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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political activism and resistance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     hindsight
    -0.86
    VERTISEMENT
    -0.82
     Presumably
    -0.75
    Interest
    -0.75
    avorable
    -0.73
    laughs
    -0.72
     reviewer
    -0.69
    Laughs
    -0.67
    Random
    -0.67
     debugging
    -0.66
    POSITIVE LOGITS
     unite
    1.16
     salute
    1.16
     pledge
    1.13
     vow
    1.03
     united
    1.02
    Together
    1.00
     patri
    0.98
     belong
    0.95
     owe
    0.93
     liberate
    0.93
    Act Density 0.367%

    No Known Activations