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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Tek
    -0.67
     Syd
    -0.66
     interf
    -0.64
     mathemat
    -0.61
     Franch
    -0.61
     Ket
    -0.60
     Skydragon
    -0.59
    anwhile
    -0.58
     Jem
    -0.58
     Bethlehem
    -0.57
    POSITIVE LOGITS
    Ļ
    1.68
    ¬
    1.53
    Ń
    1.33
    ª
    1.32
    ĸ
    1.31
    ľ
    1.28
    «
    1.28
    ķ
    1.27
    ¡
    1.26
    Ķ
    1.26
    Act Density 0.407%

    No Known Activations