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

    Neuronpedia

    INDEX
    Explanations

    mathematical references and notation related to theories and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     elucid
    -0.18
    imb
    -0.14
    indow
    -0.14
    _iterations
    -0.13
    Entered
    -0.13
    etrofit
    -0.13
    odox
    -0.13
     Diagram
    -0.13
    Exited
    -0.12
    ÑĢÑĥÑĪ
    -0.12
    POSITIVE LOGITS
     introdu
    0.23
     showed
    0.23
     proposed
    0.23
     propose
    0.22
     intro
    0.22
     pointed
    0.21
     introduce
    0.21
     introduced
    0.21
     develop
    0.20
     Introduced
    0.20
    Act Density 0.089%

    No Known Activations