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

    Neuronpedia

    INDEX
    Explanations

    references to sacrificial practices and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lies
    -0.17
    oro
    -0.16
    OrCreate
    -0.16
     dors
    -0.14
    TL
    -0.14
    467
    -0.14
    OrNull
    -0.13
    aff
    -0.13
    ially
    -0.13
    _gem
    -0.13
    POSITIVE LOGITS
    utzer
    0.15
    çĬ
    0.14
    ìĸij
    0.14
    deck
    0.14
     Dew
    0.14
    924
    0.14
    itag
    0.14
    راÙĨÙĩ
    0.14
    \Framework
    0.14
     vess
    0.14
    Act Density 0.031%

    No Known Activations