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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific experiments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "experiment" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    headers
    -0.66
    othy
    -0.65
    ACP
    -0.63
    roots
    -0.63
    cut
    -0.62
    doms
    -0.60
    miah
    -0.59
    CHAPTER
    -0.59
    ACTED
    -0.59
    clinton
    -0.58
    POSITIVE LOGITS
    imental
    1.04
    iments
    1.01
    iment
    0.86
     Experiment
    0.85
    ally
    0.84
     experiment
    0.83
    onom
    0.77
    ually
    0.73
    eers
    0.73
     experimenting
    0.73
    Act Density 0.025%

    No Known Activations