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

    Neuronpedia

    INDEX
    Explanations

    metrics related to energy efficiency and performance calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isel
    -0.16
    icorn
    -0.16
    füg
    -0.14
    æ¦ľ
    -0.14
    arte
    -0.14
    raham
    -0.14
    æ²Ļ
    -0.14
    vt
    -0.14
     automát
    -0.13
    <?↵
    -0.13
    POSITIVE LOGITS
     mas
    0.15
     det
    0.15
    ulace
    0.14
     expr
    0.14
    å¤ļå°ij
    0.14
     Lever
    0.14
    è¡¡
    0.14
     Convention
    0.14
    sky
    0.14
     res
    0.13
    Act Density 0.084%

    No Known Activations