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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or crossing locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kenin
    -0.17
    kest
    -0.17
    ernals
    -0.15
    BackStack
    -0.15
    737
    -0.15
    lez
    -0.14
    emie
    -0.14
    mie
    -0.14
     discre
    -0.14
    inerary
    -0.14
    POSITIVE LOGITS
     Crossing
    0.18
     bridge
    0.18
    -cross
    0.16
     Bridge
    0.15
    -reference
    0.15
     crossed
    0.15
     bridges
    0.15
    agara
    0.15
    Cross
    0.15
     reference
    0.15
    Act Density 0.035%

    No Known Activations