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

    Neuronpedia

    INDEX
    Explanations

    nouns and names of people or historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.39
     Wadsworth
    -0.37
    wake
    -0.37
    vac
    -0.34
    vas
    -0.34
     Vaz
    -0.34
     Vasco
    -0.33
    ûte
    -0.32
     Wak
    -0.32
     Vac
    -0.32
    POSITIVE LOGITS
     Will
    2.23
     Willi
    2.16
     Wil
    2.11
    Will
    2.09
    Wil
    2.02
    Willi
    2.00
    WILL
    1.98
     Willa
    1.86
     William
    1.86
    wil
    1.85
    Act Density 0.857%

    No Known Activations