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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opinions or evaluations about ideas and decisions

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

    Comes after an adjective of positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    good adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SuspendLayout
    -0.41
    SOUNDBITE
    -0.41
    CloseOperation
    -0.40
    قایناق‌لار
    -0.38
    انجليز
    -0.38
    enderror
    -0.37
     Numerade
    -0.36
     conceded
    -0.36
    jenost
    -0.36
     Exactos
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.60
    GEBURTSDATUM
    0.58
    onAttach
    0.57
     CGSize
    0.50
    #+#
    0.50
    basti
    0.49
     unsustainable
    0.47
    Controllo
    0.45
    Bad
    0.43
     schlecht
    0.42
    Act Density 0.866%

    No Known Activations