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

    Neuronpedia

    INDEX
    Explanations

    phrases or concepts related to names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.62
    ]-->
    -0.61
    parsedMessage
    -0.58
    ViewFeatures
    -0.57
     <=",
    -0.57
    tableFuture
    -0.56
     виправивши
    -0.54
     للمعارف
    -0.54
     незавершена
    -0.54
    ).)
    -0.54
    POSITIVE LOGITS
     name
    1.43
     names
    1.30
    名称
    1.12
     naam
    1.10
    name
    1.09
     NAME
    1.05
     named
    1.04
     nickname
    1.03
    名字
    1.02
     Name
    1.02
    Act Density 0.206%

    No Known Activations