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

    Neuronpedia

    INDEX
    Explanations

    information related to politics, government, and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bridge
    -0.69
    Applic
    -0.63
     Moves
    -0.62
    ilts
    -0.61
     rendition
    -0.59
     Adin
    -0.58
     revisions
    -0.57
     merger
    -0.57
    legal
    -0.57
    Pos
    -0.56
    POSITIVE LOGITS
     yourself
    1.35
     yourselves
    1.25
     your
    0.83
     wondering
    0.81
     Yourself
    0.79
    Tube
    0.77
     hear
    0.73
    agine
    0.73
     YOUR
    0.72
     guessed
    0.72
    Act Density 2.434%

    No Known Activations