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

    Neuronpedia

    INDEX
    Explanations

    phrases related to establishing rules or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виправивши
    -0.79
    DoubleQuotes
    -0.79
    phism
    -0.77
    Personensuche
    -0.77
    tagHelperRunner
    -0.76
    Vidite
    -0.74
    )}]{
    -0.68
    onded
    -0.68
     StatelessWidget
    -0.67
    Abit
    -0.67
    POSITIVE LOGITS
     setting
    1.48
     Setting
    1.31
    Setting
    1.29
     SETTING
    1.23
    setting
    1.14
     set
    1.08
     settings
    1.05
    SETTING
    1.04
     Settings
    0.95
    Settings
    0.95
    Act Density 0.155%

    No Known Activations