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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and technical terms related to software development and online platforms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    vironment
    -0.77
    icate
    -0.65
    icates
    -0.64
    icative
    -0.63
    icating
    -0.56
    icated
    -0.55
    ection
    -0.54
    eatures
    -0.54
    orial
    -0.53
    icals
    -0.53
    POSITIVE LOGITS
    starter
    0.67
    butt
    0.65
    gear
    0.62
    pole
    0.61
    rant
    0.58
    Daddy
    0.57
    Stack
    0.57
    assian
    0.57
    rier
    0.56
    mie
    0.56
    Act Density 5.872%

    No Known Activations