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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific names and related terms, particularly focusing on "Clement" and "cinnamon," alongside mentions of corroboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entious
    -0.77
    HAHAHAHA
    -0.72
    HAHA
    -0.68
    bnb
    -0.67
    ptives
    -0.67
    riors
    -0.66
    SPONSORED
    -0.66
    Topics
    -0.66
    itbart
    -0.66
    culosis
    -0.66
    POSITIVE LOGITS
     Clement
    0.81
     soda
    0.78
    uries
    0.76
     pulp
    0.75
     conduc
    0.73
     cinnamon
    0.72
    loo
    0.71
     oranges
    0.68
    icle
    0.68
     Coke
    0.67
    Act Density 0.012%

    No Known Activations