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

    Neuronpedia

    INDEX
    Explanations

    common filler phrases and punctuation used in casual conversation

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

    words and their punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.91
     snippetHide
    -0.79
    fromnode
    -0.76
     indígen
    -0.76
    ſicht
    -0.75
    ſchaft
    -0.73
    <unused8>
    -0.71
    <unused23>
    -0.71
    <unused3>
    -0.71
    [@BOS@]
    -0.71
    POSITIVE LOGITS
     word
    0.45
     words
    0.42
    .
    0.37
     humaines
    0.36
     and
    0.36
    word
    0.35
    words
    0.34
    ,
    0.33
     Words
    0.32
     function
    0.32
    Act Density 0.001%

    No Known Activations