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

    Neuronpedia

    INDEX
    Explanations

    specific quantities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" or phrases containing "a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bugs
    -0.72
    achu
    -0.70
    Edit
    -0.70
    Contents
    -0.69
    ATURES
    -0.69
    Reloaded
    -0.69
    agents
    -0.69
    Arcade
    -0.68
    Sources
    -0.68
    eous
    -0.67
    POSITIVE LOGITS
    cknowled
    1.03
     lot
    1.01
     handful
    1.00
     consequ
    0.98
    rouse
    0.97
     combination
    0.96
     couple
    0.94
     plethora
    0.94
     huge
    0.92
     companion
    0.92
    Act Density 0.167%

    No Known Activations