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

    Neuronpedia

    INDEX
    Explanations

    words indicating uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸įäºĨ
    -0.15
    uma
    -0.14
    ighth
    -0.14
    usa
    -0.14
    ASTER
    -0.13
    ấp
    -0.13
    æĹĹ
    -0.13
     Basin
    -0.13
    iap
    -0.13
    не
    -0.13
    POSITIVE LOGITS
     even
    0.28
     sogar
    0.22
    even
    0.20
     даже
    0.19
    /pro
    0.19
     навÑĸÑĤÑĮ
    0.17
    -even
    0.17
     même
    0.16
     incluso
    0.16
     EVEN
    0.16
    Act Density 0.044%

    No Known Activations