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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal proximity or references to the conclusion of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.54
     AssemblyCompany
    -0.51
    elemField
    -0.48
    hicles
    -0.43
     clearColor
    -0.42
     disponibilités
    -0.41
     وتسجيلات
    -0.41
    scribers
    -0.41
     ſtill
    -0.41
    createServer
    -0.41
    POSITIVE LOGITS
    後半
    0.61
     midway
    0.53
    前半
    0.51
     later
    0.50
     towards
    0.49
     späteren
    0.48
    途中
    0.47
     koń
    0.46
     temprano
    0.46
     Later
    0.46
    Act Density 0.360%

    No Known Activations