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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal information or details about individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.87
    wright
    -0.79
    ĸļ
    -0.78
    ulhu
    -0.76
    ometimes
    -0.75
    ynthesis
    -0.75
    anship
    -0.75
    agher
    -0.73
    EStream
    -0.72
    chwitz
    -0.72
    POSITIVE LOGITS
     alternative
    0.75
     versions
    0.74
    sounding
    0.74
     ones
    0.72
     version
    0.72
     nature
    0.70
     ways
    0.70
     feat
    0.69
    enough
    0.69
     manner
    0.69
    Act Density 0.114%

    No Known Activations