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

    Neuronpedia

    INDEX
    Explanations

    geographic indicators, particularly directional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦει
    -0.15
    utory
    -0.14
    pery
    -0.14
    alice
    -0.14
    Wunused
    -0.14
     sm
    -0.14
    retain
    -0.14
     Pic
    -0.14
    ãĥ¼ãĥIJ
    -0.13
     satur
    -0.13
    POSITIVE LOGITS
    lla
    0.17
    åѦä¼ļ
    0.16
    >manual
    0.15
    обов
    0.15
    ób
    0.15
    оби
    0.15
    :\/\/
    0.15
     Brun
    0.14
    disp
    0.14
    lopen
    0.14
    Act Density 0.025%

    No Known Activations