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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that connect thoughts or ideas

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

    want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.56
    parsedMessage
    -0.55
    yntaxException
    -0.55
    __':
    -0.54
    Sucesor
    -0.53
    titleMargin
    -0.52
    uxxxx
    -0.52
    sidemargin
    -0.51
    +#+#
    -0.50
    enderror
    -0.50
    POSITIVE LOGITS
     how
    0.46
     what
    0.46
     wanted
    0.43
     where
    0.42
     want
    0.41
    quilo
    0.41
    ramentas
    0.41
     känna
    0.40
     hendak
    0.39
     mitä
    0.38
    Act Density 0.038%

    No Known Activations