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

    Neuronpedia

    INDEX
    Explanations

    legal terms and names mentioned in a narrative

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     photoc
    -0.74
     decomp
    -0.71
     fortun
    -0.71
     seiz
    -0.70
     interf
    -0.69
     Marketable
    -0.68
     polyg
    -0.68
     ASC
    -0.65
     mosaic
    -0.64
     telev
    -0.63
    POSITIVE LOGITS
    Ļ
    1.35
    ¬
    1.31
    ¤
    1.19
    ħ
    1.18
    ¡
    1.12
    Ħ¢
    1.11
    ĺ
    1.10
    ı
    1.10
    Ĵ
    1.08
    ĸ
    1.08
    Act Density 0.317%

    No Known Activations