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

    Neuronpedia

    INDEX
    Explanations

    names and references related to scientific studies or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raft
    -0.18
    otte
    -0.15
    ossa
    -0.14
    adil
    -0.14
     fashion
    -0.14
    лини
    -0.13
    arian
    -0.13
    910
    -0.12
    Äĩi
    -0.12
    llen
    -0.12
    POSITIVE LOGITS
    czy
    0.15
    anim
    0.15
     dos
    0.14
     sey
    0.14
    оди
    0.14
    ders
    0.14
    zap
    0.14
    æĭ³
    0.14
    ibase
    0.14
    geb
    0.13
    Act Density 0.258%

    No Known Activations