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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or explain visual content

    oai_token-act-pair · gpt-3.5-turbo

    phrases suggesting the reader's perspective or engagement in an explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emate
    -0.64
     Ducks
    -0.62
     Deng
    -0.61
    lasting
    -0.61
    rang
    -0.60
     Pistons
    -0.60
    enberg
    -0.59
    wr
    -0.59
    wcs
    -0.59
     Penguins
    -0.59
    POSITIVE LOGITS
     guessed
    0.76
    Know
    0.72
     yourselves
    0.70
     realise
    0.67
    Figure
    0.64
     paraph
    0.64
     wont
    0.64
    :{
    0.63
     Know
    0.63
     insure
    0.60
    Act Density 0.060%

    No Known Activations