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

    Neuronpedia

    INDEX
    Explanations

    descriptions of encounters with mysterious or fantastical entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.88
    ilater
    -0.76
     Replacement
    -0.71
    Box
    -0.70
     Box
    -0.69
    ENTION
    -0.68
     attribution
    -0.66
    Problem
    -0.65
    Sources
    -0.65
     taxpayer
    -0.64
    POSITIVE LOGITS
     shimmer
    1.20
     crimson
    1.13
     throb
    1.11
     gle
    1.02
     faintly
    0.99
     translucent
    0.99
     breeze
    0.98
     sparkling
    0.97
     haze
    0.95
     illuminating
    0.95
    Act Density 0.388%

    No Known Activations