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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.50
    </>
    -0.42
    WebServlet
    -0.41
    }");
    -0.40
     Gear
    -0.40
     Hiding
    -0.40
     withdraw
    -0.39
     Mom
    -0.39
    !*\
    -0.38
     mom
    -0.38
    POSITIVE LOGITS
    tvguidetime
    0.60
    IntoConstraints
    0.56
    <_>
    0.56
    tanleria
    0.53
     Grüsse
    0.52
    BIÉN
    0.49
    También
    0.48
    awtextra
    0.48
    piecze
    0.47
    hoeddwyd
    0.47
    Act Density 1.530%

    No Known Activations