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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to programming and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confirma
    -0.51
    Ỡ
    -0.49
     transforma
    -0.47
    reducible
    -0.47
     prompts
    -0.46
    .
    -0.46
     Chosen
    -0.42
     results
    -0.42
    WireFormatLite
    -0.42
     Teil
    -0.41
    POSITIVE LOGITS
    principalColumn
    0.89
    AddTagHelper
    0.83
    تقاوى
    0.80
    conditionally
    0.75
    ніципалі
    0.74
     CreateTagHelper
    0.70
     Himo
    0.70
    dafx
    0.69
     ویکی‌پدیا
    0.69
     мәкал
    0.68
    Act Density 0.463%

    No Known Activations