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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'dirty' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mxArray
    -0.48
     mandat
    -0.48
     parameter
    -0.45
     tramontina
    -0.44
     achat
    -0.42
     málaga
    -0.42
    thansa
    -0.42
    CardHeader
    -0.41
     Multiplex
    -0.40
    JoinTable
    -0.40
    POSITIVE LOGITS
     dirt
    0.90
     dirty
    0.88
     dir
    0.87
    dirty
    0.83
    Dirty
    0.83
     Dirty
    0.80
    dirt
    0.75
    Dirt
    0.72
     Dirt
    0.71
     DIR
    0.69
    Act Density 0.249%

    No Known Activations