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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating necessity or obligation

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

    "must" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    necessity or strong inference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     testigos
    -0.42
    ViewFeatures
    -0.41
    hadap
    -0.38
     ModelExpression
    -0.38
     Ufer
    -0.35
    //
    -0.35
     Alkohol
    -0.35
     Kriege
    -0.34
    Atsauces
    -0.34
    Geografi
    -0.34
    POSITIVE LOGITS
     must
    0.66
     Must
    0.63
    Surely
    0.62
     surely
    0.62
     Surely
    0.61
    must
    0.59
     فريبيس
    0.58
    Must
    0.57
    AndroidJUnit
    0.53
     MUST
    0.50
    Act Density 0.124%

    No Known Activations