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

    Neuronpedia

    INDEX
    Explanations

    the word "names" and variations or contexts of the term throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    157
    -0.19
    ahn
    -0.16
    ptal
    -0.15
    amaz
    -0.14
    å¥Ī
    -0.14
    ernaut
    -0.14
    963
    -0.14
    eshire
    -0.13
    елиÑĩ
    -0.13
    -span
    -0.13
    POSITIVE LOGITS
    .xz
    0.17
    .idea
    0.15
    ogne
    0.14
    лим
    0.14
    LogFile
    0.14
    æı
    0.14
    ázd
    0.14
     tumble
    0.14
    kommen
    0.14
    -urlencoded
    0.14
    Act Density 0.012%

    No Known Activations