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

    Neuronpedia

    INDEX
    Explanations

    concepts related to naturalness and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.60
    rometry
    -0.44
    AntiForgeryToken
    -0.43
    awtextra
    -0.42
     natural
    -0.41
    natural
    -0.40
    MIDDLEWARE
    -0.40
    nasional
    -0.39
    ViewImports
    -0.39
     натура
    -0.38
    POSITIVE LOGITS
     occurring
    0.85
    occurring
    0.73
     disasters
    0.63
     born
    0.58
     Occur
    0.57
     Born
    0.57
     BORN
    0.55
    Born
    0.55
     occurrence
    0.54
     Feinde
    0.54
    Act Density 0.244%

    No Known Activations