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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Franch
    -0.78
     PASS
    -0.76
     Feder
    -0.74
     Frankfurt
    -0.72
     fuss
    -0.69
     Confeder
    -0.68
     Cantor
    -0.68
     CARE
    -0.68
    573
    -0.67
     Baker
    -0.67
    POSITIVE LOGITS
    x
    1.76
    xes
    1.43
    xs
    1.37
    xc
    1.30
     x
    1.29
    xb
    1.28
    X
    1.28
    xy
    1.28
    xa
    1.26
    xd
    1.25
    Act Density 0.161%

    No Known Activations