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

    Neuronpedia

    INDEX
    Explanations

    authors' names and publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .orange
    -0.16
    407
    -0.16
    arend
    -0.16
    ikki
    -0.15
    oku
    -0.14
     ActionTypes
    -0.14
    rend
    -0.14
    ical
    -0.13
    359
    -0.13
    ingo
    -0.13
    POSITIVE LOGITS
    à¸Ĭà¸Ļ
    0.16
     snaps
    0.15
     snap
    0.15
    erli
    0.15
    webtoken
    0.15
    ãĤ·ãĥ§
    0.14
    snap
    0.14
    yh
    0.14
     Belt
    0.14
     snapped
    0.14
    Act Density 0.109%

    No Known Activations