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

    Neuronpedia

    INDEX
    Explanations

    evaluative language used to express opinions and caveats about information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LEAR
    -0.16
    aber
    -0.15
     Phot
    -0.15
    ern
    -0.14
    ERN
    -0.14
     dán
    -0.14
    uben
    -0.13
    cel
    -0.13
    throp
    -0.13
    Å¡ÃŃ
    -0.13
    POSITIVE LOGITS
     Cave
    0.24
     cave
    0.23
     disclaimer
    0.23
     caveat
    0.21
     cautioned
    0.18
     caution
    0.17
     Disclaimer
    0.16
     ca
    0.16
     qualifications
    0.16
     quali
    0.16
    Act Density 0.117%

    No Known Activations