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

    Neuronpedia

    INDEX
    Explanations

    descriptive sentiments relating to experiences or qualities

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

    words following 'there'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.85
    rungsseite
    -0.72
     disambiguazione
    -0.68
    posedge
    -0.67
    Personendaten
    -0.65
    IVEREF
    -0.65
     Савезне
    -0.64
    SharedDtor
    -0.64
     nahilalakip
    -0.62
    [@BOS@]
    -0.62
    POSITIVE LOGITS
     descripción
    0.35
     Meinung
    0.32
    description
    0.32
     mulut
    0.30
     tatlı
    0.29
     descrição
    0.29
     décrire
    0.29
    describe
    0.28
    sweet
    0.28
    DESCRIPTION
    0.28
    Act Density 0.062%

    No Known Activations