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

    Neuronpedia

    INDEX
    Explanations

    mentions of oaths and related legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oath
    -2.13
     Oath
    -1.67
     oaths
    -1.52
     swear
    -1.01
     swore
    -0.97
     swearing
    -0.96
     sworn
    -0.91
     swears
    -0.78
     jura
    -0.77
     vow
    -0.68
    POSITIVE LOGITS
     flocks
    0.33
    ībā
    0.32
     adrift
    0.32
    intervento
    0.31
     responsabilità
    0.31
     gosto
    0.31
     generazione
    0.31
    少
    0.30
     Genre
    0.30
    gradu
    0.30
    Act Density 0.001%

    No Known Activations