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

    Neuronpedia

    INDEX
    Explanations

    discoveries, controversies, and events reported in texts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols at the end of sentences or questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lish
    -0.71
    ilee
    -0.68
     treasury
    -0.64
     Gur
    -0.64
     tenant
    -0.62
    arded
    -0.62
    ified
    -0.59
     cour
    -0.59
     eyeb
    -0.59
    yright
    -0.59
    POSITIVE LOGITS
    pmwiki
    0.86
    ï¸
    0.84
    BILITIES
    0.82
     [+
    0.81
    ĸļ
    0.80
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.78
     Unloaded
    0.78
     Parables
    0.74
    âķ
    0.74
    è¦ļéĨĴ
    0.73
    Act Density 0.065%

    No Known Activations