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

    Neuronpedia

    INDEX
    Explanations

    terms related to voting, users, and players

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voter participation and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mith
    -0.94
    creen
    -0.85
    hirt
    -0.84
    orem
    -0.83
    uits
    -0.81
     Maiden
    -0.80
    orie
    -0.75
    hops
    -0.75
    unda
    -0.73
    hift
    -0.72
    POSITIVE LOGITS
     satisfaction
    1.16
    hood
    1.08
     engagement
    1.02
     protection
    0.95
     empowerment
    0.94
     interaction
    0.94
     welfare
    0.89
     behavior
    0.89
     dissatisfaction
    0.88
     safety
    0.87
    Act Density 0.137%

    No Known Activations