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

    Neuronpedia

    INDEX
    Explanations

    references to Russian diplomats and military personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    豪
    -0.15
    obel
    -0.15
    arah
    -0.14
    UCE
    -0.14
    vertis
    -0.14
    opic
    -0.13
     Chall
    -0.13
    æī
    -0.13
     brace
    -0.13
    asa
    -0.13
    POSITIVE LOGITS
     Vital
    0.30
     Gle
    0.27
     Ev
    0.23
     Alexander
    0.21
     Sergei
    0.21
    Ark
    0.20
     Fed
    0.20
     Ark
    0.20
     Kir
    0.19
    Alexander
    0.19
    Act Density 0.032%

    No Known Activations