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

    Neuronpedia

    INDEX
    Explanations

    mentions of software or technological actions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols used in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scattering
    -0.75
     dividing
    -0.72
     Glou
    -0.70
     rooting
    -0.68
     scatter
    -0.67
     multiplying
    -0.66
     Nam
    -0.66
     Mayo
    -0.66
     gad
    -0.65
     swept
    -0.65
    POSITIVE LOGITS
    º
    1.17
    ¹
    1.12
    ¡
    1.08
    Į
    1.04
    ¬
    1.04
    »
    1.03
    £
    1.02
    į
    1.01
    §
    1.00
    ı
    0.97
    Act Density 0.556%

    No Known Activations