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

    Neuronpedia

    INDEX
    Explanations

    information about family relationships and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cual
    -0.44
    mozilla
    -0.42
     Vork
    -0.42
    域
    -0.41
    })$}
    -0.41
     خاط
    -0.41
    rencies
    -0.41
    pace
    -0.40
     دهید
    -0.40
    dań
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.82
     pinulongan
    0.80
    Obrázky
    0.77
    ArrowToggle
    0.76
    UnsafeEnabled
    0.71
     cherchés
    0.70
    enterOuterAlt
    0.70
     Roskov
    0.67
    :✨
    0.67
    ValueGeneration
    0.66
    Act Density 0.168%

    No Known Activations