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

    Neuronpedia

    INDEX
    Explanations

    titles of movies or series

    oai_token-act-pair · gpt-3.5-turbo

    titles and named entities of works, particularly in the context of film or other media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bias
    -0.78
     commute
    -0.77
     precisely
    -0.76
     tend
    -0.76
     inclined
    -0.75
     adjustment
    -0.73
     correspond
    -0.73
     piled
    -0.72
     coun
    -0.71
     aggrav
    -0.70
    POSITIVE LOGITS
     Reloaded
    1.38
     Definitive
    1.26
     Unleashed
    1.26
     Rise
    1.25
     Resurrection
    1.25
     Shattered
    1.21
     Reborn
    1.19
     Ascension
    1.18
     Prelude
    1.17
     Rebirth
    1.17
    Act Density 0.088%

    No Known Activations