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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence-ending markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Waray
    -0.72
     Arkivert
    -0.69
    ^(@)
    -0.69
    bibfield
    -0.60
     }}$}
    -0.57
    terday
    -0.57
    bibinfo
    -0.56
     ?</
    -0.56
    Біографія
    -0.55
     myſelf
    -0.55
    POSITIVE LOGITS
     therefore
    3.52
     Therefore
    3.04
    therefore
    2.96
    Therefore
    2.96
     hence
    2.90
     thus
    2.78
     поэтому
    2.62
     donc
    2.61
     Hence
    2.53
    Поэтому
    2.52
    Act Density 0.799%

    No Known Activations