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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and end sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     moreover
    -0.50
     также
    -0.49
     furthermore
    -0.49
     inoltre
    -0.48
     ferons
    -0.48
     consequently
    -0.48
     також
    -0.47
     ayrıca
    -0.46
     asimismo
    -0.46
     Paglinawan
    -0.46
    POSITIVE LOGITS
     Firstly
    0.69
    Firstly
    0.66
     firstly
    0.63
     Namely
    0.62
    まず
    0.61
    先是
    0.59
    ReusableCell
    0.57
     cherchés
    0.54
     namely
    0.54
    首先
    0.54
    Act Density 0.500%

    No Known Activations