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

    Neuronpedia

    INDEX
    Explanations

    references to patterns in various contexts

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

    pattern recognition and generators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :]:
    -0.54
    windowFixed
    -0.53
    chränk
    -0.51
    
    -0.50
     hydrostatic
    -0.49
     Wohnzimmer
    -0.47
    raltar
    -0.47
    без
    -0.46
    chloric
    -0.46
     noOf
    -0.45
    POSITIVE LOGITS
     pattern
    1.81
    pattern
    1.76
     Pattern
    1.71
    Pattern
    1.66
     PATTERN
    1.57
     patterns
    1.41
    PATTERN
    1.40
     Patterns
    1.29
    patterns
    1.12
    Patterns
    1.10
    Act Density 0.014%

    No Known Activations