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

    Neuronpedia

    INDEX
    Explanations

    contractions with apostrophes (') followed by a word

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Amigos
    -0.51
    桌面
    -0.50
     tortas
    -0.48
    pelo
    -0.48
     ung
    -0.48
     therapeutic
    -0.47
    puerta
    -0.47
     soft
    -0.47
     students
    -0.46
    事务
    -0.46
    POSITIVE LOGITS
     nece
    1.31
     purcha
    1.29
     effe
    1.28
     desir
    1.18
     waer
    1.15
     inev
    1.14
     lende
    1.13
     bett
    1.12
     thut
    1.12
     fto
    1.11
    Act Density 0.459%

    No Known Activations