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

    Neuronpedia

    INDEX
    Explanations

    instances of the particle "を" and related grammatical structures indicative of actions or objects in Japanese sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.06
     itſelf
    -0.99
     Monfieur
    -0.97
     Efq
    -0.95
     purpoſe
    -0.94
     houſe
    -0.94
     reaſon
    -0.92
     Theſe
    -0.91
     ſche
    -0.89
     Chriftian
    -0.88
    POSITIVE LOGITS
    を
    1.20
    을
    1.16
    子を
    1.15
    いを
    1.11
    를
    1.08
    曲を
    1.05
    みを
    1.04
    さんを
    1.03
     को
    1.01
     を
    0.98
    Act Density 0.029%

    No Known Activations