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

    Neuronpedia

    INDEX
    Explanations

    references to existing entities, concepts, or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.76
     Савезне
    -0.76
    MLLoader
    -0.72
     كومونز
    -0.71
    Parcelize
    -0.71
     الحره
    -0.70
    ⓧ
    -0.70
    tagHelperRunner
    -0.70
    rungsseite
    -0.68
    الإنجليزية
    -0.67
    POSITIVE LOGITS
     existing
    1.57
    existing
    1.40
    Existing
    1.38
     Existing
    1.37
     EXISTING
    1.19
     bestaande
    1.18
     existente
    1.07
    既存
    1.03
     existentes
    1.01
     bestehende
    1.00
    Act Density 0.251%

    No Known Activations