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

    Neuronpedia

    INDEX
    Explanations

    instances of negations or qualifiers emphasizing importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĩ
    -0.18
    ancode
    -0.17
    ptime
    -0.16
    llen
    -0.15
    ilee
    -0.15
    rox
    -0.14
    ì°¨
    -0.14
    quier
    -0.14
     Miner
    -0.14
     Alto
    -0.14
    POSITIVE LOGITS
    artz
    0.15
    awn
    0.15
    asics
    0.15
    æ³³
    0.14
    eller
    0.14
    ru
    0.13
    chalk
    0.13
    _floor
    0.13
     SetProperty
    0.13
    eds
    0.13
    Act Density 0.023%

    No Known Activations