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

    Neuronpedia

    INDEX
    Explanations

    references to community organizations or societal issues related to support and activism

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ian
    -0.27
     Pony
    -0.25
    Äį
    -0.25
    issance
    -0.25
    erb
    -0.24
    Cart
    -0.24
    arov
    -0.24
     Rousse
    -0.24
    ean
    -0.23
     Anita
    -0.23
    POSITIVE LOGITS
     members
    0.32
     membership
    0.31
     sizes
    0.31
    leader
    0.30
     gatherings
    0.29
    Members
    0.29
     participation
    0.29
    pool
    0.28
     arrangements
    0.28
     member
    0.27
    Act Density 7.603%

    No Known Activations