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

    Neuronpedia

    INDEX
    Explanations

    references to specific points, issues, or topics in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     simply
    -0.15
    TextNode
    -0.14
    anford
    -0.14
    åĢŁ
    -0.14
    924
    -0.14
    лÑı
    -0.14
    &R
    -0.14
    aleigh
    -0.13
    ắm
    -0.13
    αÏģά
    -0.13
    POSITIVE LOGITS
     another
    0.21
     indeed
    0.19
    another
    0.18
    Another
    0.18
     Another
    0.18
     Indeed
    0.17
    Indeed
    0.17
    Speaking
    0.17
    inde
    0.16
     ëĺIJ
    0.16
    Act Density 0.065%

    No Known Activations