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

    Neuronpedia

    INDEX
    Explanations

    terms related to political systems and processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.09
    epad
    -0.73
    ully
    -0.73
    ynthesis
    -0.70
    erity
    -0.70
     Calculator
    -0.69
    uria
    -0.69
     Ratio
    -0.68
    ochet
    -0.67
    ipedia
    -0.67
    POSITIVE LOGITS
     instances
    1.20
     categories
    1.18
     entries
    1.17
     cases
    1.15
     variants
    1.13
     iterations
    1.13
     locations
    1.11
     examples
    1.10
     varieties
    1.10
     entities
    1.10
    Act Density 3.187%

    No Known Activations