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

    Neuronpedia

    INDEX
    Explanations

    instances of programming or markup language tags and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مُعرِّف
    -0.54
     кӀ
    -0.48
     Vielen
    -0.44
     couvercle
    -0.41
    stateMutability
    -0.41
     Buckley
    -0.41
    masi
    -0.40
    mola
    -0.40
     prodigal
    -0.40
     pagal
    -0.40
    POSITIVE LOGITS
    ViewFeatures
    1.14
     الحره
    0.95
    Искәрмәләр
    0.85
     XCTest
    0.83
    endphp
    0.77
    المناصب
    0.75
    __':
    0.72
    InvalidProtocol
    0.71
    makeText
    0.69
    󠁿
    0.69
    Act Density 0.010%

    No Known Activations