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

    Neuronpedia

    INDEX
    Explanations

    the presence of angle brackets and less-than symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.72
    te
    -0.61
    1
    -0.59
    2
    -0.59
    re
    -0.59
    he
    -0.57
    <eos>
    -0.56
     -
    -0.56
     
    -0.55
    ed
    -0.55
    POSITIVE LOGITS
    enumi
    1.42
     nahilalakip
    1.18
     AssemblyCulture
    1.10
    ngdoc
    1.09
    DockStyle
    1.08
    IBOutlet
    1.08
    -------------</
    1.06
    AutoScaleMode
    1.05
     cref
    1.04
     EconPapers
    1.03
    Act Density 0.031%

    No Known Activations