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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Andrew" and related political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intptr
    -0.50
    кну
    -0.47
    InjectAttribute
    -0.46
    ̈́
    -0.46
    semp
    -0.44
     CreateTagHelper
    -0.44
     Bure
    -0.44
    соб
    -0.44
    angelog
    -0.43
     Cras
    -0.43
    POSITIVE LOGITS
     desmotivaciones
    0.59
     llorando
    0.55
     pleaſure
    0.55
     AssemblyCompany
    0.54
     émotions
    0.53
     matériaux
    0.53
    цездатний
    0.52
     ddelweddau
    0.50
     puentes
    0.50
     plegable
    0.50
    Act Density 0.389%

    No Known Activations