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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political ideologies and concepts like dictatorship, oppression, social structures, and critique of societal norms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    poke
    -0.53
    LOD
    -0.53
     ($
    -0.50
    -$
    -0.50
    Alert
    -0.50
     topped
    -0.50
    tackle
    -0.49
    boarding
    -0.49
    gc
    -0.48
    advertising
    -0.47
    POSITIVE LOGITS
     slightest
    0.85
     latter
    0.77
    ocratic
    0.72
     greatest
    0.71
     doctrine
    0.68
     virtues
    0.68
    ses
    0.67
     vast
    0.67
     Greeks
    0.65
     notion
    0.65
    Act Density 14.565%

    No Known Activations