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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.86
     nakalista
    -0.86
     houſe
    -0.83
     greateſt
    -0.82
     leſs
    -0.82
     pleaſure
    -0.81
     leaſt
    -0.81
     ſtate
    -0.79
     Jefus
    -0.78
    Personensuche
    -0.76
    POSITIVE LOGITS
     кӀ
    0.55
     хо
    0.52
     BoxFit
    0.51
    dafrika
    0.51
    География
    0.50
    chau
    0.50
     становника
    0.49
    errat
    0.48
    TagHelper
    0.47
     nó
    0.46
    Act Density 0.265%

    No Known Activations