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

    Neuronpedia

    INDEX
    Explanations

    references to ineffective or harmful policies and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ena
    -0.19
    erez
    -0.15
     fen
    -0.14
    retch
    -0.14
    357
    -0.14
    anden
    -0.14
    682
    -0.13
    ambil
    -0.13
    ittest
    -0.13
     Owen
    -0.13
    POSITIVE LOGITS
    imals
    0.16
     misc
    0.15
     poil
    0.14
    raç
    0.14
     proport
    0.14
    é¼ĵ
    0.14
    ép
    0.14
    ÅĤaw
    0.13
    DDL
    0.13
    åĭŁ
    0.13
    Act Density 0.401%

    No Known Activations