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

    Neuronpedia

    INDEX
    Explanations

    physical attributes and characteristics of objects or individuals, such as their appearance or composition

    oai_token-act-pair · gpt-3.5-turbo

    specific characteristics or attributes of people, objects, or entities described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.77
    orders
    -0.74
    Trust
    -0.74
    Govern
    -0.73
    éļ
    -0.70
    åĽ
    -0.70
    Values
    -0.70
    Politics
    -0.67
    gemony
    -0.66
     VIDEOS
    -0.65
    POSITIVE LOGITS
     affair
    0.86
     fashioned
    0.82
     consisting
    0.82
     sized
    0.81
     stub
    0.80
     rather
    0.80
     unto
    0.78
     shaped
    0.78
     comprised
    0.76
     disguised
    0.75
    Act Density 0.473%

    No Known Activations