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

    Neuronpedia

    INDEX
    Explanations

    phrases related to vehicle specifications and driving experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Daw
    -0.19
     Dame
    -0.18
    dag
    -0.16
     Dahl
    -0.16
     Dag
    -0.16
     Dice
    -0.16
    orsk
    -0.15
     Dorm
    -0.15
    dots
    -0.15
     Daisy
    -0.15
    POSITIVE LOGITS
     drive
    0.85
     driving
    0.82
     drives
    0.79
    -drive
    0.75
    drive
    0.74
     Drive
    0.73
    -driving
    0.71
     Driving
    0.68
     driver
    0.68
     drove
    0.68
    Act Density 0.220%

    No Known Activations