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

    Neuronpedia

    INDEX
    Explanations

    mentions of vehicles or vehicle-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     generosity
    -0.73
     Humanity
    -0.67
     Sisters
    -0.67
     beauty
    -0.66
     harmless
    -0.64
     Flask
    -0.62
     fame
    -0.61
     Hawaiian
    -0.60
     prevailing
    -0.60
     Patriot
    -0.60
    POSITIVE LOGITS
    icle
    1.25
    icular
    1.20
    icles
    1.19
    veh
    1.14
    rians
    1.01
    rolet
    0.98
    rian
    0.91
    stant
    0.84
    iqueness
    0.83
    ijah
    0.83
    Act Density 0.009%

    No Known Activations