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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate systemic corruption or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kami
    -0.16
    976
    -0.15
    berry
    -0.14
    éł¼
    -0.14
    557
    -0.14
     Oscar
    -0.14
     Gad
    -0.14
     vandal
    -0.13
    975
    -0.13
     uninsured
    -0.13
    POSITIVE LOGITS
     Bilder
    0.29
     Mason
    0.27
     Illum
    0.26
     Controllers
    0.23
     controllers
    0.23
     bilder
    0.22
     Roths
    0.21
    llum
    0.21
     Agenda
    0.21
     Elite
    0.21
    Act Density 0.107%

    No Known Activations