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

    Neuronpedia

    INDEX
    Explanations

    references to natural environments, particularly forests

    oai_token-act-pair · gpt-3.5-turbo

    references to forests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.66
    mir
    -0.65
    nor
    -0.64
    enger
    -0.63
    FontSize
    -0.61
     Pric
    -0.61
    pter
    -0.60
    ptions
    -0.60
    GET
    -0.58
    Extra
    -0.58
    POSITIVE LOGITS
     canopy
    1.05
    lands
    1.04
    forest
    1.03
     forests
    0.97
     vegetation
    0.94
     biome
    0.93
     habitat
    0.91
    ocene
    0.90
    ãĤ¼ãĤ¦ãĤ¹
    0.90
     forest
    0.89
    Act Density 0.043%

    No Known Activations