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

    Neuronpedia

    INDEX
    Explanations

    terms related to a specific TV show, possibly "Saturday Night Live"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.72
    lessly
    -0.64
     Emirates
    -0.64
     Byrne
    -0.64
     Kali
    -0.64
    flies
    -0.64
    cens
    -0.64
     Emir
    -0.62
     Alonso
    -0.61
     Lama
    -0.60
    POSITIVE LOGITS
    OW
    1.01
    SN
    0.96
    MP
    0.91
    ASH
    0.88
    ookie
    0.88
    ACK
    0.88
    igger
    0.86
    ipes
    0.86
    icket
    0.86
    azer
    0.86
    Act Density 0.013%

    No Known Activations