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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, works, or related entities

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    reshold
    -0.50
    lasm
    -0.48
     ligiloj
    -0.47
    casila
    -0.47
     rest
    -0.46
    AddTagHelper
    -0.45
    स्
    -0.45
    BREAK
    -0.44
    醒
    -0.44
    Suara
    -0.43
    POSITIVE LOGITS
    uality
    1.00
    rano
    1.00
     Segal
    0.91
     المعيارى
    0.84
     fain
    0.79
     виправивши
    0.75
     moths
    0.75
    PhysRevD
    0.75
     betweenstory
    0.73
    oya
    0.72
    Act Density 0.034%

    No Known Activations