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

    Neuronpedia

    INDEX
    Explanations

    symbols and markers indicating measurement or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    celik
    -0.15
    -toggler
    -0.15
    createClass
    -0.14
    нки
    -0.14
    nable
    -0.14
    avig
    -0.13
    avan
    -0.13
     reverted
    -0.13
    plural
    -0.13
    sell
    -0.13
    POSITIVE LOGITS
     proc
    0.27
     obtained
    0.25
     acquired
    0.23
     attract
    0.23
     Obt
    0.23
     attracted
    0.23
     pay
    0.22
     attracts
    0.22
    proc
    0.22
     acquisition
    0.21
    Act Density 0.016%

    No Known Activations