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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases that indicate actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heimer
    -0.07
    ulp
    -0.07
     Becker
    -0.07
    isay
    -0.07
    æĤ
    -0.06
    ãĥ£
    -0.06
    .codehaus
    -0.06
    oil
    -0.06
    ìļĶ
    -0.06
    tingham
    -0.06
    POSITIVE LOGITS
     matters
    0.07
     mÃł
    0.06
    kest
    0.06
    dül
    0.06
     же
    0.06
    akh
    0.06
    .gdx
    0.06
    egin
    0.06
    yy
    0.06
    robe
    0.06
    Act Density 0.037%

    No Known Activations