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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and syntactical structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -1.00
     AssemblyCompany
    -0.94
    Hentet
    -0.94
     ModelExpression
    -0.93
     ***!
    -0.91
    richTextPanel
    -0.86
    SourceChecksum
    -0.85
     Chwiliwch
    -0.84
    MessageOf
    -0.82
    دانشنامهٔ
    -0.81
    POSITIVE LOGITS
    ↵
    0.63
    ).
    0.61
    .
    0.58
    ↵↵
    0.55
    oredCriteria
    0.53
    .…
    0.53
    [toxicity=0]
    0.52
     yore
    0.52
     thereon
    0.49
     thereof
    0.49
    Act Density 33.209%

    No Known Activations