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

    Neuronpedia

    INDEX
    Explanations

    references to scientific concepts and statistical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeclareMath
    -0.66
     مرئيه
    -0.66
     محفوظة
    -0.64
     Â
    -0.62
     pann
    -0.61
    eſt
    -0.61
    igshid
    -0.60
     
    -0.60
    rungsseite
    -0.60
     ↓,
    -0.59
    POSITIVE LOGITS
    <bos>
    0.80
    J
    0.71
    FTFY
    0.68
     ,
    0.67
    ，”
    0.65
    i
    0.64
    l
    0.64
    R
    0.64
    S
    0.63
    r
    0.63
    Act Density 1.075%

    No Known Activations