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

    Neuronpedia

    INDEX
    Explanations

    frequently occurring function words in the text

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

    is followed by okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quæ
    -0.42
     ſur
    -0.39
     onely
    -0.38
     Inscrivez
    -0.38
     abſ
    -0.36
     purpoſe
    -0.36
    quels
    -0.35
     uſed
    -0.35
    wapV
    -0.34
     Joaqu
    -0.34
    POSITIVE LOGITS
     surla
    0.71
    цездатний
    0.69
     nonUne
    0.69
     noDo
    0.66
    uxxxx
    0.65
     typelib
    0.65
     otomatig
    0.64
    0.62
    InjectAttribute
    0.61
     Italijanski
    0.58
    Act Density 0.079%

    No Known Activations