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

    Neuronpedia

    INDEX
    Explanations

    information related to team structures and projects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    fect
    -1.11
    Sov
    -1.05
    ividual
    -1.05
    Reloaded
    -1.01
     Marketable
    -1.00
    tml
    -0.99
    ously
    -0.91
    sbm
    -0.89
    pmwiki
    -0.89
     plur
    -0.88
    POSITIVE LOGITS
    members
    1.48
     mates
    1.46
    peak
    1.34
    mates
    1.28
     members
    1.27
    rons
    1.26
    member
    1.26
    sters
    1.22
     member
    1.14
    liquid
    1.09
    Act Density 0.552%

    No Known Activations