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

    Neuronpedia

    INDEX
    Explanations

    concepts related to self-deception and the performance of social roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onOptions
    -0.67
    #
    -0.63
    uxxxx
    -0.60
    पया
    -0.56
    ImageContext
    -0.54
     curio
    -0.52
    StoryboardSegue
    -0.52
    VersionUID
    -0.51
     userManager
    -0.51
     ujednoznacz
    -0.51
    POSITIVE LOGITS
     pretended
    0.69
     pretends
    0.69
     pretense
    0.67
     pretending
    0.66
     facade
    0.65
     feign
    0.65
     façade
    0.64
     ivelany
    0.63
     pretence
    0.62
     pretend
    0.61
    Act Density 0.205%

    No Known Activations