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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.63
    IndentedString
    -0.62
     Czechos
    -0.56
    Jîn
    -0.55
    tvguidetime
    -0.54
     Karang
    -0.53
    توض
    -0.53
    Rujuakan
    -0.53
     fortn
    -0.53
     OMITBAD
    -0.52
    POSITIVE LOGITS
    chiha
    0.55
     farfetch
    0.54
     quibus
    0.54
     quidem
    0.52
     atque
    0.52
     habet
    0.52
     potest
    0.51
    ²/
    0.50
     neque
    0.50
    ISOString
    0.48
    Act Density 0.089%

    No Known Activations