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

    Neuronpedia

    INDEX
    Explanations

    film titles, specifically focusing on colors

    oai_token-act-pair · gpt-3.5-turbo

    titles of movies and TV shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TN
    -0.75
     contention
    -0.66
     credibility
    -0.65
    itionally
    -0.64
     opponents
    -0.64
     parity
    -0.64
     turb
    -0.63
     positioning
    -0.63
    ISA
    -0.63
     livelihood
    -0.62
    POSITIVE LOGITS
     Awakens
    1.13
     Trilogy
    1.02
     Bride
    0.90
     Files
    0.89
     Incident
    0.88
    ateful
    0.87
     Below
    0.86
     Adventures
    0.85
     Angels
    0.83
     Chronicles
    0.83
    Act Density 0.267%

    No Known Activations