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

    Neuronpedia

    INDEX
    Explanations

    references to trailers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.56
    sense
    -0.50
     Fisk
    -0.48
    THINK
    -0.48
    Архівовано
    -0.47
    Winston
    -0.47
    ukkig
    -0.47
    Angie
    -0.46
     BP
    -0.46
     Nuss
    -0.46
    POSITIVE LOGITS
     Trailer
    1.10
     trailer
    1.07
    trailer
    1.00
    Trailer
    1.00
     trailers
    0.98
     Trailers
    0.84
    parsedMessage
    0.67
    TRAIL
    0.58
     trail
    0.57
     remol
    0.57
    Act Density 0.003%

    No Known Activations