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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and features of hardware components

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and measurements related to computer hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gallup
    -0.86
     clenched
    -0.86
     Dickinson
    -0.79
     Norris
    -0.76
     NAACP
    -0.75
     Cato
    -0.71
     Pett
    -0.71
     Moreno
    -0.70
    ansas
    -0.70
     dissenting
    -0.68
    POSITIVE LOGITS
    compatible
    1.21
    level
    1.15
    based
    1.12
    device
    1.06
    package
    1.05
    enabled
    1.04
    exclusive
    1.03
    domain
    1.03
    powered
    1.02
    optim
    1.02
    Act Density 0.234%

    No Known Activations