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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    geographical names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Breitbart
    -0.72
    Miller
    -0.68
    Tube
    -0.65
     sidewalk
    -0.64
     Guilty
    -0.63
     Horowitz
    -0.62
     Alloy
    -0.62
    Ped
    -0.61
     Berger
    -0.61
     Yiannopoulos
    -0.60
    POSITIVE LOGITS
     Netherlands
    1.29
    uania
    1.27
     Islands
    1.26
     islands
    1.12
     Territories
    1.09
     Bahamas
    1.08
     Rica
    1.07
     Guinea
    1.06
    orea
    1.06
     territories
    1.05
    Act Density 0.252%

    No Known Activations