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

    Neuronpedia

    INDEX
    Explanations

    references to different types of animals, including wild animals and wildlife

    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
    ãĥ¼ãĥĨ
    -0.75
     Sutherland
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
     Fulton
    -0.67
     caut
    -0.64
    âĸ¬
    -0.63
    itudinal
    -0.63
     Beckham
    -0.63
    STRUCT
    -0.62
    stream
    -0.62
    POSITIVE LOGITS
     slaughtered
    0.94
    folk
    0.90
    wana
    0.86
     animals
    0.86
     domest
    0.85
     reptiles
    0.84
    ertodd
    0.83
    cale
    0.83
     carc
    0.82
     species
    0.77
    Act Density 0.052%

    No Known Activations