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

    Neuronpedia

    INDEX
    Explanations

    percentages and numeric data in statements

    oai_token-act-pair · gpt-3.5-turbo

    percentages indicating public opinion or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Redd
    -0.79
     Rav
    -0.72
    Rew
    -0.68
    ansom
    -0.66
    ciation
    -0.65
    Font
    -0.61
     splend
    -0.60
     Blessing
    -0.59
     Renaissance
    -0.57
    imens
    -0.57
    POSITIVE LOGITS
     undecided
    0.96
    agree
    0.88
    ecided
    0.86
     respondents
    0.85
     surveyed
    0.82
    alion
    0.80
     disapprove
    0.74
     polled
    0.73
     opted
    0.73
     opting
    0.72
    Act Density 0.080%

    No Known Activations