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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conformity and alignment

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in line."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CVE
    -1.01
    soever
    -0.79
    ilt
    -0.74
    rely
    -0.72
    NULL
    -0.71
    illed
    -0.68
    ¥µ
    -0.68
    »Ĵ
    -0.66
    AAAA
    -0.65
    wcs
    -0.63
    POSITIVE LOGITS
    backer
    0.88
    breakers
    0.86
    breaker
    0.76
    lines
    0.76
    naires
    0.74
    stad
    0.73
    ages
    0.72
    ups
    0.70
    ings
    0.69
    book
    0.68
    Act Density 0.025%

    No Known Activations