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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "conduct."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "conduct" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     msec
    -0.68
     Dise
    -0.66
    inka
    -0.65
     Nightmares
    -0.65
    corn
    -0.64
     berth
    -0.63
    cube
    -0.63
    LOAD
    -0.63
    cial
    -0.63
    iewicz
    -0.62
    POSITIVE LOGITS
    ors
    1.09
    ivity
    1.02
    uations
    0.97
    ional
    0.86
    onduct
    0.84
    ions
    0.83
     err
    0.78
    ivities
    0.77
    ORS
    0.77
    ities
    0.76
    Act Density 0.033%

    No Known Activations