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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing opinions about product quality and personal preferences

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

    positive sentiment and praise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.47
     defaultstate
    -0.47
    SharedDtor
    -0.47
     Taktlose
    -0.43
    elemField
    -0.39
    BeginContext
    -0.39
    олові
    -0.39
    TypedDataSet
    -0.39
    лтемелер
    -0.38
     Letra
    -0.38
    POSITIVE LOGITS
     excellent
    0.66
    excellent
    0.60
     excellently
    0.54
     versatile
    0.53
     superbly
    0.53
     Excellent
    0.50
     EXCELL
    0.50
     perfection
    0.49
    Excellent
    0.49
     excelente
    0.48
    Act Density 0.014%

    No Known Activations