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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )");
    -1.03
    )"),
    -0.90
    fromnode
    -0.89
    ()")
    -0.87
    />";
    -0.84
    ']):
    -0.81
    )')
    -0.79
     Lightfoot
    -0.79
    ',
    -0.78
    ...";
    -0.78
    POSITIVE LOGITS
    0
    1.04
    FXML
    0.71
     Ersten
    0.65
    mitives
    0.60
    rewards
    0.58
     Nan
    0.57
    abstractmethod
    0.55
     inocente
    0.54
     Zer
    0.53
    WARNINGS
    0.53
    Act Density 0.532%

    No Known Activations