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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or necessity of decisions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oproject
    -0.14
    .isNotEmpty
    -0.14
     ÙĤر
    -0.14
     Ä
    -0.13
     Ug
    -0.13
     ucz
    -0.13
    aths
    -0.13
    ums
    -0.13
     Bris
    -0.13
    angel
    -0.13
    POSITIVE LOGITS
     been
    0.47
    been
    0.35
     Been
    0.31
    Been
    0.29
     sido
    0.29
     BEEN
    0.28
     été
    0.25
     бÑĭÑĤÑĮ
    0.23
     zosta
    0.22
     be
    0.21
    Act Density 0.088%

    No Known Activations