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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and hierarchical roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.48
     CanadaChoose
    -0.42
    новништво
    -0.38
    KommentareTeilen
    -0.38
    ANTLR
    -0.37
    Pec
    -0.37
     الحره
    -0.36
    dings
    -0.36
    WithIOException
    -0.35
    FACTS
    -0.35
    POSITIVE LOGITS
    :✨
    0.50
     snippetHide
    0.50
    级别的
    0.50
     autorytatywna
    0.48
     level
    0.48
    级
    0.48
     feroit
    0.48
     defaultstate
    0.47
     pouvoit
    0.47
    ſelves
    0.45
    Act Density 1.256%

    No Known Activations