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

    Neuronpedia

    INDEX
    Explanations

    references to systemic issues and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥª
    -0.17
     Want
    -0.15
    igans
    -0.14
     Wanted
    -0.14
     Fetch
    -0.14
    oyer
    -0.14
    kiye
    -0.13
    ocks
    -0.13
     Includes
    -0.13
    oner
    -0.13
    POSITIVE LOGITS
     prepares
    0.35
     prepare
    0.34
     prepared
    0.31
     gears
    0.28
    prepare
    0.26
    prepared
    0.26
     continue
    0.26
     inches
    0.25
     Prepare
    0.25
     continues
    0.24
    Act Density 0.170%

    No Known Activations