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

    Neuronpedia

    INDEX
    Explanations

    terminology related to legal or ethical violations and misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osg
    -0.18
    xing
    -0.17
    'gc
    -0.16
    yr
    -0.15
    ois
    -0.15
     Traverse
    -0.15
    _notifier
    -0.15
     Howell
    -0.15
    ending
    -0.14
    dio
    -0.14
    POSITIVE LOGITS
    forth
    0.16
    505
    0.15
    ive
    0.15
    ADF
    0.14
    åĻ¨
    0.13
    odor
    0.13
    forward
    0.13
    imento
    0.13
    ucu
    0.13
    rea
    0.13
    Act Density 0.008%

    No Known Activations