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

    Neuronpedia

    INDEX
    Explanations

    references and citations within a text

    oai_token-act-pair · gpt-3.5-turbo

    brackets and their contents in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estab
    -0.83
     Engineers
    -0.82
     pudding
    -0.76
     ende
    -0.71
     plateau
    -0.70
     Franch
    -0.68
     Elon
    -0.68
     Horses
    -0.68
     upt
    -0.67
     Genie
    -0.67
    POSITIVE LOGITS
    note
    1.69
    Pg
    1.49
    reviewed
    1.34
    4
    1.33
    src
    1.32
    8
    1.32
    7
    1.32
    5
    1.31
    6
    1.30
    ...]
    1.30
    Act Density 0.022%

    No Known Activations