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

    Neuronpedia

    INDEX
    Explanations

    places or proper nouns related to countries or cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the locations "Turk" and "Uzbek," indicating a focus on geographic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WARN
    -0.74
     Superintendent
    -0.65
    ground
    -0.64
     Swan
    -0.64
     Predator
    -0.64
    VERTIS
    -0.60
     Balloon
    -0.59
    ingly
    -0.59
     Colleg
    -0.59
    âĢ¢âĢ¢
    -0.59
    POSITIVE LOGITS
    istani
    1.27
    istan
    1.06
    oman
    0.92
    ovsky
    0.85
    oglu
    0.85
    atar
    0.84
    icans
    0.82
    aido
    0.80
    heimer
    0.78
    ipedia
    0.77
    Act Density 0.052%

    No Known Activations