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

    Neuronpedia

    INDEX
    Explanations

    web sources embedded in text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific institutions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.83
    cffff
    -0.80
     metic
    -0.76
     Klux
    -0.74
    uminati
    -0.74
    querade
    -0.73
    conservancy
    -0.71
     ende
    -0.69
    interstitial
    -0.69
     chimpanzees
    -0.68
    POSITIVE LOGITS
    Requires
    0.80
    reviewed
    0.79
    cdn
    0.71
    Topic
    0.71
     Featuring
    0.71
     Edited
    0.67
    girl
    0.67
     IMAGES
    0.65
    Available
    0.65
     VIEW
    0.64
    Act Density 0.345%

    No Known Activations