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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical interactions between characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     apprehen
    -1.25
     gaily
    -1.21
     accla
    -1.07
     mischie
    -1.06
     intrigu
    -1.04
     maneu
    -1.03
     disagre
    -1.01
     pooh
    -1.00
     shenan
    -0.98
     fuf
    -0.96
    POSITIVE LOGITS
    Palabras
    0.54
     words
    0.52
     cât
    0.52
     aproape
    0.51
     îna
    0.50
    words
    0.50
    invokeLater
    0.49
    hoeddwyd
    0.48
     vă
    0.48
    зулта
    0.48
    Act Density 0.249%

    No Known Activations