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

    Neuronpedia

    INDEX
    Explanations

    references to trailers and spokespersons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hti
    -0.79
    '),
    -0.78
     Nuss
    -0.76
     fe
    -0.75
    FIG
    -0.73
    Skocz
    -0.69
    klus
    -0.68
     se
    -0.66
     McClure
    -0.65
    "),
    -0.65
    POSITIVE LOGITS
     Trailer
    1.23
    Trailer
    1.20
     trailers
    1.17
     trailer
    1.13
    trailer
    1.12
     Trailers
    1.11
     Apothe
    0.93
     ampoule
    0.89
     Shakspeare
    0.87
    MemoryWarning
    0.84
    Act Density 0.119%

    No Known Activations