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

    Neuronpedia

    INDEX
    Explanations

    references to various types or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.73
    ientras
    -0.66
     titolata
    -0.65
     térmica
    -0.62
     Komunikasi
    -0.60
     bordada
    -0.60
     plástica
    -0.60
    windowFixed
    -0.59
     Infór
    -0.58
    Hochspringen
    -0.58
    POSITIVE LOGITS
     types
    1.09
     type
    1.00
     kinds
    0.90
     Types
    0.77
    Types
    0.74
     TYPES
    0.74
     tipe
    0.74
    types
    0.74
     tipo
    0.71
     TYPE
    0.71
    Act Density 0.530%

    No Known Activations