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

    Neuronpedia

    INDEX
    Explanations

    words that indicate importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emean
    -0.15
    olley
    -0.15
    ÑĥÑĢÑģ
    -0.15
    onical
    -0.15
    dül
    -0.14
    ãĤ±ãĥĥãĥĪ
    -0.14
    íĥģ
    -0.14
    intptr
    -0.14
    Ÿ
    -0.14
    aeda
    -0.14
    POSITIVE LOGITS
    mente
    0.23
    /key
    0.19
    ly
    0.19
     ingredient
    0.18
     importance
    0.18
    hole
    0.17
    /core
    0.17
    ity
    0.17
     moments
    0.16
     role
    0.16
    Act Density 0.029%

    No Known Activations