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

    Neuronpedia

    INDEX
    Explanations

    references to media relations and communication strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inis
    -0.16
    adt
    -0.16
    ij
    -0.15
    orta
    -0.15
     Reeves
    -0.15
    uÃŃ
    -0.14
    ãĤ¤ãĥ³
    -0.14
     charged
    -0.14
    ramer
    -0.14
     Bers
    -0.14
    POSITIVE LOGITS
    atoon
    0.17
    ully
    0.15
    ifa
    0.15
    _exceptions
    0.15
    compound
    0.15
    ippet
    0.14
     Ukra
    0.14
     compound
    0.14
    646
    0.13
    .prod
    0.13
    Act Density 0.033%

    No Known Activations