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

    Neuronpedia

    INDEX
    Explanations

    the subject of sentences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ாள
    -0.66
    ंदीखरीदारी
    -0.64
     Holo
    -0.64
    warten
    -0.62
    Cyfarwyddwr
    -0.62
     Odon
    -0.61
    存于互联网档案馆
    -0.61
    ouwd
    -0.61
     velkommen
    -0.60
    verwijspagina
    -0.60
    POSITIVE LOGITS
    が
    1.59
    가
    1.25
     が
    1.15
    이
    1.07
    리가
    1.05
    りが
    1.04
    氏が
    0.97
    様が
    0.96
    さが
    0.95
    さんが
    0.91
    Act Density 0.039%

    No Known Activations