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

    Neuronpedia

    INDEX
    Explanations

    terms related to technicality and formality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.90
    #
    -0.68
     devenus
    -0.62
     regionales
    -0.61
    גרפיה
    -0.58
    Bakgrunnsstoff
    -0.57
     debout
    -0.57
    ruptedException
    -0.57
    horts
    -0.56
     passés
    -0.56
    POSITIVE LOGITS
     nominally
    0.89
     nominal
    0.77
    NameInMap
    0.72
     superfic
    0.68
     ceremony
    0.68
     outwardly
    0.67
     formality
    0.67
     superficial
    0.65
     ceremonial
    0.63
    nominal
    0.63
    Act Density 0.324%

    No Known Activations