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

    Neuronpedia

    INDEX
    Explanations

    references to animals or animal-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compton
    -0.77
    heit
    -0.76
    unda
    -0.72
    lain
    -0.72
    landers
    -0.70
    ounced
    -0.69
    creen
    -0.68
    lining
    -0.66
    hower
    -0.66
    itudinal
    -0.65
    POSITIVE LOGITS
     carc
    0.99
     kingdom
    0.94
    aclysm
    0.89
     cruelty
    0.88
    oreal
    0.87
     animals
    0.87
    arium
    0.86
     lover
    0.83
     welfare
    0.83
     mammals
    0.82
    Act Density 0.037%

    No Known Activations