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

    Neuronpedia

    INDEX
    Explanations

    the word "because" and related expressions of causation or reasoning

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

    introducing reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.62
    -0.62
    enumi
    -0.57
     AssemblyTitle
    -0.54
    VYMaps
    -0.52
     initComponents
    -0.51
    matchCondition
    -0.50
    InputBorder
    -0.50
    ôtel
    -0.50
     AssemblyProduct
    -0.49
    POSITIVE LOGITS
     because
    1.04
    because
    0.94
    Because
    0.81
     Because
    0.80
     porque
    0.80
     BECAUSE
    0.75
     perché
    0.74
    ECAUSE
    0.73
     fordi
    0.70
     karena
    0.70
    Act Density 0.098%

    No Known Activations