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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and their prominence in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elow
    -0.15
    ees
    -0.14
    ies
    -0.14
     acqu
    -0.14
    Lua
    -0.14
     Luz
    -0.14
     based
    -0.13
    leases
    -0.13
    esium
    -0.13
    aghan
    -0.13
    POSITIVE LOGITS
    adiator
    0.15
    ekt
    0.14
    agraph
    0.14
    ège
    0.14
    ToProps
    0.14
    phere
    0.13
    -runner
    0.13
     æ°¸
    0.13
    lashes
    0.13
     pockets
    0.13
    Act Density 0.038%

    No Known Activations