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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords that denote classes and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .synthetic
    -0.18
    ATALOG
    -0.16
     Kov
    -0.15
    æ¹
    -0.14
    EATURE
    -0.14
     proven
    -0.14
    nice
    -0.14
    à¸Ńà¸Ķ
    -0.13
    unei
    -0.13
    .xxx
    -0.13
    POSITIVE LOGITS
     Solution
    0.18
    =”
    0.16
    .arm
    0.15
    LR
    0.15
    hte
    0.15
    voy
    0.15
    ÙĪاÙĦ
    0.14
     LR
    0.14
    inha
    0.14
     Ashe
    0.14
    Act Density 0.206%

    No Known Activations