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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "test" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of tests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.80
    etheless
    -0.80
    ignt
    -0.73
    ĺħ
    -0.67
    resent
    -0.66
    nown
    -0.65
    vironment
    -0.65
    SOURCE
    -0.65
    taboola
    -0.65
    vernment
    -0.65
    POSITIVE LOGITS
    osterone
    1.43
    imony
    1.29
    imon
    1.08
    icular
    1.04
    icles
    1.03
    udo
    1.01
    ifies
    0.94
    icle
    0.93
    aments
    0.84
    su
    0.79
    Act Density 0.030%

    No Known Activations