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

    Neuronpedia

    INDEX
    Explanations

    reference to notable people or famous figures

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and statistics involving people or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shutterstock
    -0.56
     NSW
    -0.54
    boss
    -0.54
     Allaah
    -0.52
    uxe
    -0.51
    flight
    -0.50
    Released
    -0.49
     Melbourne
    -0.48
     Delhi
    -0.47
    fortunately
    -0.47
    POSITIVE LOGITS
     documenting
    0.80
     predicting
    0.79
     demonstrating
    0.78
     discussing
    0.77
     recommending
    0.77
     regarding
    0.76
     approving
    0.76
     recognizing
    0.76
     devoted
    0.75
     admitting
    0.74
    Act Density 1.308%

    No Known Activations