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

    Neuronpedia

    INDEX
    Explanations

    names of news channels and media outlets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    earable
    -0.45
    */(
    -0.44
    iking
    -0.44
    enei
    -0.42
    enty
    -0.42
    imentary
    -0.41
    ourcing
    -0.41
    itated
    -0.40
    enced
    -0.40
    uary
    -0.40
    POSITIVE LOGITS
     Channel
    0.51
     Islands
    0.48
     Tunnel
    0.45
     Divinity
    0.43
    Channel
    0.42
     Coastal
    0.41
     News
    0.39
     Broadcasting
    0.39
     Mobil
    0.39
     Coast
    0.39
    Act Density 8.549%

    No Known Activations