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

    Neuronpedia

    INDEX
    Explanations

    references to political and military strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rette
    -0.16
    emento
    -0.15
    nze
    -0.15
     Conspiracy
    -0.14
    .grpc
    -0.14
    osate
    -0.14
    åĩī
    -0.13
    tti
    -0.13
    antis
    -0.13
    侯
    -0.13
    POSITIVE LOGITS
     surge
    0.27
     Petra
    0.26
     Surge
    0.25
     Afghan
    0.24
     Afghanistan
    0.24
     troop
    0.22
     stabilization
    0.22
     Af
    0.22
     trainers
    0.21
     Iraq
    0.21
    Act Density 0.071%

    No Known Activations