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

    Neuronpedia

    INDEX
    Explanations

    mentions of zoos

    oai_token-act-pair · gpt-3.5-turbo

    references to various zoos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pring
    -0.74
    acies
    -0.71
    lass
    -0.70
    ioxide
    -0.70
     Lauder
    -0.70
    itimate
    -0.69
     Prosper
    -0.68
     glim
    -0.66
    ÑĮ
    -0.66
    agher
    -0.66
    POSITIVE LOGITS
     animals
    0.93
    onga
    0.92
    ey
    0.84
    elling
    0.83
    ÅĤ
    0.82
    biology
    0.82
     Animals
    0.81
    erness
    0.78
    yssey
    0.78
     Zoo
    0.78
    Act Density 0.049%

    No Known Activations