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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political engagement and information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fas
    -0.17
    quia
    -0.16
     poh
    -0.15
     secret
    -0.14
     tts
    -0.14
    yo
    -0.14
    åĭŁ
    -0.14
    itches
    -0.14
     Ulus
    -0.14
    usz
    -0.14
    POSITIVE LOGITS
     residents
    0.23
     Audience
    0.21
     audiences
    0.21
     audience
    0.21
    /local
    0.19
     locals
    0.19
     local
    0.19
     Residents
    0.19
    Residents
    0.18
     consumption
    0.18
    Act Density 0.002%

    No Known Activations