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

    Neuronpedia

    INDEX
    Explanations

    expletives and expressions of frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.56
    enlace
    -0.50
    CodeAttribute
    -0.50
    method
    -0.50
     method
    -0.49
    الإنجليزية
    -0.48
    yarnpkg
    -0.47
    roppo
    -0.47
    UIControlState
    -0.47
    ngdoc
    -0.46
    POSITIVE LOGITS
    hole
    0.81
    holes
    0.73
    HOLE
    0.72
    Hole
    0.68
     hole
    0.67
     HOLE
    0.66
    Holes
    0.62
     Hole
    0.61
    RegressionTest
    0.58
     load
    0.57
    Act Density 0.227%

    No Known Activations