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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causality or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.77
    diğimiz
    -0.70
    CharStream
    -0.65
     الدولى
    -0.59
    ğimiz
    -0.58
    Smooth
    -0.57
     functions
    -0.56
    Saluti
    -0.56
    ğiniz
    -0.55
    cjon
    -0.55
    POSITIVE LOGITS
    enterOuterAlt
    0.56
     XCTest
    0.50
    奈
    0.49
    IntoConstraints
    0.49
     <<<<<<<<<<<<<<
    0.46
    CodeAttribute
    0.45
     AssemblyProduct
    0.45
    millimeters
    0.45
    DockStyle
    0.44
     danni
    0.43
    Act Density 0.690%

    No Known Activations