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

    Neuronpedia

    INDEX
    Explanations

    patterns in various contexts, including gameplay instructions, visual design elements, and social discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    omez
    -0.83
    ascular
    -0.80
    phies
    -0.71
    UGH
    -0.70
    rican
    -0.68
    IVERS
    -0.66
    amina
    -0.66
    zona
    -0.65
    ayson
    -0.65
    venture
    -0.64
    POSITIVE LOGITS
     pattern
    0.97
     Pattern
    0.93
    pattern
    0.93
     patterns
    0.92
    gradient
    0.89
    Pattern
    0.88
     Patterns
    0.87
    eering
    0.81
    ĸļ
    0.78
     repeats
    0.77
    Act Density 0.047%

    No Known Activations