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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or relationships between different entities

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

    comparisons using 'that of'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.60
     ſte
    -0.58
     faſt
    -0.57
     تضيفلها
    -0.54
     poffible
    -0.52
     fhew
    -0.52
     ſta
    -0.51
     Chriftian
    -0.50
     Reſ
    -0.50
     ſtate
    -0.49
    POSITIVE LOGITS
     diejenigen
    0.44
    ništvo
    0.43
    jenigen
    0.43
     desmotivaciones
    0.42
    Personensuche
    0.42
    Життєпис
    0.42
    ita
    0.42
     vielmehr
    0.41
     unknownFields
    0.41
     fatiga
    0.41
    Act Density 0.093%

    No Known Activations