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

    Neuronpedia

    INDEX
    Explanations

    relative clauses and phrases that provide additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.64
     détail
    -0.61
    Θ
    -0.59
     vägen
    -0.57
     publiek
    -0.57
     muſt
    -0.57
    hyrchwyd
    -0.57
     becauſe
    -0.57
    DoubleQuotes
    -0.57
     dépôt
    -0.56
    POSITIVE LOGITS
     wherein
    0.90
     whereby
    0.87
    wherein
    0.84
     waarbij
    0.83
     where
    0.73
     involving
    0.67
     INVOL
    0.65
     hvor
    0.65
     kdy
    0.65
     जहां
    0.61
    Act Density 0.356%

    No Known Activations