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

    Neuronpedia

    INDEX
    Explanations

    references to "these" and "those" along with their variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    this
    -0.56
     oreilles
    -0.53
     ongles
    -0.50
     Kleidung
    -0.49
     jambes
    -0.49
    /
    -0.48
     this
    -0.47
     Juifs
    -0.47
     épaules
    -0.45
     touristes
    -0.45
    POSITIVE LOGITS
     kinds
    1.15
     sorts
    1.11
     Theſe
    1.09
     guys
    0.89
     disambiguazione
    0.87
     autorytatywna
    0.86
    NameInMap
    0.86
    principalTable
    0.86
    })*/
    0.86
    kinds
    0.86
    Act Density 0.148%

    No Known Activations