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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer programming and technology

    oai_token-act-pair · gpt-3.5-turbo

    specific terminology related to mechanics, legality, and technical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cale
    -0.83
    creen
    -0.78
    icter
    -0.78
    ounding
    -0.76
    imentary
    -0.76
    maxwell
    -0.75
    risome
    -0.75
    ervative
    -0.75
    untled
    -0.75
    outhern
    -0.73
    POSITIVE LOGITS
    ages
    0.87
    lets
    0.81
    aires
    0.81
     syndrome
    0.78
     holders
    0.78
    backs
    0.77
    lies
    0.76
    eers
    0.76
    ings
    0.74
    agers
    0.74
    Act Density 0.789%

    No Known Activations