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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistics

    oai_token-act-pair · gpt-3.5-turbo

    statistical data or percentages related to public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rew
    -0.66
    Merit
    -0.64
     Prelude
    -0.59
    PDATE
    -0.59
    Recipe
    -0.59
     Rebirth
    -0.57
     Strikes
    -0.57
    breaks
    -0.57
    Wars
    -0.56
     Raid
    -0.56
    POSITIVE LOGITS
     undecided
    0.84
     surveyed
    0.83
    ecided
    0.81
     disapprove
    0.80
    agree
    0.79
     respondents
    0.79
     unsure
    0.78
     overest
    0.77
     estimate
    0.75
    alion
    0.73
    Act Density 0.097%

    No Known Activations