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

    Neuronpedia

    INDEX
    Explanations

    vocabulary related to well-being and comfort

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

    experiencecomfort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.59
     <=",
    -0.58
    دانشنامهٔ
    -0.54
    transQ
    -0.54
     lenker
    -0.53
     AssemblyCompany
    -0.52
     المعيارى
    -0.51
     للاسماء
    -0.50
    الدراسه
    -0.50
     informée
    -0.50
    POSITIVE LOGITS
    engagent
    0.43
     ModelExpression
    0.39
     kirj
    0.38
     Vergnügen
    0.37
     communs
    0.36
     Asamblea
    0.35
     yelek
    0.35
     Inscrivez
    0.34
     essentiels
    0.34
    løs
    0.34
    Act Density 0.023%

    No Known Activations