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

    Neuronpedia

    INDEX
    Explanations

    indicators for the end of the text, most likely content separation symbols such as

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that contain line breaks or separations indicating topic shifts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     theirs
    -0.52
     circulation
    -0.51
     embargo
    -0.50
     reper
    -0.49
     amnesty
    -0.49
     displacement
    -0.48
     obligation
    -0.48
     established
    -0.47
     abandon
    -0.46
     limit
    -0.46
    POSITIVE LOGITS
    Untitled
    1.04
    Abstract
    1.00
    Description
    0.98
    WASHINGTON
    0.98
    CLOSE
    0.97
    Overview
    0.93
    CTV
    0.92
    SAN
    0.89
    Welcome
    0.88
    Still
    0.87
    Act Density 0.136%

    No Known Activations