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

    Neuronpedia

    INDEX
    Explanations

    situations or discussions related to societal issues and activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    andise
    -0.73
    opolis
    -0.70
    ãĥ©ãĥ³
    -0.69
    ãĤº
    -0.64
    ario
    -0.63
    ãĥīãĥ©
    -0.63
    anwhile
    -0.62
    ume
    -0.61
    ROR
    -0.61
    restling
    -0.60
    POSITIVE LOGITS
     deserved
    1.06
     underrated
    0.94
     unfairly
    0.93
     deserves
    0.90
     ought
    0.88
     warranted
    0.86
     underest
    0.83
     underestimated
    0.82
     exaggerated
    0.82
     misunderstood
    0.80
    Act Density 1.660%

    No Known Activations