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

    Neuronpedia

    INDEX
    Explanations

    terms related to various species and their biological classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Animals
    -0.18
     rats
    -0.17
     animals
    -0.17
    animals
    -0.16
     animal
    -0.16
     rodents
    -0.15
     Animal
    -0.15
    rats
    -0.15
    eration
    -0.15
    extensions
    -0.15
    POSITIVE LOGITS
     populations
    0.24
     population
    0.23
    /cat
    0.18
     species
    0.18
     husband
    0.17
    population
    0.17
    -human
    0.17
     physiology
    0.17
    friendly
    0.16
    /pl
    0.16
    Act Density 0.105%

    No Known Activations