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

    Neuronpedia

    INDEX
    Explanations

    research institutions or activities.

    oai_token-act-pair · gpt-3.5-turbo

    references to research and research-related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icago
    -0.66
    conv
    -0.60
     Rowling
    -0.59
     Garfield
    -0.59
    âĶĢâĶĢ
    -0.57
    same
    -0.57
     cringe
    -0.57
     cracks
    -0.56
    phot
    -0.56
    size
    -0.55
    POSITIVE LOGITS
     Laboratory
    0.87
     Laboratories
    0.85
     Institute
    0.81
     Scientist
    0.81
     Center
    0.80
    Gate
    0.80
     Ethics
    0.79
     Associates
    0.78
     Research
    0.78
     Digest
    0.77
    Act Density 0.027%

    No Known Activations