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

    Neuronpedia

    INDEX
    Explanations

    words related to ongoing TV series or show episodes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.79
    nai
    -0.74
    orgetown
    -0.73
    zie
    -0.73
    ablishment
    -0.71
    rian
    -0.68
    ryn
    -0.68
    yer
    -0.67
    esse
    -0.66
    orget
    -0.66
    POSITIVE LOGITS
     finale
    1.06
    manship
    0.73
    ĸļ
    0.72
     regulars
    0.69
     Reborn
    0.67
    ends
    0.66
    mable
    0.65
    Series
    0.63
     Abrams
    0.63
    unit
    0.62
    Act Density 0.597%

    No Known Activations