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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "st" and its variations, indicating a focus on words or phrases that begin with "st."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.17
    igi
    -0.16
    s
    -0.16
    ubat
    -0.16
    arkan
    -0.15
    eof
    -0.15
    scheduler
    -0.15
     Pey
    -0.15
    izard
    -0.15
     Storm
    -0.15
    POSITIVE LOGITS
     st
    0.35
    aid
    0.20
    stile
    0.19
    iffer
    0.18
    ee
    0.18
    unted
    0.17
    ung
    0.17
    ym
    0.17
    ammer
    0.17
    lil
    0.16
    Act Density 0.015%

    No Known Activations