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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight self-interest and conflicting motivations in social and economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    巾
    -0.40
     ExecuteAsync
    -0.37
    MethodManager
    -0.36
    isfile
    -0.36
    PickerController
    -0.35
    Digitized
    -0.34
    GtkWidget
    -0.34
     wart
    -0.34
    SBS
    -0.33
     yPos
    -0.33
    POSITIVE LOGITS
     interests
    0.73
     Interests
    0.69
    interests
    0.66
     kepentingan
    0.64
     Interessen
    0.64
     intérêt
    0.63
    Interests
    0.63
     benefit
    0.58
    rawDesc
    0.57
     intereses
    0.56
    Act Density 0.524%

    No Known Activations