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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "openly."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    nesota
    -1.19
    ailand
    -0.99
    akeru
    -0.91
    vic
    -0.91
     Stick
    -0.90
     Cth
    -0.89
     Echo
    -0.89
     Mew
    -0.87
     Summoner
    -0.87
     GOODMAN
    -0.85
    POSITIVE LOGITS
     contradicted
    1.11
    isSpecialOrderable
    1.10
     confess
    1.06
     traded
    1.06
     expressed
    1.05
     acknowledged
    1.04
     addressed
    1.03
    ached
    1.01
     contradict
    1.00
     apologized
    1.00
    Act Density 0.883%

    No Known Activations