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

    Neuronpedia

    INDEX
    Explanations

    references to geographic and demographic information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arat
    -0.16
    gen
    -0.16
     Rox
    -0.15
    utherland
    -0.15
    دار
    -0.14
    ÏĨι
    -0.14
    بÙĨ
    -0.14
    astro
    -0.14
    ast
    -0.13
    emes
    -0.13
    POSITIVE LOGITS
    mbH
    0.15
    :↵↵
    0.14
     mens
    0.14
    égor
    0.14
    JM
    0.14
    :↵
    0.14
    ↵↵
    0.14
     |
    0.14
     according
    0.13
     :↵↵
    0.13
    Act Density 0.042%

    No Known Activations