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

    Neuronpedia

    INDEX
    Explanations

    just the keyword "Ep" with different numbers following it

    oai_token-act-pair · gpt-3.5-turbo

    referrals to episodes in a serialized narrative or media series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FUL
    -0.79
     unauthorized
    -0.71
    LESS
    -0.67
     Pru
    -0.66
     clearance
    -0.65
     humming
    -0.63
     Sunderland
    -0.62
    ^^^^
    -0.62
     Polk
    -0.62
    hips
    -0.61
    POSITIVE LOGITS
    iphany
    1.72
    hemer
    1.71
    isodes
    1.50
    iscopal
    1.43
    onymous
    1.40
    istle
    1.35
    igraph
    1.27
    iph
    1.20
    onym
    1.16
    idem
    1.15
    Act Density 0.019%

    No Known Activations