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

    Neuronpedia

    INDEX
    Explanations

    audio related terms, specifically focusing on channels

    oai_token-act-pair · gpt-3.5-turbo

    references to audio channels and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.70
     OECD
    -0.69
    ENA
    -0.63
     furnished
    -0.60
     requisite
    -0.59
     Ducks
    -0.59
     videog
    -0.58
     Oilers
    -0.58
     Dodgers
    -0.58
    emale
    -0.57
    POSITIVE LOGITS
    Channel
    1.08
     channel
    1.03
    channel
    1.02
    annels
    0.99
    Mask
    0.91
    annel
    0.88
     channels
    0.87
    ranch
    0.86
    icut
    0.84
    voy
    0.82
    Act Density 0.008%

    No Known Activations