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

    Neuronpedia

    INDEX
    Explanations

    words related to audits or auditing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to auditing and oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.75
    TON
    -0.72
    xual
    -0.70
    ulkan
    -0.69
    ña
    -0.67
    OPLE
    -0.65
    tons
    -0.64
    WAYS
    -0.63
    terday
    -0.62
    ULAR
    -0.61
    POSITIVE LOGITS
    iov
    1.29
    acious
    1.24
    itors
    1.19
    ience
    1.18
    acity
    1.17
    iences
    1.14
    yssey
    1.12
    iology
    1.10
    ibly
    1.10
    aciously
    1.09
    Act Density 0.023%

    No Known Activations