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

    Neuronpedia

    INDEX
    Explanations

    activities related to social interactions and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _mapper
    -0.15
    agas
    -0.15
    à¥įà¤
    -0.15
    ãĤ¹ãĤ«
    -0.14
    roker
    -0.14
    åł¡
    -0.14
    utting
    -0.14
    when
    -0.13
    utr
    -0.13
    еÑĢÑĤи
    -0.13
    POSITIVE LOGITS
    åIJĦç§į
    0.15
    ÎŃν
    0.13
     comet
    0.13
    istically
    0.13
    ContentAlignment
    0.13
     DISCLAIMER
    0.13
    Various
    0.13
     sor
    0.13
     altern
    0.13
     quietly
    0.13
    Act Density 0.170%

    No Known Activations