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

    Neuronpedia

    INDEX
    Explanations

    evaluative language related to standards and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    judged against a standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.72
     utafitiHapana
    -0.65
     وتسجيلات
    -0.62
    Espèce
    -0.58
    rungsseite
    -0.56
    homonymie
    -0.52
     Chwiliwch
    -0.52
    цездатний
    -0.50
    tvguidetime
    -0.50
    adpleegd
    -0.49
    POSITIVE LOGITS
     judged
    0.56
     comparaison
    0.51
     comparison
    0.49
     performance
    0.49
     juicio
    0.46
     penilaian
    0.46
     comparación
    0.46
     arvio
    0.46
     jugement
    0.45
    Performance
    0.45
    Act Density 0.092%

    No Known Activations