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

    Neuronpedia

    INDEX
    Explanations

    repeated references to the government and its statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apt
    -0.15
    \application
    -0.14
    usercontent
    -0.14
    CKER
    -0.14
     Les
    -0.14
     Fro
    -0.14
     Dr
    -0.13
    eldom
    -0.13
     Lips
    -0.13
    úa
    -0.13
    POSITIVE LOGITS
     Museum
    0.20
     Simulator
    0.17
     Foundation
    0.17
     Company
    0.16
     Church
    0.16
     Hospital
    0.16
     Mosque
    0.16
     Stadium
    0.16
     Council
    0.15
     College
    0.15
    Act Density 0.012%

    No Known Activations