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

    Neuronpedia

    INDEX
    Explanations

    elements related to film analysis, including titles and director information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byshev
    -0.58
    ommen
    -0.50
    ïque
    -0.48
     fib
    -0.48
     Publishing
    -0.46
    dete
    -0.46
     Cover
    -0.44
     processed
    -0.44
    ensatz
    -0.44
     péri
    -0.44
    POSITIVE LOGITS
     director
    1.24
     directors
    1.19
     directing
    1.08
    director
    1.07
     directed
    1.04
    directors
    1.00
    directed
    0.97
    Directors
    0.95
     Director
    0.94
    Director
    0.94
    Act Density 0.147%

    No Known Activations