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

    Neuronpedia

    INDEX
    Explanations

    terms related to carbon and its environmental impact

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.75
    GBT
    -0.75
     Psychiatric
    -0.73
    ---------------
    -0.70
    HCR
    -0.69
    swer
    -0.69
    doms
    -0.69
    mir
    -0.68
    udeb
    -0.68
     Brach
    -0.67
    POSITIVE LOGITS
     dioxide
    1.68
     fibre
    1.04
    aceous
    1.02
    ohydrate
    1.00
     emissions
    0.99
     footprint
    0.98
     fiber
    0.98
     offsets
    0.96
    ohyd
    0.92
     footprints
    0.92
    Act Density 0.014%

    No Known Activations