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

    Neuronpedia

    INDEX
    Explanations

    instances of the Japanese particle "を" in contexts related to actions or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marlins
    -0.67
    Mann
    -0.66
     disagre
    -0.65
     Mann
    -0.64
     Valera
    -0.64
     Fara
    -0.64
     SSS
    -0.64
    ❗
    -0.62
    ilar
    -0.60
     ard
    -0.60
    POSITIVE LOGITS
    mu
    0.99
     Mu
    0.96
    μ
    0.95
     μ
    0.95
     MUL
    0.95
    MUL
    0.93
    Mu
    0.92
    Muri
    0.92
    WriteLiteral
    0.89
    Му
    0.87
    Act Density 0.198%

    No Known Activations