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

    Neuronpedia

    INDEX
    Explanations

    references to borders

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical or political borders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynasty
    -0.73
    orah
    -0.71
    ibur
    -0.70
    ointed
    -0.69
     partName
    -0.67
    ctive
    -0.65
    verbs
    -0.65
    %]
    -0.64
    odor
    -0.64
    thora
    -0.64
    POSITIVE LOGITS
     borders
    0.94
     Borders
    0.89
    ansas
    0.80
    lines
    0.78
     crossings
    0.77
    afety
    0.75
    radius
    0.74
     delim
    0.73
    rants
    0.73
     border
    0.72
    Act Density 0.017%

    No Known Activations