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

    Neuronpedia

    INDEX
    Explanations

    mentions of past events, timelines, and historical references

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Ô
    -1.03
     Mehran
    -1.01
    ocene
    -0.96
    skirts
    -0.90
    NetMessage
    -0.88
    heses
    -0.86
     reperto
    -0.86
     partName
    -0.85
     CTR
    -0.85
    mberg
    -0.82
    POSITIVE LOGITS
     course
    2.12
    course
    1.52
    ortunately
    1.47
     Course
    1.42
     sorts
    1.22
    sted
    1.22
    Ļ½
    1.17
    elia
    1.15
    onso
    1.09
     COUR
    1.05
    Act Density 1.052%

    No Known Activations