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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and technical references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     gaily
    -1.38
     pamph
    -1.25
     Bartholo
    -1.20
     McLaugh
    -1.16
     Kün
    -1.13
     unspeak
    -1.10
     Juf
    -1.09
     McInt
    -1.09
     apprehen
    -1.07
     depic
    -1.07
    POSITIVE LOGITS
     locu
    0.57
     通販
    0.55
    原始内容存档
    0.55
     Wikiquote
    0.54
     nevo
    0.53
     MainAxisSize
    0.53
     creativos
    0.53
    躇
    0.52
     EconPapers
    0.52
     SDLK
    0.52
    Act Density 0.095%

    No Known Activations