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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.83
    EDEFAULT
    -0.81
    CppMethod
    -0.78
     nahilalakip
    -0.71
    rungsseite
    -0.68
     ujednoznacz
    -0.65
    Tembelea
    -0.65
     saites
    -0.65
     betweenstory
    -0.64
    Datuak
    -0.64
    POSITIVE LOGITS
    kanan
    0.32
     meisje
    0.30
     antwoord
    0.29
    术
    0.29
     prefeitura
    0.28
     Antwort
    0.28
    gaande
    0.28
     Vergrößern
    0.27
     čierna
    0.27
     paard
    0.27
    Act Density 1.035%

    No Known Activations