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

    Neuronpedia

    INDEX
    Explanations

    patterns related to code syntax

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     rval
    -0.75
     unspeak
    -0.74
     Lmao
    -0.70
     gaily
    -0.70
     Whence
    -0.70
     Whoa
    -0.70
     toils
    -0.69
     despotism
    -0.68
     McLaugh
    -0.68
     Considerable
    -0.68
    POSITIVE LOGITS
     ù
    1.20
     lomb
    1.02
     Gemeinsame
    1.01
     luy
    0.98
     bont
    0.97
     dì
    0.96
     BnF
    0.95
     adal
    0.95
     magis
    0.95
     dè
    0.94
    Act Density 0.241%

    No Known Activations