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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "nonsense"

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

    nonsense mutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.49
     Deleg
    -0.45
    ftrag
    -0.44
     deleg
    -0.41
    |/
    -0.41
    <tr>
    -0.39
     Kiri
    -0.39
     CreateTagHelper
    -0.38
    Kiri
    -0.38
    *}[
    -0.38
    POSITIVE LOGITS
     nonsense
    1.91
    nonsense
    1.70
    onsense
    1.50
    Nonsense
    1.46
    ensical
    0.86
    废话
    0.82
     bullshit
    0.81
     foolishness
    0.79
     absurdo
    0.79
     rubbish
    0.77
    Act Density 0.004%

    No Known Activations