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

    Neuronpedia

    INDEX
    Explanations

    references to nuclear weapons and related geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osa
    -0.15
    etu
    -0.15
     <!--[
    -0.14
    ispiel
    -0.14
    Raster
    -0.13
    andas
    -0.13
    ietet
    -0.13
    onda
    -0.13
    _PATCH
    -0.13
    اتر
    -0.13
    POSITIVE LOGITS
     fiss
    0.20
     nuclear
    0.20
     Nuclear
    0.17
     uranium
    0.17
     plu
    0.17
     enrichment
    0.16
    Capability
    0.16
     enrich
    0.16
     plut
    0.16
     enriched
    0.16
    Act Density 0.024%

    No Known Activations