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

    Neuronpedia

    INDEX
    Explanations

    terms related to production and processing

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers or indicate transitions in content formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swat
    -0.78
    ayan
    -0.76
    urnal
    -0.72
     lat
    -0.70
    vous
    -0.68
     sisters
    -0.66
    inki
    -0.66
    izon
    -0.65
     scarf
    -0.65
    uddin
    -0.65
    POSITIVE LOGITS
     readiness
    0.79
     Extras
    0.77
    flows
    0.71
     downstream
    0.70
     guiActiveUnfocused
    0.69
    artifacts
    0.67
    Performance
    0.67
     IQ
    0.66
     Performance
    0.66
     DVD
    0.66
    Act Density 0.714%

    No Known Activations