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

    Neuronpedia

    INDEX
    Explanations

    terms related to oversight and quality control in reporting systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idis
    -0.17
    motion
    -0.15
    aign
    -0.15
    á»Ĩ
    -0.15
    agem
    -0.15
    اسÙĬØ©
    -0.14
     __("
    -0.14
     Bast
    -0.14
    BarItem
    -0.14
    avers
    -0.14
    POSITIVE LOGITS
     Treasury
    0.15
    jed
    0.15
     risks
    0.15
    .Dto
    0.14
     dipl
    0.14
    arten
    0.14
    warts
    0.13
    æ··
    0.13
    rng
    0.13
    136
    0.13
    Act Density 0.002%

    No Known Activations