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

    Neuronpedia

    INDEX
    Explanations

    keywords related to borders or boundaries

    oai_token-act-pair · gpt-3.5-turbo

    references to borders or boundary-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ase
    -0.70
    osh
    -0.70
     <<
    -0.61
    cher
    -0.61
     repeated
    -0.61
     pr
    -0.60
    ment
    -0.60
    antom
    -0.60
    sing
    -0.59
     heavy
    -0.59
    POSITIVE LOGITS
     Borders
    4.97
     borders
    1.77
     Border
    1.29
    Border
    1.17
     Bridges
    1.14
     Walls
    1.13
     border
    1.07
    Balt
    0.99
     horizont
    0.99
     boundaries
    0.96
    Act Density 0.012%

    No Known Activations