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

    Neuronpedia

    INDEX
    Explanations

    references to literal or metaphorical paths and routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Complexes
    -0.78
     Monfieur
    -0.77
     reaſon
    -0.70
     Eureka
    -0.70
     GSC
    -0.69
     DMR
    -0.69
    Lager
    -0.69
     ſmall
    -0.68
     Efq
    -0.68
     Beren
    -0.68
    POSITIVE LOGITS
     path
    3.15
     paths
    2.98
     Path
    2.82
     Paths
    2.70
    path
    2.58
    paths
    2.49
     PATH
    2.45
    Path
    2.39
    Paths
    2.21
    PATH
    2.18
    Act Density 0.065%

    No Known Activations