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

    Neuronpedia

    INDEX
    Explanations

    references to traffic-related concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     olympique
    -0.77
     Clone
    -0.74
    uploader
    -0.72
     plát
    -0.71
     Blazer
    -0.71
     Maher
    -0.70
     Solver
    -0.70
    nder
    -0.67
     COLE
    -0.67
    Pha
    -0.67
    POSITIVE LOGITS
     traffic
    1.67
     TRAFFIC
    1.57
     Traffic
    1.56
    Traffic
    1.53
    traffic
    1.45
    FFIC
    1.31
     traff
    1.11
     trafic
    1.07
     trafficking
    0.94
     tráfico
    0.89
    Act Density 0.063%

    No Known Activations