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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "way" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rapper
    -0.16
    ivor
    -0.16
    argent
    -0.15
    iero
    -0.15
    epad
    -0.14
    itian
    -0.14
    cky
    -0.14
    iams
    -0.14
     Fits
    -0.14
    ByExample
    -0.14
    POSITIVE LOGITS
     back
    0.21
    finding
    0.20
     beyond
    0.20
    lon
    0.19
     WAY
    0.19
    ne
    0.18
     past
    0.18
    lay
    0.18
     overdue
    0.18
     way
    0.18
    Act Density 0.015%

    No Known Activations