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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and references to specific names or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Rai, Rae

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Edith
    -0.54
     فريبيس
    -0.51
     betweenstory
    -0.50
    ächs
    -0.46
    pean
    -0.46
     Viv
    -0.45
    ╯
    -0.44
     Nutri
    -0.44
     nack
    -0.43
     fag
    -0.43
    POSITIVE LOGITS
     Rai
    2.59
    Rai
    2.38
     RAI
    1.68
     rai
    1.61
    rai
    1.34
    RAI
    1.32
     Rae
    1.10
     Rais
    0.94
    Rae
    0.91
     Рай
    0.90
    Act Density 0.002%

    No Known Activations