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

    Neuronpedia

    INDEX
    Explanations

    French words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to groups, individuals, or characteristics in a sociocultural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bright
    -0.82
    ATH
    -0.74
    Flight
    -0.71
    Steel
    -0.70
    ISON
    -0.68
    Neal
    -0.68
    Buzz
    -0.67
    enhagen
    -0.66
    RAY
    -0.66
    Chance
    -0.66
    POSITIVE LOGITS
    ources
    1.05
     que
    1.01
    aurus
    0.99
     aux
    0.98
     Ãł
    0.98
    ystem
    0.96
     qui
    0.96
    pora
    0.95
    ques
    0.94
     du
    0.93
    Act Density 0.049%

    No Known Activations