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

    Neuronpedia

    INDEX
    Explanations

    references to atrocities and war crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Needle
    -0.15
     Prest
    -0.15
     schem
    -0.14
    enal
    -0.14
     l
    -0.14
     overd
    -0.14
     nominal
    -0.14
    utf
    -0.14
    obby
    -0.14
    npos
    -0.13
    POSITIVE LOGITS
    immel
    0.16
     Lod
    0.15
    urum
    0.14
    _KHR
    0.14
     improvised
    0.13
    ilor
    0.13
    ầm
    0.13
    /manual
    0.13
    ocl
    0.13
    /loader
    0.13
    Act Density 0.249%

    No Known Activations