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

    Neuronpedia

    INDEX
    Explanations

    steps and ingredients in a recipe

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     monaster
    -1.04
     Wikisource
    -0.84
     Milán
    -0.82
     ideolog
    -0.81
     Pediat
    -0.79
     Rektor
    -0.79
     Siria
    -0.78
     valla
    -0.77
     Occidente
    -0.74
     Sankt
    -0.73
    POSITIVE LOGITS
     increa
    1.00
     yoda
    0.99
     impra
    0.95
     affor
    0.95
     snoopy
    0.94
     pollut
    0.94
     unve
    0.91
     shenan
    0.91
     simpsons
    0.90
     jurassic
    0.89
    Act Density 0.105%

    No Known Activations