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

    Neuronpedia

    INDEX
    Explanations

    intensifying adverbs and their qualifiers

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

    quite followed by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fo
    -0.38
     sur
    -0.36
     ins
    -0.36
    hljs
    -0.36
     Pun
    -0.35
     straff
    -0.34
     menthe
    -0.33
     conta
    -0.33
     teller
    -0.32
    Fo
    -0.32
    POSITIVE LOGITS
    Quite
    0.93
     Quite
    0.90
    quite
    0.89
     quite
    0.81
    Quiet
    0.66
    quiet
    0.66
     Quiet
    0.63
    parsedMessage
    0.61
     cał
    0.59
     autorytatywna
    0.58
    Act Density 0.017%

    No Known Activations