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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and numerical data in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    therford
    -0.53
     Electro
    -0.52
    ">//
    -0.51
    Dyn
    -0.50
     differ
    -0.49
    Electro
    -0.48
     ineligible
    -0.48
     dụng
    -0.48
    alini
    -0.48
     Daun
    -0.48
    POSITIVE LOGITS
    bkz
    0.77
    WillAppear
    0.75
     étoient
    0.75
     avoient
    0.75
     asiatique
    0.72
    setVerticalGroup
    0.70
    +#+#
    0.69
     Norvège
    0.66
    aarrggbb
    0.66
    AndEndTag
    0.65
    Act Density 0.016%

    No Known Activations