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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and software development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pantal
    -0.53
     mondeo
    -0.52
     sape
    -0.51
    principalColumn
    -0.50
     adal
    -0.49
    UnusedPrivate
    -0.49
    twimg
    -0.48
     LoginComponent
    -0.47
     vícti
    -0.46
     trouva
    -0.46
    POSITIVE LOGITS
     why
    0.81
    why
    0.75
     WHY
    0.67
    Why
    0.67
    WHY
    0.66
     Why
    0.65
     dlaczego
    0.58
     Pourquoi
    0.57
     pourquoi
    0.56
     proč
    0.54
    Act Density 0.271%

    No Known Activations