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

    Neuronpedia

    INDEX
    Explanations

    written content related to political or social commentary, particularly regarding feminism, activism, and controversial social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    estones
    -0.82
     Finder
    -0.78
    contact
    -0.74
    foreseen
    -0.74
     linem
    -0.73
     gauge
    -0.70
    oother
    -0.69
    ounter
    -0.69
     milestones
    -0.69
    joining
    -0.69
    POSITIVE LOGITS
     hypocrisy
    1.67
     hypocritical
    1.48
     disingen
    1.36
     hypoc
    1.34
     coward
    1.33
     hypocr
    1.33
     disgrace
    1.33
     arrogance
    1.32
     stupidity
    1.30
     ignorant
    1.29
    Act Density 6.502%

    No Known Activations