    1.99
     UN
    1.94
     unt
    1.91
     unc
    1.87
    Act Density 0.859%

    No Known Activations