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

    Neuronpedia

    INDEX
    Explanations

    mandatory conditions and obligations in legal or procedural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expresses obligation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kohdetta
    -0.47
     "..\..\..\
    -0.46
    rovnik
    -0.45
    verifyException
    -0.43
    abestanden
    -0.43
    клопе
    -0.42
    AnimationsModule
    -0.41
    ptonshire
    -0.40
    Grüße
    -0.40
    getDoctrine
    -0.40
    POSITIVE LOGITS
     must
    0.63
    must
    0.54
     Must
    0.51
    Must
    0.50
     registered
    0.46
     adhered
    0.45
     MUST
    0.45
     compul
    0.41
     preferred
    0.41
    magitan
    0.41
    Act Density 0.031%

    No Known Activations