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

    Neuronpedia

    INDEX
    Explanations

    emotions and expressions of positivity or negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.61
    +#+#
    -0.55
    richTextPanel
    -0.55
    IntoConstraints
    -0.52
     سكانية
    -0.52
    stateProvider
    -0.52
    ynchronously
    -0.51
    cadilly
    -0.49
     שוליים
    -0.49
    ivably
    -0.49
    POSITIVE LOGITS
     manifested
    0.77
     manifests
    0.68
     contagious
    0.65
     manifest
    0.61
     instilled
    0.60
     manifesting
    0.59
     manifesta
    0.59
     fueled
    0.58
     displayed
    0.56
     exhibited
    0.56
    Act Density 0.520%

    No Known Activations