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

    Neuronpedia

    INDEX
    Explanations

    repeated references to "the" in various contexts

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

    "The" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    'the' followed by descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.52
     stuff
    -0.47
    dafx
    -0.47
     بيها
    -0.46
    others
    -0.46
     things
    -0.44
     AssemblyCulture
    -0.44
    PYX
    -0.43
    Personensuche
    -0.43
    Datuak
    -0.43
    POSITIVE LOGITS
     progressive
    0.45
    anglès
    0.44
     cortas
    0.43
     ظل
    0.43
     envisaged
    0.43
    assertNotNull
    0.43
     chaînes
    0.43
     gesloten
    0.42
     permitted
    0.42
     concerned
    0.41
    Act Density 1.360%

    No Known Activations