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

    Neuronpedia

    INDEX
    Explanations

    terms related to ethics and moral reasoning

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    fjspx
    -0.56
    Istorija
    -0.55
    ьогодні
    -0.53
    InputTagHelper
    -0.52
     Hoover
    -0.50
    eningrad
    -0.50
    EntityFramework
    -0.49
     unconsciously
    -0.48
     viewType
    -0.47
     groupBox
    -0.46
    POSITIVE LOGITS
     bouch
    0.66
    XmlAccessType
    0.65
    abestanden
    0.64
    rungsseite
    0.64
    Prä
    0.59
    rawDesc
    0.59
    uspiel
    0.58
     pluie
    0.56
    λαι
    0.56
     ویکی‌پدی
    0.55
    Act Density 0.026%

    No Known Activations