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

    Neuronpedia

    INDEX
    Explanations

    references to economic changes and growth metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etty
    -0.15
    heel
    -0.15
    midi
    -0.14
     fewer
    -0.14
    edelta
    -0.14
    aber
    -0.14
    abcdefghijkl
    -0.14
    DDL
    -0.14
    nul
    -0.13
    incess
    -0.13
    POSITIVE LOGITS
     twice
    0.44
    tw
    0.40
     tw
    0.40
     ten
    0.36
     Twice
    0.33
     five
    0.32
     four
    0.31
     three
    0.31
     TW
    0.31
     orders
    0.30
    Act Density 0.149%

    No Known Activations