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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflict and controversy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     alkoh
    -1.02
     kram
    -0.97
     praktik
    -0.97
     meis
    -0.96
     makro
    -0.92
     kosme
    -0.91
     franz
    -0.91
     antik
    -0.90
     pira
    -0.90
     solidar
    -0.90
    POSITIVE LOGITS
     sondern
    1.02
     nor
    1.01
     but
    0.81
    but
    0.74
     بلکه
    0.74
    而是
    0.72
    nor
    0.69
    <bos>
    0.68
     nhưng
    0.65
     sino
    0.60
    Act Density 0.226%

    No Known Activations