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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming languages and technical details

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Aff
    -0.41
     Adren
    -0.36
     photoc
    -0.34
     Lionel
    -0.34
    idth
    -0.34
     Ag
    -0.34
    Aff
    -0.32
     ..."
    -0.31
     ejac
    -0.30
     Caribbean
    -0.30
    POSITIVE LOGITS
    âķIJ
    0.37
    hover
    0.34
    âĹ¼
    0.34
    Champ
    0.34
    Weiss
    0.32
    Streamer
    0.31
     rul
    0.31
    UTC
    0.31
     Pixie
    0.31
    Ptr
    0.31
    Act Density 12.500%

    No Known Activations