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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code snippets related to computer programming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    obook
    -1.12
    ossession
    -0.98
    bett
    -0.95
    opard
    -0.90
    adle
    -0.90
    é¾į
    -0.88
    irsch
    -0.87
    owship
    -0.87
    igion
    -0.86
    vertisement
    -0.86
    POSITIVE LOGITS
     congr
    1.31
     huh
    1.24
     eh
    1.10
     tho
    1.04
     intel
    1.00
     ya
    0.98
     pics
    0.98
     gotta
    0.94
     Seems
    0.94
     :(
    0.91
    Act Density 3.864%

    No Known Activations