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

    Neuronpedia

    INDEX
    Explanations

    words related to abstract concepts and fields such as perception, behavior, philosophy, freedom, vision, reaction, growth, esteem, prohibition, consciousness, modern computing, awareness, commitment, operation, satisfaction, authorization, management, responsibility, investment, energy

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to psychological and social factors influencing behaviors and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.88
    abee
    -0.75
    âĸ¬
    -0.69
     Niet
    -0.65
     Oval
    -0.63
    Ire
    -0.63
     thous
    -0.62
     Frie
    -0.61
    orld
    -0.60
    lear
    -0.59
    POSITIVE LOGITS
     partName
    0.54
     creep
    0.54
     bias
    0.53
     conceal
    0.53
    lessly
    0.52
     prompt
    0.51
     awareness
    0.51
     rates
    0.51
    quickShipAvailable
    0.50
     adjustment
    0.50
    Act Density 0.293%

    No Known Activations