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

    Neuronpedia

    INDEX
    Explanations

    scenarios involving political intrigue and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Karma
    -0.18
    út
    -0.16
    ughs
    -0.15
     télé
    -0.15
    idy
    -0.15
     подÑģ
    -0.15
     brilliantly
    -0.15
     tele
    -0.15
    argout
    -0.15
    plit
    -0.14
    POSITIVE LOGITS
     Å
    0.20
     divers
    0.18
     popis
    0.17
    vpn
    0.15
     Turk
    0.15
     meer
    0.15
    meer
    0.15
     ãĢĪ
    0.15
     vp
    0.14
    arie
    0.14
    Act Density 0.104%

    No Known Activations