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

    Neuronpedia

    INDEX
    Explanations

    legal or courtroom-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to spiritual practices and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tricked
    -0.81
    utics
    -0.73
     capitalize
    -0.70
     habit
    -0.70
     compound
    -0.70
     sucker
    -0.69
    apon
    -0.69
    udo
    -0.69
     nab
    -0.67
     inverse
    -0.66
    POSITIVE LOGITS
    Thank
    1.06
    Therefore
    0.97
    Brend
    0.96
    Chair
    0.93
    Article
    0.92
    ONSORED
    0.92
    Through
    0.91
    Our
    0.90
    ³³³³³³³³³³³³³³³³
    0.89
    Learn
    0.87
    Act Density 0.574%

    No Known Activations