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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographic locations or political entities involved in conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .SelectedItems
    -0.15
    krát
    -0.14
     addCriterion
    -0.14
    еÑĢо
    -0.14
    _PLATFORM
    -0.14
    roken
    -0.14
    ÑĢив
    -0.14
    iffies
    -0.14
    Borders
    -0.14
    idata
    -0.14
    POSITIVE LOGITS
     upscale
    0.21
     Australian
    0.19
     remote
    0.18
     heavily
    0.17
     volatile
    0.17
     Canadian
    0.17
     central
    0.17
     pred
    0.16
     normally
    0.16
     popular
    0.16
    Act Density 0.153%

    No Known Activations