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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to voting yes on a specific issue

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bage
    -0.81
    leted
    -0.69
    perial
    -0.68
    inary
    -0.67
    hyde
    -0.64
    EStreamFrame
    -0.63
     Halls
    -0.61
    Wra
    -0.61
    RAW
    -0.61
     Stru
    -0.60
    POSITIVE LOGITS
    terday
    1.85
     matter
    0.72
     Means
    0.71
    hua
    0.71
     sir
    0.70
    TER
    0.70
    yes
    0.69
    YES
    0.67
     bake
    0.66
    ï¸
    0.66
    Act Density 0.023%

    No Known Activations