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

    Neuronpedia

    INDEX
    Explanations

    terms related to engineering and technical fields

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of engines or engineering terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dos
    -0.89
    giving
    -0.82
    ities
    -0.75
    guyen
    -0.71
    berra
    -0.71
    laus
    -0.71
     Jagu
    -0.70
    ctuary
    -0.70
    ITY
    -0.68
    apa
    -0.67
    POSITIVE LOGITS
    ered
    1.03
     Engine
    1.01
    Engine
    0.81
    engine
    0.80
    breaker
    0.73
    ering
    0.73
    ugal
    0.73
    stration
    0.71
    iHUD
    0.71
    rued
    0.70
    Act Density 0.011%

    No Known Activations