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

    Neuronpedia

    INDEX
    Explanations

    phrases related to borders, particularly those mentioning the concept of a wall

    oai_token-act-pair · gpt-3.5-turbo

    terms related to borders and border security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frey
    -0.66
     Featured
    -0.65
    OME
    -0.65
    andum
    -0.64
     Mons
    -0.63
     partName
    -0.63
     EDT
    -0.62
    akia
    -0.62
    tle
    -0.62
     il
    -0.60
    POSITIVE LOGITS
     crossings
    1.30
    lands
    1.25
     crossing
    1.11
    lines
    1.09
     fence
    1.08
     fences
    1.00
     patrol
    0.96
     Crossing
    0.91
     guards
    0.86
    less
    0.86
    Act Density 0.050%

    No Known Activations