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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     earnestness
    -0.53
     frivol
    -0.47
    corpion
    -0.44
     nobly
    -0.44
    undial
    -0.42
     walang
    -0.41
     ingrat
    -0.40
     impet
    -0.40
     Bekasi
    -0.40
    couts
    -0.40
    POSITIVE LOGITS
     Sy
    1.13
    Sy
    1.11
     SYN
    1.07
     syn
    1.06
     sy
    1.03
     Syn
    1.03
    Syn
    1.02
     SY
    0.96
    sy
    0.96
    SYN
    0.93
    Act Density 0.111%

    No Known Activations