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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations, particularly those involving multiplication and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.53
    </thead>
    -0.40
     disturbed
    -0.39
    setDo
    -0.36
     disrupted
    -0.33
     DialogInterface
    -0.31
     Halo
    -0.30
     cref
    -0.30
     чел
    -0.29
     seashore
    -0.29
    POSITIVE LOGITS
     multiplication
    1.02
    multiplication
    0.98
    Multiplication
    0.93
     Multiplication
    0.92
     multiplying
    0.87
    multiply
    0.85
    Multiply
    0.83
     Multiply
    0.82
    multip
    0.82
     multiplied
    0.81
    Act Density 1.222%

    No Known Activations