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

    Neuronpedia

    INDEX
    Explanations

    historical and mythological references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     broder
    -0.83
     pét
    -0.80
     dè
    -0.77
     marte
    -0.76
     lapto
    -0.75
     torba
    -0.75
     balon
    -0.74
     patin
    -0.74
     cori
    -0.74
     traktor
    -0.74
    POSITIVE LOGITS
     McLaugh
    1.01
     McInt
    0.96
     despotism
    0.93
     Rodrig
    0.83
     Vaugh
    0.81
     prerog
    0.76
     Bartholo
    0.76
     belliger
    0.73
     Daven
    0.73
     unlaw
    0.72
    Act Density 0.321%

    No Known Activations