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

    Neuronpedia

    INDEX
    Explanations

    references to possession or personal relationships

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

    Possessive pronouns followed by a title

    np_acts-logits-general · gemini-2.0-flash

    possessive pronoun + relation/group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ')],
    -0.53
     TimeUnit
    -0.52
    DoubleQuotes
    -0.51
    SharedCtor
    -0.49
    ("")]
    -0.49
    setVerticalGroup
    -0.48
    ;';
    -0.48
    };*/
    -0.47
    utek
    -0.47
    );*/
    -0.46
    POSITIVE LOGITS
    fellow
    0.78
     assigned
    0.72
     fellow
    0.72
     neighbors
    0.69
    WebServlet
    0.68
     neighbours
    0.68
     favorite
    0.67
     favourite
    0.66
     teammates
    0.64
     classmates
    0.61
    Act Density 0.238%

    No Known Activations