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

    Neuronpedia

    INDEX
    Explanations

    words related to public opinion or consensus

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to polling data and public opinion trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.69
     Shutterstock
    -0.69
     unintentionally
    -0.65
    IRD
    -0.65
    racted
    -0.61
     voluntarily
    -0.61
     sacrific
    -0.60
    ruct
    -0.60
    ulence
    -0.58
    iae
    -0.58
    POSITIVE LOGITS
     doom
    0.78
     bullish
    0.77
     favoring
    0.72
     Remain
    0.71
     predicting
    0.68
     indicating
    0.68
     favorable
    0.66
    essim
    0.66
     optimism
    0.64
     Depot
    0.64
    Act Density 0.439%

    No Known Activations