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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and phrases indicating ownership or belonging

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

    Possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive determiners and following nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    telsen
    -0.52
    mongoose
    -0.51
    Capítulo
    -0.47
    ֲ
    -0.44
     LoggerFactory
    -0.44
    ωνα
    -0.44
     Mengh
    -0.43
     Band
    -0.43
    andır
    -0.43
     anahtar
    -0.42
    POSITIVE LOGITS
     own
    1.02
     propia
    0.74
     própria
    0.72
    ScopeManager
    0.71
     Own
    0.71
     mistress
    0.69
    own
    0.69
    EDEFAULT
    0.68
    Own
    0.67
     GenerationType
    0.65
    Act Density 0.343%

    No Known Activations