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

    Neuronpedia

    INDEX
    Explanations

    references to "s" which could indicate possessive forms or parts of compound nouns related to various subjects

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

    possessive nation's descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.52
     carc
    -0.50
     Einkauf
    -0.49
     Evangelio
    -0.49
    存于互联网档案馆
    -0.49
    Pautan
    -0.47
     brisa
    -0.46
    หม
    -0.45
     galer
    -0.45
     detención
    -0.45
    POSITIVE LOGITS
     national
    0.69
     National
    0.61
     Nigeria
    0.59
     Britain
    0.57
     China
    0.57
     nation
    0.56
    national
    0.55
     India
    0.53
    National
    0.51
     Australia
    0.50
    Act Density 0.015%

    No Known Activations