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

    Neuronpedia

    INDEX
    Explanations

    references to communication or broadcasting channels

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lindo
    -0.55
    dison
    -0.47
    pous
    -0.46
    Caprio
    -0.46
     stratigraph
    -0.46
    petits
    -0.46
    coso
    -0.43
    bosky
    -0.43
     tipto
    -0.42
    coeur
    -0.42
    POSITIVE LOGITS
     channel
    1.58
     Channel
    1.49
    channel
    1.49
     channels
    1.40
    Channel
    1.38
     Channels
    1.36
    channels
    1.28
     CHANNEL
    1.28
    CHANNEL
    1.23
    Channels
    1.20
    Act Density 0.105%

    No Known Activations