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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dramatic or troubling situations hinting at abuse or violence

    oai_token-act-pair · gpt-3.5-turbo

    references to traumatic experiences and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amacare
    -0.80
    claimer
    -0.74
    xit
    -0.72
    Brexit
    -0.71
    bold
    -0.71
    capitalist
    -0.71
     Conclusion
    -0.70
    utterstock
    -0.68
     2017
    -0.68
     UPDATE
    -0.67
    POSITIVE LOGITS
     dinners
    1.16
     nightly
    1.08
     mornings
    1.08
     whenever
    1.04
     nights
    1.02
     evenings
    1.00
     Sundays
    0.96
     babys
    0.94
     Occasionally
    0.93
     Saturdays
    0.90
    Act Density 0.836%

    No Known Activations