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

    Neuronpedia

    INDEX
    Explanations

    the phrase "write your own" followed by a noun, encouraging user-generated content or personalization

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lehem
    -0.81
     Mub
    -0.75
    erest
    -0.74
    hovah
    -0.74
    EGIN
    -0.72
    usted
    -0.70
    atform
    -0.69
    Rus
    -0.69
    doi
    -0.68
    oms
    -0.68
    POSITIVE LOGITS
     personalized
    0.95
     customized
    0.93
     version
    0.90
     personal
    0.89
     unique
    0.86
     custom
    0.86
     copy
    0.84
     private
    0.83
     distinctive
    0.78
     destiny
    0.76
    Act Density 0.032%

    No Known Activations