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

    Neuronpedia

    INDEX
    Explanations

    references to hip-hop slang and music-related terminology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    atis
    -1.03
    kens
    -0.98
    anmar
    -0.83
    irez
    -0.79
    ICLE
    -0.78
    kok
    -0.76
    olkien
    -0.75
    gerald
    -0.75
    stad
    -0.74
    urn
    -0.73
    POSITIVE LOGITS
    \":
    0.75
     McAuliffe
    0.66
     Matters
    0.63
    onsense
    0.62
     causation
    0.62
     milliseconds
    0.61
    management
    0.60
     coordinate
    0.59
     dial
    0.59
     OCD
    0.58
    Act Density 0.158%

    No Known Activations