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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and power dynamics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -0.70
     surveys
    -0.65
     assumptions
    -0.64
     interviews
    -0.62
     petitions
    -0.62
     ceilings
    -0.62
    tails
    -0.60
    icts
    -0.60
     twists
    -0.60
     pregnancies
    -0.60
    POSITIVE LOGITS
     unto
    1.14
     extraord
    0.88
     fodder
    0.86
     worthy
    0.82
     conduit
    0.81
     unworthy
    0.76
     discipl
    0.72
     deserving
    0.72
     keeper
    0.70
     incarn
    0.70
    Act Density 1.896%

    No Known Activations