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

    Neuronpedia

    INDEX
    Explanations

    sentences describing technical details and procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Darum
    -0.87
     Zwar
    -0.85
     Endlich
    -0.76
     Tudo
    -0.62
     Daß
    -0.61
     Muitos
    -0.61
    Kdo
    -0.59
    万美元
    -0.58
     Hoje
    -0.57
     Enquanto
    -0.56
    POSITIVE LOGITS
     lts
    0.96
     afp
    0.89
     Telex
    0.85
     fter
    0.83
     Quod
    0.83
     Juf
    0.82
     fte
    0.81
     lele
    0.81
     épis
    0.80
     scottish
    0.80
    Act Density 0.144%

    No Known Activations