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

    Neuronpedia

    INDEX
    Explanations

    content that provides guidance or helpful advice on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Synopsis
    -0.15
     Duis
    -0.15
    ussion
    -0.15
    ãĥ³ãĤ¯
    -0.15
     Guth
    -0.14
     Commentary
    -0.14
    пеÑĩ
    -0.14
     vign
    -0.14
    ùi
    -0.14
     pau
    -0.14
    POSITIVE LOGITS
     guide
    0.45
    guide
    0.37
    -guide
    0.35
     guides
    0.34
     Guide
    0.34
     handy
    0.31
    Guide
    0.29
    _guide
    0.28
     GUIDE
    0.27
     Guides
    0.25
    Act Density 0.176%

    No Known Activations