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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns and reflexive pronouns

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

    possessive pronouns and reflexives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.59
    LabelTagHelper
    -0.50
     StringTokenizer
    -0.45
    afficheront
    -0.45
     ExecuteAsync
    -0.44
     spy
    -0.42
    ExtendWith
    -0.41
    djangoproject
    -0.39
    jątk
    -0.39
    .*")]
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.56
    enumii
    0.48
    Chham
    0.45
    posób
    0.43
     مشين
    0.43
    urlpatterns
    0.40
    httphttps
    0.40
     butterknife
    0.39
    StoreMessageInfo
    0.38
     CYTHON
    0.37
    Act Density 0.000%

    No Known Activations