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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political intrigue and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Karma
    -0.18
     brill
    -0.16
     tavs
    -0.15
     Tee
    -0.14
     Grove
    -0.14
     Biblical
    -0.14
    183
    -0.14
    út
    -0.14
     GUIStyle
    -0.14
    woff
    -0.14
    POSITIVE LOGITS
     Å
    0.23
    vpn
    0.16
     Exceptions
    0.15
     Rarity
    0.15
     divers
    0.15
    opy
    0.15
     Instances
    0.15
    iversit
    0.15
     vpn
    0.14
    iversite
    0.14
    Act Density 0.105%

    No Known Activations