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

    Neuronpedia

    INDEX
    Explanations

    references to elephants and rhinos, particularly in contexts discussing their existence or conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Poultry
    -0.40
     Chickens
    -0.40
     Chicken
    -0.37
    ingles
    -0.36
    IVEREF
    -0.35
     Binary
    -0.35
    findpost
    -0.34
    PMailer
    -0.33
    Wheat
    -0.33
     Wheat
    -0.33
    POSITIVE LOGITS
     elephant
    1.16
     elephants
    1.13
     Elephant
    1.05
    Elephant
    1.03
     Elephants
    0.93
    elephant
    0.91
     elef
    0.90
     elefante
    0.86
     giraffe
    0.79
    phants
    0.77
    Act Density 0.426%

    No Known Activations