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

    Neuronpedia

    INDEX
    Explanations

    news articles focusing on legal and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to authoritative directives or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.80
    âĹ¼
    -0.78
    }.
    -0.72
    )."
    -0.72
    .).
    -0.70
    _.
    -0.69
    76561
    -0.68
     versa
    -0.67
    Secondly
    -0.66
    ãĢĤ
    -0.65
    POSITIVE LOGITS
     Belfast
    0.81
     âĢº
    0.71
     Wednesday
    0.71
     Thursday
    0.70
     Donald
    0.70
     Hillary
    0.67
     reportedly
    0.67
     Tuesday
    0.66
     embattled
    0.66
    zbollah
    0.64
    Act Density 1.996%

    No Known Activations