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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts emphasizing community, unity, and shared experiences

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

    phrases related to communal identity and uniformity

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

    precedes common nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InvalidProtocol
    -0.78
    featureID
    -0.70
     ProtoMessage
    -0.63
     resourceCulture
    -0.59
    Personendaten
    -0.56
     esterno
    -0.56
     dépens
    -0.55
     feroit
    -0.55
     inútil
    -0.54
     épis
    -0.54
    POSITIVE LOGITS
     Мексичка
    0.68
    RÉ
    0.67
    ëlle
    0.63
     utafitiHapana
    0.62
     فريبيس
    0.61
     everything
    0.60
    ngdoc
    0.60
    setw
    0.59
    &_
    0.58
     timing
    0.58
    Act Density 0.145%

    No Known Activations