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

    Neuronpedia

    INDEX
    Explanations

    repeated references to "channel" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ydi
    -0.75
     Betts
    -0.68
     Mortimer
    -0.68
     sourire
    -0.67
    esserung
    -0.67
    ukasz
    -0.67
     BeautifulSoup
    -0.66
     moſt
    -0.65
     StatelessWidget
    -0.65
     Madsen
    -0.65
    POSITIVE LOGITS
     channels
    2.24
     channel
    2.05
     Channels
    1.99
    Channels
    1.97
    channels
    1.97
     Channel
    1.95
     CHANNEL
    1.86
    CHANNEL
    1.79
    Channel
    1.79
    channel
    1.79
    Act Density 0.049%

    No Known Activations