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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and associated personal references

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

    Possessive pronouns followed by thoughts/assessments

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.60
    出版年
    -0.57
    ]--;
    -0.57
    AddTagHelper
    -0.56
     Мексичка
    -0.55
    ⓧ
    -0.54
    ::::::::
    -0.54
     ligiloj
    -0.53
    født
    -0.53
    ыгана
    -0.52
    POSITIVE LOGITS
     colleagues
    0.87
     colleague
    0.79
     clients
    0.78
     countrymen
    0.76
     constituents
    0.76
     Colleagues
    0.68
     own
    0.67
    clients
    0.64
    ReusableCell
    0.63
     predecessors
    0.62
    Act Density 0.332%

    No Known Activations