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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, such as names of places or people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rew."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kenyan
    -0.71
    ãĤ¿
    -0.70
     è£ı
    -0.69
     Ghana
    -0.68
     Senegal
    -0.67
     quo
    -0.67
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
    ãĤ¶
    -0.65
     è£ıè¦ļéĨĴ
    -0.65
     Liberia
    -0.65
    POSITIVE LOGITS
    atche
    1.09
    ritten
    1.00
    sburg
    0.94
    atts
    0.92
    orld
    0.91
    enthal
    0.91
    ipes
    0.89
    driver
    0.89
    bles
    0.88
    inders
    0.87
    Act Density 0.009%

    No Known Activations