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

    Neuronpedia

    INDEX
    Explanations

    information related to changes in emissions levels and reduction targets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ossip
    -0.77
     arra
    -0.75
     pawn
    -0.71
     teammates
    -0.70
     Sham
    -0.69
     offic
    -0.68
     DMCA
    -0.67
     backstage
    -0.65
     POV
    -0.65
    River
    -0.64
    POSITIVE LOGITS
     2050
    1.48
     2030
    1.47
     2025
    1.42
     2020
    1.26
     2021
    1.10
     2100
    1.10
    2020
    1.06
     GDP
    1.02
     2024
    1.01
     emissions
    0.95
    Act Density 0.879%

    No Known Activations