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

    Neuronpedia

    INDEX
    Explanations

    the presence of brackets and other types of delimiters in text

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

    Text enclosed in square brackets

    np_acts-logits-general · gemini-2.0-flash

    numeric or bracketed references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )':
    -0.65
    ')))
    -0.64
    ())))
    -0.63
     ''),
    -0.62
     ")");
    -0.60
    ")));
    -0.59
    )')
    -0.59
     useHistory
    -0.59
    ())));
    -0.58
    }")
    -0.58
    POSITIVE LOGITS
     [
    1.38
    [
    1.36
    ([
    1.10
     $[
    1.06
    {[
    1.02
    [\
    1.01
    =[
    1.00
     }^{[
    0.99
     ([
    0.98
    -[
    0.97
    Act Density 0.708%

    No Known Activations