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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals, particularly focusing on ownership and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vectorielles
    -0.51
     przekon
    -0.46
    ⤹
    -0.45
     Wikiseite
    -0.44
     Fantasia
    -0.44
     wireType
    -0.43
    pecabe
    -0.42
     nameof
    -0.42
     Futura
    -0.42
    ⟭
    -0.41
    POSITIVE LOGITS
     ujednoznacz
    0.56
    His
    0.52
     They
    0.52
     She
    0.50
     Their
    0.50
    She
    0.49
     they
    0.49
     His
    0.48
     He
    0.48
    rungsseite
    0.47
    Act Density 0.721%

    No Known Activations