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

    Neuronpedia

    INDEX
    Explanations

    words related to auditing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to auditing and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.68
    TON
    -0.66
    tons
    -0.65
     Tend
    -0.62
    terday
    -0.61
     Ars
    -0.61
     Slug
    -0.60
    chairs
    -0.60
    ña
    -0.58
     Pearce
    -0.58
    POSITIVE LOGITS
    iov
    1.51
    itors
    1.38
    acity
    1.34
    ience
    1.33
    iences
    1.32
    iology
    1.29
    acious
    1.28
    iting
    1.26
    itions
    1.26
    yssey
    1.26
    Act Density 0.024%

    No Known Activations