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

    Neuronpedia

    INDEX
    Explanations

    references to government surveillance and intelligence operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iska
    -0.17
    aira
    -0.16
    fst
    -0.16
    atti
    -0.15
    xFFF
    -0.15
    opup
    -0.14
    _digits
    -0.14
    itest
    -0.14
    lsen
    -0.14
     Oliv
    -0.14
    POSITIVE LOGITS
     intelligence
    0.54
     Intelligence
    0.50
    intelligence
    0.44
     intel
    0.36
    elligence
    0.32
     intelig
    0.32
     Intel
    0.29
     CIA
    0.29
    Intel
    0.26
     NSA
    0.24
    Act Density 0.084%

    No Known Activations