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

    Neuronpedia

    INDEX
    Explanations

    numerical values along with some specific names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     znacznie
    -0.56
     głó
    -0.56
     pelic
    -0.55
     squire
    -0.54
     rascal
    -0.52
     wspania
    -0.51
     făcut
    -0.50
     dokład
    -0.49
     pelican
    -0.49
     estekak
    -0.49
    POSITIVE LOGITS
     allarg
    1.07
     apparti
    1.03
     parlar
    1.01
     cæ
    1.00
     Gemeinsame
    0.98
     potest
    0.98
     habet
    0.94
     Cfr
    0.94
     quæ
    0.94
     sappi
    0.93
    Act Density 0.146%

    No Known Activations