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

    Neuronpedia

    INDEX
    Explanations

    references to locations, particularly streets and places named after saints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.91
     purpoſe
    -0.78
     perſon
    -0.77
     مشين
    -0.77
     themſelves
    -0.76
     snippetHide
    -0.75
     pleaſure
    -0.72
     myſelf
    -0.72
     houſe
    -0.70
     Majefty
    -0.70
    POSITIVE LOGITS
     Saint
    0.70
     Santa
    0.63
    ematica
    0.58
    Saint
    0.57
    ormal
    0.52
    Funded
    0.52
     Ha
    0.52
    Santa
    0.51
     Vanden
    0.51
    Datuak
    0.50
    Act Density 0.217%

    No Known Activations