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

    Neuronpedia

    INDEX
    Explanations

    references to political surveillance and intelligence activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rag
    -0.17
    inters
    -0.16
    ¼
    -0.16
    noxious
    -0.15
    verity
    -0.15
    ugu
    -0.14
     Sav
    -0.14
    εÏĤ
    -0.14
    yg
    -0.13
    åı°
    -0.13
    POSITIVE LOGITS
    aja
    0.15
     Bust
    0.15
     Levi
    0.14
    olation
    0.14
     NSA
    0.14
    NotificationCenter
    0.14
    _OW
    0.14
    CALE
    0.14
     Operation
    0.14
    .Byte
    0.14
    Act Density 0.024%

    No Known Activations