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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obligations or suggestions towards others

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

    can followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.68
    SequentialGroup
    -0.51
    tonode
    -0.51
     CWE
    -0.50
    Personendaten
    -0.49
     cherchés
    -0.48
    StoryboardSegue
    -0.47
    Portail
    -0.47
    Personensuche
    -0.46
    freopen
    -0.44
    POSITIVE LOGITS
    swatch
    0.35
    roek
    0.34
    ZQ
    0.34
    ust
    0.34
    Życiorys
    0.32
    cephala
    0.32
    равда
    0.32
     continuing
    0.32
    BigInteger
    0.31
    utex
    0.31
    Act Density 0.062%

    No Known Activations