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

    Neuronpedia

    INDEX
    Explanations

    features and capabilities related to consumer products, particularly electronics

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

    "your" or related possessive pronouns

    np_acts-logits-general · gemini-2.0-flash

    your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RSpec
    -0.73
     somewhat
    -0.71
    较为
    -0.69
     данного
    -0.67
    somewhat
    -0.67
    {}",
    -0.65
    也算是
    -0.64
    であるが
    -0.64
     although
    -0.64
     beziehungs
    -0.63
    POSITIVE LOGITS
    your
    0.74
     your
    0.73
     YOUR
    0.69
    ™
    0.69
     clín
    0.69
     confiance
    0.68
     youll
    0.68
     smarter
    0.68
     superiori
    0.68
     yours
    0.66
    Act Density 0.501%

    No Known Activations