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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns related to personal or collective experiences

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

    possessive pronoun followed by personal attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuenca
    -0.49
    ycznego
    -0.48
     Autónoma
    -0.47
     Regionen
    -0.46
     unjustly
    -0.46
     Bewußt
    -0.46
     hermanas
    -0.45
     esclavos
    -0.45
    ChildScrollView
    -0.45
     Flasche
    -0.43
    POSITIVE LOGITS
     Qual
    0.47
     viciss
    0.44
    nmgp
    0.43
    shafen
    0.43
     Quer
    0.41
     CallOverrides
    0.41
     sangu
    0.40
    awtextra
    0.40
    UNIS
    0.40
     positions
    0.40
    Act Density 0.048%

    No Known Activations