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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to smartphone processors and memory

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications of electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACTIONS
    -0.79
    tsy
    -0.76
    vernment
    -0.69
    ople
    -0.68
    geries
    -0.66
    ertain
    -0.66
    versive
    -0.66
    xious
    -0.66
    bart
    -0.64
     Incident
    -0.64
    POSITIVE LOGITS
     powering
    1.07
     boasting
    1.02
     paired
    1.01
     coupled
    0.96
     plus
    0.91
     chipset
    0.91
     bundled
    0.91
     configured
    0.90
     capable
    0.87
     delivering
    0.87
    Act Density 0.187%

    No Known Activations