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

    Neuronpedia

    INDEX
    Explanations

    discussions about specific subjects or topics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -0.73
    HasAnnotation
    -0.73
    ImageContext
    -0.73
     الحره
    -0.71
    ISupport
    -0.70
     XCTest
    -0.70
    Issues
    -0.68
    SequentialGroup
    -0.66
    #
    -0.66
     enjeux
    -0.66
    POSITIVE LOGITS
    pare
    0.56
    кове
    0.52
     Maguire
    0.52
     Devine
    0.51
     organizado
    0.46
    ardless
    0.45
    copied
    0.44
    illo
    0.43
    лага
    0.43
    GetSize
    0.43
    Act Density 0.031%

    No Known Activations