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

    Neuronpedia

    INDEX
    Explanations

    dates, locations, and proper nouns

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     asses
    -0.65
    existent
    -0.62
     culprit
    -0.62
     flagged
    -0.62
     dstg
    -0.62
    :/
    -0.59
    icons
    -0.59
    =>
    -0.58
    estamp
    -0.58
     %%
    -0.57
    POSITIVE LOGITS
     addition
    1.21
     hindsight
    1.16
     2006
    1.16
     retrospect
    1.15
     2005
    1.14
     2003
    1.13
     2004
    1.12
     2002
    1.11
     1998
    1.10
     spite
    1.10
    Act Density 0.122%

    No Known Activations