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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atti
    -0.17
    lobs
    -0.15
    Dirs
    -0.15
     McGregor
    -0.15
    attr
    -0.14
    abee
    -0.14
    ATTR
    -0.14
    ëŀį
    -0.14
    igg
    -0.13
    ensburg
    -0.13
    POSITIVE LOGITS
     inclusion
    0.16
     mus
    0.16
    plex
    0.15
    /topics
    0.15
    tf
    0.15
     Tier
    0.15
    WND
    0.14
    errat
    0.14
    QUIRE
    0.14
    tm
    0.14
    Act Density 0.038%

    No Known Activations