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

    Neuronpedia

    INDEX
    Explanations

    references to various types of meat and animal-derived food products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.89
     propOrder
    -0.88
    .‏
    -0.88
    theless
    -0.85
    Germain
    -0.84
    edly
    -0.83
     entanto
    -0.82
    팎
    -0.81
     Anfitrión
    -0.81
    naires
    -0.80
    POSITIVE LOGITS
     meat
    1.10
    y
    0.96
    meat
    0.92
     Meat
    0.90
     beef
    0.85
     MEAT
    0.84
     carne
    0.84
    Meat
    0.79
     Fleisch
    0.78
    beef
    0.77
    Act Density 0.137%

    No Known Activations