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

    Neuronpedia

    INDEX
    Explanations

    words and terms related to specific cultural references and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egr
    -0.23
    eka
    -0.19
    east
    -0.19
    e
    -0.19
    ego
    -0.18
    ร
    -0.17
    eer
    -0.17
    egen
    -0.17
    een
    -0.17
    ãĥ³ãĤ°
    -0.17
    POSITIVE LOGITS
    nowledge
    0.30
    ernels
    0.26
    tober
    0.25
    nowled
    0.25
    ansas
    0.23
    owski
    0.23
    à¥įष
    0.23
    inesis
    0.23
    hor
    0.23
    à¹Ģà¸ģà¸Ńร
    0.23
    Act Density 0.163%

    No Known Activations