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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols that indicate negative emotions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kişilik
    -0.35
     Gericht
    -0.35
     öner
    -0.32
    -
    -0.29
     Arbeitgeber
    -0.29
    ส่ง
    -0.28
     a
    -0.28
     geldi
    -0.28
     Angebote
    -0.28
     Dienste
    -0.28
    POSITIVE LOGITS
     للمعارف
    1.08
    ftagPool
    0.89
    tagHelperRunner
    0.89
     queſta
    0.87
     ujednoznacz
    0.87
     otomatig
    0.81
    GEBURTSDATUM
    0.81
    OGND
    0.81
    rungsseite
    0.80
    RegistryLite
    0.79
    Act Density 0.882%

    No Known Activations