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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of formal statements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.83
    oiler
    -0.73
    animate
    -0.71
     unsus
    -0.69
    skill
    -0.67
    cffffcc
    -0.66
    elsius
    -0.66
    iencies
    -0.65
    illions
    -0.65
    regor
    -0.64
    POSITIVE LOGITS
     emailed
    1.12
     issued
    1.08
     released
    1.03
     announcing
    1.03
     statement
    0.99
     accompanying
    0.88
     thanking
    0.85
     obtained
    0.83
     Thursday
    0.81
    Statement
    0.81
    Act Density 0.044%

    No Known Activations