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

    Neuronpedia

    INDEX
    Explanations

    references to silence or silencing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     industrias
    -0.55
     particuliers
    -0.52
    AsUp
    -0.51
     enfermos
    -0.51
     Handlungen
    -0.50
     embarazadas
    -0.50
     chrétienne
    -0.49
     miasto
    -0.49
     działalności
    -0.48
     compañías
    -0.48
    POSITIVE LOGITS
     silent
    1.05
     sil
    0.90
     Sil
    0.88
     Silent
    0.84
     silence
    0.80
    Sil
    0.77
     SIL
    0.76
     silencing
    0.75
    silent
    0.75
    SIL
    0.73
    Act Density 0.232%

    No Known Activations