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

    Neuronpedia

    INDEX
    Explanations

    different references to "other" entities or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lainnya
    -0.83
     الأخرى
    -0.74
    AddTagHelper
    -0.73
     berikutnya
    -0.70
     autre
    -0.69
     restantes
    -0.66
     mourut
    -0.66
    others
    -0.65
     JSTOR
    -0.65
     andern
    -0.64
    POSITIVE LOGITS
    worldly
    1.45
     than
    1.16
    than
    0.85
    था
    0.82
    Than
    0.81
    world
    0.78
     niż
    0.77
     THAN
    0.76
    ness
    0.74
     kinds
    0.73
    Act Density 0.140%

    No Known Activations