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

    Neuronpedia

    INDEX
    Explanations

    situations involving competition and performance in racing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Changes in position during a race

    np_acts-logits-general · gemini-2.0-flash

    racing position changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.65
     Mérimée
    -0.53
    shadowRadius
    -0.52
     Hinge
    -0.52
    enumi
    -0.51
    minecraftforge
    -0.50
     Nagoya
    -0.49
     orth
    -0.49
     незавершена
    -0.48
     veto
    -0.47
    POSITIVE LOGITS
     overtaking
    0.72
     traffic
    0.63
     overtake
    0.62
     <<<<<<<<<<<<<<
    0.57
    traffic
    0.57
     slowest
    0.57
    IsContent
    0.56
    cipar
    0.56
     Positions
    0.55
     overtook
    0.54
    Act Density 0.130%

    No Known Activations