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

    Neuronpedia

    INDEX
    Explanations

    expressions related to scientific experiments

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nergy
    -0.68
    corruption
    -0.66
    othy
    -0.65
    MET
    -0.64
    partisan
    -0.63
    olulu
    -0.63
    flush
    -0.62
    lining
    -0.62
    miah
    -0.60
    games
    -0.59
    POSITIVE LOGITS
    imental
    1.08
     Experiment
    1.07
     experiment
    0.99
    iments
    0.99
    iment
    0.97
    ually
    0.88
    eers
    0.86
     experimented
    0.84
    uates
    0.83
    ally
    0.83
    Act Density 0.009%

    No Known Activations