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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving variables and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mer
    -0.42
    ufer
    -0.41
     meta
    -0.38
     rid
    -0.38
     bibli
    -0.38
    uren
    -0.38
    helmet
    -0.38
     Junction
    -0.38
     din
    -0.37
    /**
    -0.36
    POSITIVE LOGITS
    帖最后由
    0.87
     متعلقه
    0.77
     MainAxisSize
    0.77
     resourceCulture
    0.71
    aarrggbb
    0.71
     propOrder
    0.71
    Хьажоргаш
    0.70
    InputTagHelper
    0.69
    RegressionTest
    0.68
    tdessen
    0.68
    Act Density 0.722%

    No Known Activations