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

    Neuronpedia

    INDEX
    Explanations

    references to spatial or contextual relationships across different entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.69
     отношению
    -0.66
     Moines
    -0.66
    tanooga
    -0.65
     étrangères
    -0.65
     ISU
    -0.63
    тература
    -0.61
    ResponseEntity
    -0.61
    <()>
    -0.60
    Hansen
    -0.60
    POSITIVE LOGITS
     ACROSS
    1.60
     Across
    1.54
    Across
    1.50
    across
    1.48
     across
    1.47
    crossing
    0.94
    ROSS
    0.94
    Crossing
    0.93
     Crossing
    0.92
     crosses
    0.91
    Act Density 0.038%

    No Known Activations