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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various types of animals

    oai_token-act-pair · gpt-3.5-turbo

    references to animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sutherland
    -0.76
    minster
    -0.73
    âĸ¬
    -0.71
    heit
    -0.70
    nance
    -0.67
    nder
    -0.65
    ãĥ´ãĤ¡
    -0.64
    pai
    -0.64
    ership
    -0.62
    stream
    -0.61
    POSITIVE LOGITS
     animals
    1.17
     mammals
    0.98
     carc
    0.92
     Animals
    0.92
     animal
    0.90
     primates
    0.83
     elephants
    0.83
     carniv
    0.82
     slaughtered
    0.82
    animal
    0.80
    Act Density 0.015%

    No Known Activations