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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "non" or related prefixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.50
     Erwä
    -0.49
     Beschluss
    -0.48
    tagHelper
    -0.47
     betrekking
    -0.47
    ViewStyle
    -0.47
     izquier
    -0.46
     getTitle
    -0.46
     échanti
    -0.45
     Mayfield
    -0.43
    POSITIVE LOGITS
     Non
    1.31
     non
    1.29
    non
    1.17
    Non
    1.16
     NON
    1.06
    NON
    0.98
     Nons
    0.88
     Nong
    0.82
    nons
    0.82
     nons
    0.80
    Act Density 0.136%

    No Known Activations