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

    Neuronpedia

    INDEX
    Explanations

    words related to the scope, nature, or validity of something, often in a scientific, legal, or political context.

    oai_token-act-pair · gemini-2.0-flash

    words indicating possession or relationship

    np_token-act-pair-logits · gpt-4o-mini

    say "of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.59
    setStyleSheet
    -0.52
    atschapp
    -0.51
    lgari
    -0.48
     structure
    -0.47
    SerializedName
    -0.47
    DataAdapter
    -0.47
    én
    -0.47
     us
    -0.47
     "
    -0.47
    POSITIVE LOGITS
     of
    1.51
    ของ
    0.80
     của
    0.75
     InputDecoration
    0.74
     célèbres
    0.66
     ofre
    0.64
     ofreci
    0.64
    ủa
    0.64
     ofrec
    0.63
    uação
    0.63
    Act Density 6.258%

    No Known Activations