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

    Neuronpedia

    INDEX
    Explanations

    references to female pronouns and possessive forms

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

    feminine pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    økt
    -0.34
    StructEnd
    -0.32
    Aktualisiert
    -0.32
     Captains
    -0.29
    legungen
    -0.29
    legt
    -0.28
    HIND
    -0.28
    patine
    -0.28
    Lyn
    -0.28
     оригіналу
    -0.28
    POSITIVE LOGITS
    AddTagHelper
    0.61
    Obrigada
    0.59
     ModelRenderer
    0.58
    himself
    0.55
     NSCoder
    0.54
    contentLoaded
    0.54
    :✨
    0.53
     ExecuteAsync
    0.53
     himself
    0.53
     daughter
    0.52
    Act Density 0.172%

    No Known Activations