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

    Neuronpedia

    INDEX
    Explanations

    phrases related to borders and border-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "borders."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thora
    -0.89
    ENA
    -0.87
    VERTISEMENT
    -0.82
    IVES
    -0.77
    umption
    -0.76
    IGHTS
    -0.73
    ynthesis
    -0.68
    awks
    -0.68
    FORMATION
    -0.67
    é¾įå
    -0.67
    POSITIVE LOGITS
     border
    1.09
     crossings
    1.05
     Border
    0.93
     crossing
    0.90
    border
    0.88
     borders
    0.88
     patrol
    0.86
     guards
    0.81
     Patrol
    0.78
     fence
    0.78
    Act Density 0.017%

    No Known Activations