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

    Neuronpedia

    INDEX
    Explanations

    important abbreviations and terminology in specific fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -gnu
    -0.16
     Roberts
    -0.16
    ubre
    -0.16
    _ROM
    -0.15
     Rib
    -0.15
    ãĥª
    -0.15
    robe
    -0.15
    (ro
    -0.14
     Rip
    -0.14
    رÙĪÙģ
    -0.14
    POSITIVE LOGITS
     ra
    0.90
     Ra
    0.89
    RA
    0.89
    ra
    0.87
     RA
    0.86
    Ra
    0.83
    _ra
    0.77
    .ra
    0.77
    -ra
    0.77
    (ra
    0.75
    Act Density 0.307%

    No Known Activations