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

    Neuronpedia

    INDEX
    Explanations

    sections of text that contain structured information such as biographies and histories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.96
    fromnode
    -0.94
    Diweddarwch
    -0.90
    uxxxx
    -0.88
     betweenstory
    -0.86
    GraphicsUnit
    -0.84
    BufferException
    -0.84
     snippetHide
    -0.82
    windowFixed
    -0.82
     AssemblyTitle
    -0.81
    POSITIVE LOGITS
    CTIONS
    0.46
    kti
    0.44
    ennai
    0.44
    openapi
    0.42
    год
    0.41
    %)$
    0.41
     I
    0.41
    ganta
    0.40
     overzicht
    0.40
     History
    0.39
    Act Density 0.013%

    No Known Activations