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

    Neuronpedia

    INDEX
    Explanations

    the word "even."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.83
    JsonPropertyName
    -0.77
     fieldNum
    -0.77
    PhysRevLett
    -0.75
    opsida
    -0.73
    MSD
    -0.72
    BAI
    -0.72
     Wils
    -0.71
     SAK
    -0.70
     Hickman
    -0.69
    POSITIVE LOGITS
     even
    2.21
    even
    1.93
     EVEN
    1.83
     Even
    1.75
    Even
    1.70
    EVEN
    1.59
     Incluso
    1.41
     incluso
    1.35
    حتی
    1.34
     sogar
    1.32
    Act Density 0.058%

    No Known Activations