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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social sciences and economics

    oai_token-act-pair · gpt-3.5-turbo

    statements related to demographic and societal trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     offic
    -0.73
     scrim
    -0.73
    earchers
    -0.73
     glim
    -0.72
     decorations
    -0.71
     scoreboard
    -0.70
     showc
    -0.67
     volleyball
    -0.66
    eree
    -0.65
     navy
    -0.65
    POSITIVE LOGITS
     He
    1.36
     Specifically
    1.27
    He
    1.26
     Indeed
    1.18
     Furthermore
    1.17
     His
    1.16
     Whereas
    1.15
     Moreover
    1.14
     Accordingly
    1.14
    Specifically
    1.14
    Act Density 0.573%

    No Known Activations