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

    Neuronpedia

    INDEX
    Explanations

    references to popular television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritt
    -0.15
    otlin
    -0.15
    abad
    -0.14
     Pompe
    -0.14
    iska
    -0.13
     Kan
    -0.13
    itore
    -0.13
    .pred
    -0.13
    VN
    -0.13
     Daughter
    -0.13
    POSITIVE LOGITS
     royal
    0.24
     season
    0.21
     Season
    0.21
     Seasons
    0.20
    roy
    0.19
     Crown
    0.19
     Royals
    0.19
     Princess
    0.19
     palace
    0.19
     royalty
    0.17
    Act Density 0.003%

    No Known Activations