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

    Neuronpedia

    INDEX
    Explanations

    key technical terms and jargon related to technology and software development

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Hours
    -0.87
     ÂŃ
    -0.76
    leased
    -0.75
    ãĥĹ
    -0.71
    pleted
    -0.71
    sylv
    -0.71
    Washington
    -0.70
    vernight
    -0.70
     Adolf
    -0.69
    Thousands
    -0.68
    POSITIVE LOGITS
     causation
    1.14
     specialization
    1.04
     concepts
    1.03
     terminology
    1.02
     abstraction
    1.02
     analogy
    1.01
     optimizing
    1.01
     complexity
    1.00
     optimization
    0.99
     definitions
    0.99
    Act Density 0.927%

    No Known Activations