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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving summations and indices in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reduction
    -0.81
     Reduction
    -0.74
    减
    -0.73
     减
    -0.73
     reductions
    -0.72
    Minus
    -0.72
    reduction
    -0.70
    Subtract
    -0.68
     minus
    -0.67
     Redu
    -0.67
    POSITIVE LOGITS
    ++
    0.80
     ++
    0.76
    posedge
    0.75
    +
    0.74
    ++;
    0.73
    ++
    0.71
    клопе
    0.69
    [++
    0.69
    ++;
    0.68
    ++.
    0.67
    Act Density 0.350%

    No Known Activations