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

    instances of the verb "was"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Extend
    -0.69
    Make
    -0.68
     IMAGES
    -0.67
    izable
    -0.66
     entails
    -0.66
     HAVE
    -0.66
     Which
    -0.65
     Compare
    -0.65
    Kids
    -0.64
    holders
    -0.64
    POSITIVE LOGITS
     able
    1.20
     born
    1.19
     unable
    1.05
     originally
    1.01
     supposed
    0.99
    hes
    0.99
     tasked
    0.97
     instrumental
    0.96
     arrested
    0.96
     sentenced
    0.95
    Act Density 0.348%

    No Known Activations