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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Ad" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     civilian
    -0.48
    magitan
    -0.46
    iedział
    -0.42
     pylint
    -0.41
    SqlParameter
    -0.41
    WriteTagHelper
    -0.40
    ioutil
    -0.39
    Spoljašnje
    -0.39
    rokken
    -0.39
    ্ত
    -0.38
    POSITIVE LOGITS
     HOC
    0.42
     nakalista
    0.41
    options
    0.41
     absurd
    0.40
    Geplaatst
    0.40
     hoc
    0.40
    GPI
    0.40
     astra
    0.39
     Astra
    0.39
    uxxxx
    0.38
    Act Density 0.211%

    No Known Activations