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

    Neuronpedia

    INDEX
    Explanations

    words indicating time-related uncertainties or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.25
    MigrationBuilder
    -1.16
    awtextra
    -1.14
    OGND
    -1.09
     EconPapers
    -1.04
    NameInMap
    -1.04
     defaultstate
    -0.98
    SourceChecksum
    -0.98
    تقاوى
    -0.97
    expandindo
    -0.95
    POSITIVE LOGITS
     nữa
    0.55
     L
    0.45
     "
    0.44
     (
    0.42
     '
    0.42
     via
    0.42
     M
    0.41
     -
    0.40
    `
    0.40
     l
    0.39
    Act Density 0.458%

    No Known Activations