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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "even."

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

    "even" followed by a comparative

    np_acts-logits-general · gemini-2.0-flash

    even though / even if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BPS
    -0.75
    JsonPropertyName
    -0.75
    Koordin
    -0.73
     Maje
    -0.69
    Locke
    -0.68
     Rosalie
    -0.68
    MSD
    -0.67
     PublicKey
    -0.67
     Roi
    -0.66
     Rigidbody
    -0.66
    POSITIVE LOGITS
     EVEN
    0.96
     even
    0.95
     though
    0.91
     Even
    0.91
    even
    0.86
    Even
    0.83
    EVEN
    0.78
    though
    0.73
    emang
    0.72
    Mesmo
    0.70
    Act Density 0.074%

    No Known Activations