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

    Neuronpedia

    INDEX
    Explanations

    political terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     prouve
    -0.61
     reconnaît
    -0.59
     nomme
    -0.55
     mène
    -0.54
     paraît
    -0.54
     désigne
    -0.53
     occupe
    -0.53
     étu
    -0.52
     reçoit
    -0.52
     soutient
    -0.52
    POSITIVE LOGITS
     embodi
    0.67
     veiks
    0.65
     provato
    0.64
     sentito
    0.60
     thut
    0.59
     facciamo
    0.58
     fays
    0.58
     tew
    0.56
     espri
    0.56
     yaa
    0.55
    Act Density 0.140%

    No Known Activations