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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical conflicts and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OOSE
    -0.17
     eskort
    -0.16
    avanaugh
    -0.16
     Rein
    -0.14
    IFE
    -0.14
    974
    -0.14
    orent
    -0.14
    antium
    -0.14
    TextNode
    -0.14
     ÑģиÑĢ
    -0.14
    POSITIVE LOGITS
     Border
    0.22
    Border
    0.20
     border
    0.18
    adow
    0.17
    jian
    0.16
    border
    0.16
     BORDER
    0.15
    Borders
    0.15
    Boundary
    0.15
    -border
    0.14
    Act Density 0.037%

    No Known Activations