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

    Neuronpedia

    INDEX
    Explanations

    terms related to reducing or minimizing aspects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]!='
    -0.65
     Wikispecies
    -0.63
    Olaf
    -0.63
    Portale
    -0.61
    OrderStatus
    -0.61
    usty
    -0.60
    uxxxx
    -0.60
    ècie
    -0.59
    ninth
    -0.59
    psia
    -0.58
    POSITIVE LOGITS
     reduc
    1.29
     Reduced
    1.24
     Reduce
    1.22
     reduced
    1.21
     reduction
    1.19
     reduce
    1.18
     REDUC
    1.17
    Reduce
    1.17
    reduce
    1.16
     reducers
    1.14
    Act Density 0.117%

    No Known Activations