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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "also" indicating additional information or points in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ascension
    -0.70
    endi
    -0.69
    agus
    -0.66
     Extension
    -0.63
    irin
    -0.63
    click
    -0.62
    acious
    -0.62
    VERSION
    -0.62
    £
    -0.62
     Hive
    -0.62
    POSITIVE LOGITS
     thanked
    0.91
     includes
    0.90
     cautioned
    0.90
     congratulated
    0.89
     participated
    0.88
     contributed
    0.87
     noted
    0.86
     criticized
    0.85
     risked
    0.83
     discussed
    0.82
    Act Density 0.111%

    No Known Activations