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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating popularity or well-known status of subjects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abay
    -0.16
    zÃŃ
    -0.15
    unik
    -0.15
    itsu
    -0.14
     geil
    -0.14
    StreamReader
    -0.13
    oki
    -0.13
     Beaut
    -0.13
    ÏĥÏĦα
    -0.13
    breadcrumbs
    -0.13
    POSITIVE LOGITS
     known
    0.71
    known
    0.63
    -known
    0.63
     famous
    0.62
     Known
    0.59
     well
    0.54
    Known
    0.53
     know
    0.52
     bekannt
    0.50
     Famous
    0.48
    Act Density 0.261%

    No Known Activations