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

    Neuronpedia

    INDEX
    Explanations

    recent updates or information regarding reports and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itinéraire
    -0.36
    ยะ
    -0.33
     couldn
    -0.30
     tissu
    -0.30
     bukan
    -0.29
    ReadInt
    -0.29
     nebude
    -0.28
     métiers
    -0.28
    INTR
    -0.28
     OnTrigger
    -0.28
    POSITIVE LOGITS
    adaptiveStyles
    0.68
    LookAnd
    0.66
    ViewImports
    0.65
    ंदीखरीदारी
    0.61
     kasarigan
    0.61
     fashiola
    0.60
    BeginContext
    0.60
    <unused43>
    0.59
    Diweddarwch
    0.59
    [@BOS@]
    0.58
    Act Density 0.743%

    No Known Activations