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

    Neuronpedia

    INDEX
    Explanations

    phrases related to television series and episodes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    zie
    -0.79
    orget
    -0.76
    artisan
    -0.76
    orgetown
    -0.72
    lig
    -0.72
    attled
    -0.71
    ovo
    -0.70
    ntil
    -0.69
    ividual
    -0.67
    yer
    -0.66
    POSITIVE LOGITS
     finale
    1.07
    manship
    0.88
     regulars
    0.83
     Reborn
    0.79
    ends
    0.75
     premiere
    0.74
    mable
    0.71
     Premiere
    0.70
    peak
    0.69
    isodes
    0.69
    Act Density 0.035%

    No Known Activations