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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to societal issues and problems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.81
    oire
    -0.78
    oyer
    -0.78
    osate
    -0.77
    etheless
    -0.76
    enium
    -0.75
    icism
    -0.73
    leneck
    -0.73
    raper
    -0.72
    icka
    -0.70
    POSITIVE LOGITS
     constants
    0.89
    types
    0.87
     truths
    0.86
     examples
    0.86
     mutually
    0.83
     moments
    0.79
     topics
    0.78
     reminders
    0.77
     acron
    0.75
     metaphors
    0.75
    Act Density 0.051%

    No Known Activations