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

    Neuronpedia

    INDEX
    Explanations

    deceptions or misleading information related to assumptions about people based on their appearance or behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jegy
    -0.54
     مرجع
    -0.51
     Lieber
    -0.50
     đạp
    -0.50
    kloped
    -0.49
     inéd
    -0.48
    quot
    -0.48
    zugs
    -0.48
     fondamentali
    -0.48
    Segoe
    -0.46
    POSITIVE LOGITS
     kasarigan
    0.90
     apparente
    0.80
     outwardly
    0.67
     Appearances
    0.66
     appearances
    0.62
    一見
    0.60
    Appearances
    0.60
     viewDidLoad
    0.59
     deceiving
    0.59
     decep
    0.59
    Act Density 0.268%

    No Known Activations