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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax rules within programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.82
     '\\;'
    -0.70
    -0.70
    -0.69
    ArrowToggle
    -0.69
     autorytatywna
    -0.69
    <unused43>
    -0.68
     jspb
    -0.68
    <unused8>
    -0.68
    <pad>
    -0.68
    POSITIVE LOGITS
     If
    0.38
     if
    0.34
     Eğer
    0.34
    If
    0.32
    if
    0.30
     eğer
    0.30
     jestli
    0.28
     خ
    0.25
    .
    0.24
     You
    0.23
    Act Density 0.078%

    No Known Activations