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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "We" indicating group statements or collective actions

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

    "we" followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AISSEE
    -0.68
     defaultstate
    -0.63
    Хьажоргаш
    -0.62
    GTCX
    -0.57
    ACHUSET
    -0.55
     Италијани
    -0.53
     GenerationType
    -0.48
     ujednoznacz
    -0.48
    AutoModerator
    -0.47
    DataAnnotations
    -0.47
    POSITIVE LOGITS
    We
    0.56
     We
    0.54
    timme
    0.44
     we
    0.43
    we
    0.42
     אנו
    0.38
     Ours
    0.36
    WE
    0.35
     bekende
    0.34
    oarece
    0.33
    Act Density 0.074%

    No Known Activations