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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated references within a narrative context

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

    personal pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.51
     cafetería
    -0.47
     rodillas
    -0.45
     gafas
    -0.42
     llavero
    -0.41
     piernas
    -0.41
     cepillo
    -0.41
     tropas
    -0.40
    Organisateur
    -0.40
     agresión
    -0.40
    POSITIVE LOGITS
     kasarigan
    0.55
    ArgsConstructor
    0.52
    nisse
    0.51
    ousands
    0.47
    weck
    0.46
    ejs
    0.46
    )_/¯
    0.45
     Bark
    0.44
    ousand
    0.43
    aq
    0.42
    Act Density 0.243%

    No Known Activations