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

    Neuronpedia

    INDEX
    Explanations

    terms related to data analysis and methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     włosów
    -0.52
     Dateien
    -0.51
     invokingState
    -0.50
     cars
    -0.50
    Buses
    -0.49
     boats
    -0.49
     buses
    -0.48
     Schiffe
    -0.48
    cars
    -0.47
     rockets
    -0.47
    POSITIVE LOGITS
     vessel
    0.66
     album
    0.64
     vehicle
    0.61
     vaccine
    0.61
     tournament
    0.60
     appliance
    0.59
     instrument
    0.59
     device
    0.57
     project
    0.57
     tablet
    0.57
    Act Density 2.214%

    No Known Activations