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

    Neuronpedia

    INDEX
    Explanations

    graphics processing units (GPUs) names and models

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications related to graphics cards and their models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icity
    -0.81
    atively
    -0.80
    cially
    -0.78
    glass
    -0.75
     Debor
    -0.74
    sonian
    -0.74
    biz
    -0.72
    chy
    -0.72
    Interstitial
    -0.71
    ically
    -0.70
    POSITIVE LOGITS
     1070
    0.94
     1080
    0.87
     460
    0.86
     580
    0.86
     470
    0.82
     570
    0.82
     680
    0.81
     480
    0.80
    ĪĴ
    0.77
     760
    0.75
    Act Density 0.059%

    No Known Activations