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

    Neuronpedia

    INDEX
    Explanations

    different types of patterns and pattern-related terms

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

    pattern recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectMocks
    -0.57
    
    -0.52
    chränk
    -0.49
     Belf
    -0.49
     Wohnzimmer
    -0.47
     hydrostatic
    -0.45
     Luxe
    -0.44
    Deine
    -0.44
    ||}
    -0.44
    без
    -0.44
    POSITIVE LOGITS
     pattern
    1.20
     Pattern
    1.18
    pattern
    1.13
    Pattern
    1.10
     patterns
    1.07
     PATTERN
    1.07
     Patterns
    0.99
    PATTERN
    0.95
    Patterns
    0.85
    Patterson
    0.82
    Act Density 0.022%

    No Known Activations