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

    Neuronpedia

    INDEX
    Explanations

    mentions of various countries and political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures, colors, and various social and fantasy themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.70
     acknowledgement
    -0.65
    quartered
    -0.62
     Bris
    -0.60
    eatures
    -0.60
    GoldMagikarp
    -0.59
    etheless
    -0.58
     Authorization
    -0.57
     diplomatic
    -0.56
     Verb
    -0.55
    POSITIVE LOGITS
     etc
    1.33
     respectively
    1.08
     or
    0.94
    !/
    0.83
    /$
    0.80
    etc
    0.79
     versa
    0.78
     blah
    0.78
     versus
    0.77
    *.
    0.76
    Act Density 0.402%

    No Known Activations