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

    Neuronpedia

    INDEX
    Explanations

    indicators of deception or misinformation in political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemLayout
    -0.53
    RTDA
    -0.51
    erialization
    -0.49
     Affiliations
    -0.48
    XmlAccessType
    -0.47
     devriez
    -0.45
    DrawerToggle
    -0.45
    IntoConstraints
    -0.45
    ArgsConstructor
    -0.44
     ***!
    -0.44
    POSITIVE LOGITS
     viewers
    2.32
     consumers
    2.23
     audiences
    2.23
     readers
    2.15
     fans
    2.08
     customers
    2.04
     listeners
    1.94
     voters
    1.94
     users
    1.93
     audience
    1.91
    Act Density 1.230%

    No Known Activations