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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or capabilities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    chiha
    -0.54
    FlatAppearance
    -0.52
     Bahía
    -0.51
     opc
    -0.50
     patata
    -0.50
     urg
    -0.49
    ждую
    -0.49
     ecuador
    -0.48
    €)
    -0.48
     Viana
    -0.48
    POSITIVE LOGITS
     pintadas
    0.54
     safely
    0.53
     decoradas
    0.52
     contribué
    0.50
     calyx
    0.49
    <bos>
    0.49
     pouvaient
    0.48
     незавершена
    0.47
     konden
    0.47
     Савезне
    0.46
    Act Density 0.609%

    No Known Activations