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

    Neuronpedia

    INDEX
    Explanations

    patterns or pattern-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of patterns and pattern-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omez
    -0.80
    ascular
    -0.75
    venture
    -0.68
    zona
    -0.68
    rican
    -0.67
    assing
    -0.66
    phies
    -0.66
    ULTS
    -0.66
    =-=-=-=-
    -0.65
    UGE
    -0.64
    POSITIVE LOGITS
    gradient
    0.89
     Pattern
    0.86
     pattern
    0.85
    pattern
    0.85
    Pattern
    0.81
     patterns
    0.80
     repeats
    0.78
     Patterns
    0.77
    ĸļ
    0.75
    icity
    0.75
    Act Density 0.036%

    No Known Activations