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

    Neuronpedia

    INDEX
    Explanations

    references to milk and dairy products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roberta
    -0.60
     himo
    -0.58
    hå
    -0.57
    esthetics
    -0.57
    Roberta
    -0.57
    aconda
    -0.57
     thủ
    -0.56
     zout
    -0.56
    unch
    -0.55
    ('-'
    -0.55
    POSITIVE LOGITS
     milk
    2.54
     Milk
    2.43
    milk
    2.33
     MILK
    2.31
    Milk
    2.30
     leche
    1.69
     Milch
    1.51
     milking
    1.41
     dairy
    1.38
     milky
    1.36
    Act Density 0.048%

    No Known Activations