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

    Neuronpedia

    INDEX
    Explanations

    mentions of television shows and movies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific TV shows or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osate
    -0.75
    ernel
    -0.67
    ickr
    -0.66
     advant
    -0.66
    ulic
    -0.65
    ¬¼
    -0.64
    ntil
    -0.64
     econom
    -0.63
     fiat
    -0.63
    orgetown
    -0.62
    POSITIVE LOGITS
     Whedon
    1.26
     cinematic
    1.21
     cinem
    1.18
    episode
    1.16
     sequels
    1.15
     screenplay
    1.15
    movie
    1.13
     actors
    1.12
     actress
    1.10
     actresses
    1.10
    Act Density 1.676%

    No Known Activations