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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social justice and positive change

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing fairness, compassion, and improvement in societal conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aunts
    -0.78
    steps
    -0.77
     caveats
    -0.75
    tons
    -0.74
    errors
    -0.73
     quirks
    -0.73
     glitches
    -0.73
    attacks
    -0.72
     maneuvers
    -0.71
    inches
    -0.69
    POSITIVE LOGITS
     environment
    1.21
     society
    1.20
     future
    1.15
     atmosphere
    1.01
     economy
    0.99
     world
    0.96
     relationship
    0.95
     planet
    0.95
     workplace
    0.92
     outcome
    0.92
    Act Density 0.137%

    No Known Activations