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

    Neuronpedia

    INDEX
    Explanations

    concepts related to moral values and the consequences of committed behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.62
     nobly
    -0.49
    thenia
    -0.48
    wiek
    -0.46
    backers
    -0.44
    laise
    -0.44
    fxml
    -0.44
     handkerchief
    -0.44
     Rupert
    -0.43
    uinal
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.79
    Personendaten
    0.70
    хьтан
    0.67
     lenker
    0.67
    UnusedPrivate
    0.67
     فريبيس
    0.65
    0.65
    TemporalType
    0.64
    ########.
    0.63
    Kaynakça
    0.63
    Act Density 0.373%

    No Known Activations