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

    Neuronpedia

    INDEX
    Explanations

    references to a specific source or citation in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to sources of information or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uckle
    -0.93
     satell
    -0.92
    andel
    -0.91
    interstitial
    -0.86
    aeper
    -0.77
    oÄŁ
    -0.77
     teasp
    -0.76
     compr
    -0.75
     exting
    -0.74
    pload
    -0.74
    POSITIVE LOGITS
     Source
    1.38
     Sources
    1.25
    source
    1.07
    Sources
    0.95
    Source
    0.95
    ource
    0.93
    Fed
    0.93
    Forge
    0.90
    books
    0.89
     source
    0.88
    Act Density 0.003%

    No Known Activations