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

    Neuronpedia

    INDEX
    Explanations

    references to categories, specifically related to organization or classification of entities, including people and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yaz
    -0.16
    लत
    -0.16
     Yard
    -0.16
    æ¦
    -0.16
     Yates
    -0.15
    aires
    -0.15
    yles
    -0.15
     Dame
    -0.15
    ÏĦÏī
    -0.15
     Ri
    -0.14
    POSITIVE LOGITS
    ÑģÑĥ
    0.26
    ny
    0.24
    ry
    0.24
    hy
    0.23
    eyJ
    0.23
    try
    0.23
    py
    0.22
    sy
    0.22
    by
    0.22
    dry
    0.21
    Act Density 0.131%

    No Known Activations