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

    Neuronpedia

    INDEX
    Explanations

    the verb "do" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    457
    -0.15
    antly
    -0.15
    azer
    -0.15
    kol
    -0.15
    rox
    -0.14
    foon
    -0.14
    stras
    -0.14
    trak
    -0.14
    anse
    -0.14
    OfSize
    -0.14
    POSITIVE LOGITS
    estre
    0.18
    xygen
    0.15
    bserv
    0.15
     justice
    0.14
    Comparator
    0.14
     ayn
    0.14
    cket
    0.13
    -done
    0.13
    inand
    0.13
    inth
    0.13
    Act Density 0.100%

    No Known Activations