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

    Neuronpedia

    INDEX
    Explanations

    keywords related to societal change and progress

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     deducted
    -0.83
     penalties
    -0.80
     reimburse
    -0.76
     penalty
    -0.75
     reimb
    -0.74
     improperly
    -0.74
     USPS
    -0.70
     defendants
    -0.70
     vetoed
    -0.69
    anuts
    -0.69
    POSITIVE LOGITS
     revolution
    1.35
     revolutions
    1.29
     awakening
    1.28
     transformative
    1.27
     renaissance
    1.26
    revolution
    1.20
     democrat
    1.20
     transformation
    1.20
     rebirth
    1.19
     transforming
    1.17
    Act Density 0.763%

    No Known Activations