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

    Neuronpedia

    INDEX
    Explanations

    words related to linguistics, language origins, and the meaning of words

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Ended
    -1.03
     ********************************
    -0.98
    JM
    -0.91
    vez
    -0.90
     redeemed
    -0.83
    ARC
    -0.83
    owsky
    -0.80
    worms
    -0.80
    ior
    -0.80
    ©¶æ¥µ
    -0.80
    POSITIVE LOGITS
     noun
    1.16
     plural
    1.13
     predic
    1.03
    literally
    1.02
     pronunciation
    1.01
    terday
    0.99
     pronounced
    0.99
     adject
    0.96
     slang
    0.96
    spell
    0.95
    Act Density 1.173%

    No Known Activations