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

    Neuronpedia

    INDEX
    Explanations

    phrases related to privacy and confidential information

    oai_token-act-pair · gpt-3.5-turbo

    references to privacy and privileged information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grass
    -0.69
    LER
    -0.67
     Legion
    -0.65
     conver
    -0.64
    ORN
    -0.63
     Gentle
    -0.62
    eric
    -0.62
     spur
    -0.61
     composed
    -0.61
     composing
    -0.60
    POSITIVE LOGITS
    ilege
    1.75
    ileged
    1.62
    ately
    1.33
    acies
    1.31
    acy
    1.12
    aband
    1.09
    atile
    1.05
    atis
    0.98
    ilage
    0.98
    acist
    0.97
    Act Density 0.036%

    No Known Activations