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

    Neuronpedia

    INDEX
    Explanations

    words associated with necessity and importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irut
    -0.17
    ogne
    -0.16
    elian
    -0.14
    енÑı
    -0.14
    aterno
    -0.13
     ราà¸Ħ
    -0.13
    xae
    -0.13
    bdd
    -0.13
    agli
    -0.13
    lemn
    -0.13
    POSITIVE LOGITS
    lessly
    0.13
    ges
    0.12
    надлеж
    0.12
    ÌĢ
    0.12
    ñana
    0.12
    uyla
    0.12
    strict
    0.12
    ("'"
    0.12
    verse
    0.12
    fully
    0.12
    Act Density 0.023%

    No Known Activations