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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.72
    thia
    -0.60
    rounder
    -0.57
     transcripts
    -0.56
    inis
    -0.56
    liction
    -0.55
    selling
    -0.54
    LOG
    -0.54
    ules
    -0.54
    ister
    -0.53
    POSITIVE LOGITS
     behest
    1.37
     expense
    1.23
     outset
    1.15
     discretion
    1.06
     intersections
    1.01
     helm
    1.00
     glance
    0.97
     intervals
    0.93
     junction
    0.89
     mercy
    0.87
    Act Density 1.018%

    No Known Activations