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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating performance and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lapsingToolbar
    -0.58
    esseract
    -0.57
     Wicidata
    -0.55
    '));
    -0.55
     two
    -0.55
    .*")]
    -0.53
    IBarButtonItem
    -0.52
    DoubleQuotes
    -0.52
    [
    -0.52
    천
    -0.52
    POSITIVE LOGITS
     đều
    0.66
     câte
    0.64
    toHaveBeenCalled
    0.54
    IBOutlet
    0.53
    AsUp
    0.53
     birbir
    0.52
     sauf
    0.51
    ajara
    0.51
    aarrggbb
    0.50
    Hozzáférés
    0.49
    Act Density 1.004%

    No Known Activations