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

    Neuronpedia

    INDEX
    Explanations

    keywords related to coding and programming concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to restrictions or limitations on usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     marqu
    -0.80
     Barth
    -0.78
    ylum
    -0.76
    arious
    -0.75
     Leviathan
    -0.70
     Kath
    -0.67
    Roberts
    -0.67
     Centauri
    -0.67
     Ralph
    -0.67
     Born
    -0.67
    POSITIVE LOGITS
     use
    1.96
     USE
    1.78
    use
    1.77
     Use
    1.72
     uses
    1.72
    Use
    1.65
     usage
    1.62
     Uses
    1.57
     used
    1.56
     utilize
    1.48
    Act Density 0.245%

    No Known Activations