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

    Neuronpedia

    INDEX
    Explanations

    mentions of geographical borders

    oai_token-act-pair · gpt-3.5-turbo

    references to borders or border-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thora
    -0.82
    frey
    -0.80
    oeuv
    -0.73
    olute
    -0.73
    hots
    -0.71
    ointed
    -0.70
    idespread
    -0.69
    andum
    -0.68
    encer
    -0.68
    ived
    -0.68
    POSITIVE LOGITS
     crossings
    1.17
     fence
    0.94
     crossing
    0.94
     Patrol
    0.93
    lines
    0.92
     patrol
    0.91
     border
    0.85
    lands
    0.80
     Crossing
    0.80
     Border
    0.79
    Act Density 0.026%

    No Known Activations