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

    Neuronpedia

    INDEX
    Explanations

    references to paired relationships or comparisons between two entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.86
     autorytatywna
    -0.70
     /\.(
    -0.58
     للاسماء
    -0.55
     للمعارف
    -0.54
     Référence
    -0.54
    üyada
    -0.54
     الحره
    -0.53
    談社
    -0.53
     GenerationType
    -0.53
    POSITIVE LOGITS
     pairs
    0.89
    Partners
    0.79
     partners
    0.78
    Pairs
    0.76
     Pairs
    0.74
     Partners
    0.69
    partners
    0.69
     Pair
    0.68
    pairs
    0.67
     pair
    0.66
    Act Density 0.105%

    No Known Activations