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

    Neuronpedia

    INDEX
    Explanations

    specific noun forms and suffixes commonly used in academic or formal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sheet
    -0.20
    erb
    -0.19
    y
    -0.18
    ily
    -0.18
    s
    -0.18
    erk
    -0.17
    erse
    -0.17
    ship
    -0.17
    sf
    -0.16
    ERING
    -0.16
    POSITIVE LOGITS
    ted
    0.26
    ters
    0.23
    ta
    0.22
    tings
    0.20
    ts
    0.19
    ect
    0.19
    tes
    0.18
    ECH
    0.18
    dings
    0.17
    chio
    0.17
    Act Density 0.100%

    No Known Activations