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

    Neuronpedia

    INDEX
    Explanations

    keywords related to communication and sharing experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anza
    -0.16
    ãģ¤ãģ¶
    -0.15
     Santa
    -0.15
    dr
    -0.14
    mith
    -0.13
     respectively
    -0.13
    (TM
    -0.13
     pa
    -0.13
    /rss
    -0.13
    anus
    -0.13
    POSITIVE LOGITS
     cui
    0.18
    which
    0.17
     Which
    0.17
     which
    0.16
     cuales
    0.15
    claimer
    0.14
    Which
    0.14
    cem
    0.14
    dag
    0.14
     denen
    0.14
    Act Density 0.114%

    No Known Activations