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

    Neuronpedia

    INDEX
    Explanations

    references to government authority and drone policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordial
    -0.17
    steam
    -0.15
    éĶ
    -0.14
    allery
    -0.14
     Breath
    -0.14
     late
    -0.13
     âĶ
    -0.13
    /grpc
    -0.13
     ÏĥÏĩ
    -0.13
     ÑģоÑĨи
    -0.13
    POSITIVE LOGITS
    antanamo
    0.19
     Guantanamo
    0.17
    çµ
    0.17
    ToWorld
    0.16
     Predator
    0.16
    åŁºåľ°
    0.15
    icas
    0.15
     TORT
    0.15
     Tort
    0.15
     Git
    0.14
    Act Density 0.035%

    No Known Activations