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

    Neuronpedia

    INDEX
    Explanations

    statistics or survey results

    oai_token-act-pair · gpt-3.5-turbo

    references to polls and surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Contents
    -0.81
    assetsadobe
    -0.78
    agents
    -0.78
     talents
    -0.73
    devices
    -0.72
     engagements
    -0.72
     extrad
    -0.68
     conting
    -0.67
     tyres
    -0.66
     tattoos
    -0.66
    POSITIVE LOGITS
     survey
    1.24
     Pew
    1.19
     Gallup
    1.14
     study
    1.10
     poll
    1.04
     whopping
    1.01
     plurality
    0.95
     quarter
    0.93
     Rasmussen
    0.93
    usterity
    0.90
    Act Density 0.141%

    No Known Activations