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

    Neuronpedia

    INDEX
    Explanations

    the word "Tuzla" followed by a number indicating the strength of the association

    oai_token-act-pair · gpt-3.5-turbo

    references to the location "Tuzla."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siren
    -0.88
    ADS
    -0.72
     Wooden
    -0.70
     Planetary
    -0.68
     Yards
    -0.67
    brates
    -0.66
     Predator
    -0.65
    Interstitial
    -0.64
     Danger
    -0.61
    ³³³³
    -0.61
    POSITIVE LOGITS
    uz
    1.17
    hao
    1.03
    awa
    0.93
    ombie
    0.92
    insk
    0.92
    hou
    0.91
    alez
    0.88
    atile
    0.87
    oan
    0.87
    arro
    0.87
    Act Density 0.006%

    No Known Activations