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

    Neuronpedia

    INDEX
    Explanations

    elements related to procedural instructions and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Non-English words or code

    np_acts-logits-general · gemini-2.0-flash

    foreign words indicating possession or origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.74
     myſelf
    -1.68
     houſe
    -1.66
     Efq
    -1.66
     itſelf
    -1.65
     Jefus
    -1.62
     Houſe
    -1.59
     themſelves
    -1.59
     pleaſure
    -1.56
     Majefty
    -1.52
    POSITIVE LOGITS
     of
    1.20
     của
    1.09
    ของ
    0.80
     del
    0.77
     
    0.69
     eines
    0.69
     seines
    0.69
     della
    0.68
     einer
    0.67
     des
    0.63
    Act Density 0.016%

    No Known Activations