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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and possessive adjectives

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

    Possessive pronouns followed by descriptions

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns followed by personal attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.65
    دانشنامهٔ
    -0.59
    OGND
    -0.53
     Scientists
    -0.52
    mybatisplus
    -0.51
    AuthContext
    -0.49
     obligé
    -0.48
    出版年
    -0.48
     egiten
    -0.48
    Organiser
    -0.48
    POSITIVE LOGITS
     passion
    0.75
     expertise
    0.75
     latest
    0.73
     work
    0.72
     grandfather
    0.71
     father
    0.68
     specialties
    0.67
     recent
    0.66
     hometown
    0.65
     involvement
    0.63
    Act Density 0.274%

    No Known Activations