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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intensity or significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llor
    -0.73
    LOG
    -0.66
    irl
    -0.63
     compat
    -0.61
    lynn
    -0.59
    BUG
    -0.59
    ghost
    -0.57
    EngineDebug
    -0.57
    DEM
    -0.56
     Advertisement
    -0.56
    POSITIVE LOGITS
    animate
    1.04
    organic
    1.03
    ordinate
    1.00
    clusions
    0.96
    humane
    0.96
    efficiency
    0.94
    patient
    0.92
    clusively
    0.91
    effic
    0.91
    offensive
    0.89
    Act Density 0.244%

    No Known Activations