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

    Neuronpedia

    INDEX
    Explanations

    references to the concepts of "inside" and "outside."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.65
    ative
    -0.58
    ATIVE
    -0.57
    RUnlock
    -0.54
     Falun
    -0.53
    Datuak
    -0.52
    meneu
    -0.52
    APON
    -0.52
     Serap
    -0.51
    nological
    -0.51
    POSITIVE LOGITS
    outside
    0.89
    OUTSIDE
    0.88
     Outside
    0.88
    Outside
    0.86
     OUTSIDE
    0.83
    inside
    0.77
    Inside
    0.71
    INSIDE
    0.71
     outside
    0.70
     Inside
    0.69
    Act Density 0.057%

    No Known Activations