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

    Neuronpedia

    INDEX
    Explanations

    titles or forms of address related to individuals, particularly those with formal titles

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

    titles followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.65
     يتيمه
    -0.56
    はじめに
    -0.46
     INTERESAR
    -0.40
    Välislingid
    -0.40
     cerrada
    -0.39
     puissiez
    -0.39
    makeConstraints
    -0.38
     mengalir
    -0.37
     giudi
    -0.37
    POSITIVE LOGITS
     mister
    0.60
    Mister
    0.60
     Mr
    0.59
     Mister
    0.58
     Miss
    0.57
    mister
    0.55
    Miss
    0.53
    Mr
    0.53
     miss
    0.52
     Mrs
    0.52
    Act Density 0.025%

    No Known Activations