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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating interpersonal relationships or social interactions

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

    personal and possessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.52
     esterni
    -0.48
     saites
    -0.45
    RTLI
    -0.45
    protoimpl
    -0.44
    舺
    -0.42
    Արտաքին
    -0.41
    səhifə
    -0.40
    ammans
    -0.40
    ✨:
    -0.40
    POSITIVE LOGITS
     propias
    0.47
    自分も
    0.46
     own
    0.44
     propia
    0.44
    RenderAtEndOf
    0.42
     propios
    0.42
     propio
    0.41
     propre
    0.41
     eigener
    0.41
     propres
    0.41
    Act Density 0.129%

    No Known Activations