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

    Neuronpedia

    INDEX
    Explanations

    words related to approval/disapproval ratings in relation to political figures

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to approval and disapproval ratings in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udic
    -0.68
    orage
    -0.67
    esis
    -0.66
    çīĪ
    -0.65
    utical
    -0.65
    GV
    -0.65
    aer
    -0.64
     Codex
    -0.64
    RAW
    -0.61
     Kepler
    -0.61
    POSITIVE LOGITS
     rating
    1.05
     ratings
    1.02
    rating
    0.92
    rated
    0.85
    Rating
    0.77
    watching
    0.75
    osuke
    0.74
    lihood
    0.74
     neighb
    0.73
     Ratings
    0.70
    Act Density 0.084%

    No Known Activations