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

    Neuronpedia

    INDEX
    Explanations

    references to patterns and their characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.49
    Autoritní
    -0.46
    tisone
    -0.45
     >=",
    -0.45
     mulut
    -0.44
     TimeUnit
    -0.44
     Autorisations
    -0.44
    usitis
    -0.44
    PMailer
    -0.42
     evoc
    -0.41
    POSITIVE LOGITS
     pattern
    1.94
     Pattern
    1.81
    pattern
    1.79
     patterns
    1.77
    Pattern
    1.77
     PATTERN
    1.72
     Patterns
    1.70
    patterns
    1.59
    Patterns
    1.57
    PATTERN
    1.53
    Act Density 0.062%

    No Known Activations