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

    Neuronpedia

    INDEX
    Explanations

    specific numeric and symbolic values, particularly in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    criptor
    -0.15
    tega
    -0.14
    ervoir
    -0.14
    ÑĢай
    -0.13
    DBus
    -0.13
     æ½
    -0.13
    Drv
    -0.13
    adora
    -0.13
    attern
    -0.13
    岸
    -0.13
    POSITIVE LOGITS
     demolition
    0.29
     Building
    0.27
     Buildings
    0.27
     AE
    0.26
     Controlled
    0.25
     demol
    0.24
     Architects
    0.23
     controlled
    0.23
     buildings
    0.23
     firefighters
    0.23
    Act Density 0.006%

    No Known Activations