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

    Neuronpedia

    INDEX
    Explanations

    mentions of regularity or routines

    oai_token-act-pair · gpt-3.5-turbo

    the concept of consistency or frequency in behavior or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.77
    kamp
    -0.70
    artisan
    -0.69
    uden
    -0.67
    Cub
    -0.67
    arta
    -0.66
    leneck
    -0.65
    lda
    -0.65
    IRO
    -0.63
    enario
    -0.62
    POSITIVE LOGITS
    ity
    1.27
    cy
    1.05
    ization
    1.04
    ised
    1.03
    isation
    0.98
    izing
    0.96
     occurrence
    0.95
    ities
    0.93
    ITY
    0.92
     intervals
    0.90
    Act Density 0.018%

    No Known Activations