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

    Neuronpedia

    INDEX
    Explanations

    references to political turmoil and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yn
    -0.17
    kke
    -0.16
     Newman
    -0.16
    olik
    -0.15
     UUID
    -0.15
     ноÑĢмаÑĤив
    -0.15
    ueva
    -0.15
     resett
    -0.15
    han
    -0.14
    ias
    -0.14
    POSITIVE LOGITS
     demonstrations
    0.28
     demonstrators
    0.24
     Demonstr
    0.22
     protests
    0.22
     Jasmine
    0.21
     protesters
    0.20
     street
    0.20
     regime
    0.20
     Maid
    0.19
     Velvet
    0.19
    Act Density 0.077%

    No Known Activations