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

    Neuronpedia

    INDEX
    Explanations

    terms related to driving or movement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McNamara
    -0.82
     Orton
    -0.76
     olympique
    -0.75
     Pronto
    -0.71
     Dok
    -0.70
     Bok
    -0.69
     McManus
    -0.69
     Newberry
    -0.69
     fact
    -0.66
     hypoxia
    -0.65
    POSITIVE LOGITS
     drives
    2.19
     drive
    2.04
     Drives
    2.02
     Drive
    2.00
    drives
    1.98
    drive
    1.97
    Drive
    1.95
     DRIVE
    1.90
    DRIVE
    1.82
     drove
    1.70
    Act Density 0.080%

    No Known Activations