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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning and dialogue interaction

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

    past occurrences and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.48
     leyes
    -0.43
     révolution
    -0.43
     legislación
    -0.42
     Política
    -0.40
     ainfi
    -0.40
     asesino
    -0.40
     entornos
    -0.39
     ilustracja
    -0.39
     professionnelle
    -0.39
    POSITIVE LOGITS
     otomatig
    0.70
     yesterday
    0.65
     earlier
    0.62
     вчера
    0.59
    あんな
    0.56
     overheard
    0.56
     kissed
    0.55
     Yesterday
    0.55
     ieri
    0.54
    yesterday
    0.54
    Act Density 0.047%

    No Known Activations