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

    Neuronpedia

    INDEX
    Explanations

    instances of recurring themes or patterns

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes or repeated elements in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Titus
    -0.86
     bis
    -0.86
     Tanzania
    -0.79
    itus
    -0.78
     Cantor
    -0.78
     Paran
    -0.77
     Paso
    -0.75
    lde
    -0.74
     pas
    -0.73
     Kane
    -0.73
    POSITIVE LOGITS
     motif
    1.22
     Cavern
    1.13
     pawn
    1.08
     squirrel
    1.06
     subsystem
    1.04
     storefront
    1.02
     glyph
    1.00
     precept
    0.95
    ystem
    0.94
    review
    0.94
    Act Density 0.143%

    No Known Activations