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

    Neuronpedia

    INDEX
    Explanations

    terms related to reduction or decrease in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clable
    -0.67
    Pautan
    -0.60
     sabido
    -0.59
    itoneal
    -0.58
    arthed
    -0.57
    databinding
    -0.57
     gynnwys
    -0.56
    flink
    -0.56
     ailleurs
    -0.56
    üd
    -0.54
    POSITIVE LOGITS
     reduction
    1.36
     reduced
    1.25
     decrease
    1.23
     reduce
    1.22
     reducing
    1.20
     reductions
    1.15
     Reduction
    1.15
     Reduce
    1.13
     Reduced
    1.12
     reduces
    1.11
    Act Density 0.348%

    No Known Activations