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

    Neuronpedia

    INDEX
    Explanations

    currency denominations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Thomson
    -0.73
     interf
    -0.73
     traffic
    -0.68
     Tinker
    -0.67
     photoc
    -0.66
     ASC
    -0.65
     transc
    -0.64
     NEC
    -0.64
     MET
    -0.63
     Jem
    -0.62
    POSITIVE LOGITS
    Ļ
    1.80
    ¬
    1.51
    ¡
    1.43
    ı
    1.43
    ª
    1.42
    £
    1.38
    ¥
    1.36
    ¨
    1.34
    ´
    1.33
    Ĵ
    1.32
    Act Density 0.150%

    No Known Activations