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

    Neuronpedia

    INDEX
    Explanations

    specific language elements related to community guidelines and rules

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

    not, assume, allowed

    np_acts-logits-general · gemini-2.5-flash-lite

    Phrases expressing rules, permissions, obligations, or requests — i.e., deontic/modal language (must, allowed, please, have to, no, only, etc.).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.50
    SequentialGroup
    -0.49
     nozze
    -0.46
     DBNull
    -0.42
    altor
    -0.42
    Parcelize
    -0.42
     opty
    -0.41
     Secretario
    -0.40
    χεία
    -0.40
    setUsername
    -0.40
    POSITIVE LOGITS
     linkovi
    0.64
     Chwiliwch
    0.45
    CppMethod
    0.43
    ResponseWriter
    0.43
    NewReader
    0.39
    AddTagHelper
    0.39
    ValueStyle
    0.38
     désolés
    0.36
     Signalez
    0.35
     MonoBehaviour
    0.35
    Act Density 0.693%

    No Known Activations