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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to controversial or challenging societal issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Platform
    -0.73
     Kinnikuman
    -0.66
    ulative
    -0.65
    arial
    -0.65
    amina
    -0.64
     Staten
    -0.64
     Chinatown
    -0.64
    ortment
    -0.64
     Hok
    -0.63
     Amendments
    -0.63
    POSITIVE LOGITS
    ishly
    0.76
    ensibly
    0.75
    ecause
    0.75
     citiz
    0.73
     <-
    0.70
    etheless
    0.70
    \",
    0.68
    imposed
    0.67
    ifully
    0.67
    vation
    0.66
    Act Density 13.446%

    No Known Activations