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

    Neuronpedia

    INDEX
    Explanations

    instances of bracket-like symbols or delimiters used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -1.16
    ^(@)
    -1.15
     ModelExpression
    -1.08
     autorytatywna
    -1.07
    GEBURTSDATUM
    -1.04
    WithIOException
    -1.03
    SaveChangesAsync
    -0.93
    ?}",
    -0.92
    sizeCache
    -0.90
    Autoritní
    -0.88
    POSITIVE LOGITS
    [
    2.17
     [
    1.84
    ([
    1.08
    -[
    1.07
    [\
    1.03
    {[
    1.00
    [$
    0.97
     }^{[
    0.93
    .[
    0.93
    [_
    0.92
    Act Density 0.452%

    No Known Activations