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

    Neuronpedia

    INDEX
    Explanations

    discussions about authority figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.62
    loroethane
    -0.52
     مواليد
    -0.51
    +#+#
    -0.51
    SequentialGroup
    -0.50
    AddTagHelper
    -0.47
     aires
    -0.46
    hower
    -0.45
     ग्राहक
    -0.45
     ويكيميديا
    -0.45
    POSITIVE LOGITS
     hoped
    0.85
     hoping
    0.73
     feared
    0.72
     believe
    0.71
     everywhere
    0.71
     flocked
    0.70
     hopes
    0.70
     rejoiced
    0.68
     hope
    0.66
     speculate
    0.65
    Act Density 0.266%

    No Known Activations