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

    Neuronpedia

    INDEX
    Explanations

    key terms and numbers related to scientific theories and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /release
    -0.15
    ordinate
    -0.15
    556
    -0.14
     seins
    -0.14
    ordin
    -0.13
    eldom
    -0.13
    zw
    -0.13
     rozh
    -0.13
    letal
    -0.13
    DataExchange
    -0.13
    POSITIVE LOGITS
     other
    0.19
     why
    0.19
     further
    0.19
     conclusion
    0.18
    Conclusion
    0.17
     how
    0.17
     bibli
    0.16
    ãģĿãģ®ä»ĸ
    0.15
     towards
    0.15
     examples
    0.15
    Act Density 0.071%

    No Known Activations