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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, policies, and standards

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.91
    ilus
    -0.84
    fortune
    -0.80
    pocket
    -0.73
    jiang
    -0.72
    joy
    -0.71
    ience
    -0.70
    asca
    -0.69
    ortun
    -0.67
    semble
    -0.65
    POSITIVE LOGITS
     imposed
    1.18
     governing
    1.09
     enforced
    1.09
     dictates
    1.04
     guidelines
    1.02
     criteria
    1.01
     requirements
    1.01
     stip
    1.00
     rules
    0.98
     deviation
    0.96
    Act Density 1.307%

    No Known Activations