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

    Neuronpedia

    INDEX
    Explanations

    phrases related to titles of books, movies, or albums

    oai_token-act-pair · gpt-3.5-turbo

    titles or names of films and books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referen
    -0.87
     chem
    -0.79
     nav
    -0.73
     credential
    -0.69
     carbohyd
    -0.69
     councill
    -0.66
     advoc
    -0.66
    itionally
    -0.65
     attendance
    -0.63
    atern
    -0.63
    POSITIVE LOGITS
     Trilogy
    0.93
     Reborn
    0.91
     Reloaded
    0.91
     Deadly
    0.89
     Remix
    0.89
     Collection
    0.86
     Seasons
    0.85
     Productions
    0.84
     Written
    0.83
     Lonely
    0.83
    Act Density 0.300%

    No Known Activations