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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    the verb "was" indicating past actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entails
    -0.70
     Extend
    -0.68
    Make
    -0.68
     Which
    -0.66
     antioxid
    -0.65
    izable
    -0.65
    ological
    -0.63
    inav
    -0.62
    holders
    -0.60
     HAVE
    -0.60
    POSITIVE LOGITS
     able
    1.14
     born
    1.08
    hes
    1.02
     unable
    1.01
    wolves
    1.00
     originally
    0.98
     diagnosed
    0.95
     supposed
    0.95
     instrumental
    0.95
     sentenced
    0.94
    Act Density 0.345%

    No Known Activations