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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and related code structure indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.83
    #+#
    -0.82
    şört
    -0.79
    MessageTagHelper
    -0.79
    новниш
    -0.79
     المعيارى
    -0.77
     kasarigan
    -0.76
    enderror
    -0.76
     beginnetje
    -0.75
    -0.75
    POSITIVE LOGITS
    ↵↵
    0.69
    ↵
    0.51
    ↵↵↵↵
    0.48
    ↵↵↵
    0.47
     St
    0.44
    .
    0.44
    <eos>
    0.43
    }
    0.43
    ↵↵↵↵↵
    0.42
    <h2>
    0.41
    Act Density 0.110%

    No Known Activations