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
    cassert
    -0.40
    assertNotNull
    -0.39
     Apo
    -0.39
    Apo
    -0.38
    Conclusión
    -0.37
     Novelty
    -0.36
    RegressionTest
    -0.36
     Topo
    -0.35
     phases
    -0.35
     concer
    -0.35
    POSITIVE LOGITS
    OGND
    0.48
    dit
    0.45
    dy
    0.45
    dle
    0.45
    ži
    0.44
     تضيفلها
    0.44
    ige
    0.43
     AssemblyVersion
    0.43
    iger
    0.42
     ComVisible
    0.42
    Act Density 0.371%

    No Known Activations