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

    Neuronpedia

    INDEX
    Explanations

    mentions of interpersonal relationships and social connections

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

    Follows a pronoun

    np_acts-logits-general · gemini-2.0-flash

    pronouns and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.64
     themſelves
    -0.58
     myſelf
    -0.58
     propOrder
    -0.54
     himſelf
    -0.54
    caris
    -0.52
    HtmlAttribute
    -0.52
     pleaſure
    -0.52
     Pind
    -0.51
     ujednoznacz
    -0.51
    POSITIVE LOGITS
    NameInMap
    0.69
    Sucesor
    0.56
    Билгалдахарш
    0.54
    mergeFrom
    0.51
     exig
    0.50
     exige
    0.48
    Personensuche
    0.47
    StructEnd
    0.47
     wymaga
    0.46
     القدم
    0.45
    Act Density 0.423%

    No Known Activations