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

    Neuronpedia

    INDEX
    Explanations

    words related to the word "pale" or 'le'

    oai_token-act-pair · gpt-3.5-turbo

    the word "le" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -0.91
    yrinth
    -0.87
     Seym
    -0.81
    iaries
    -0.80
    inelli
    -0.79
    ovych
    -0.78
    ĸļ
    -0.76
    ividual
    -0.76
    raint
    -0.76
    raviolet
    -0.75
    POSITIVE LOGITS
    ttes
    1.34
    agues
    1.15
    lla
    1.08
    phant
    1.07
    isure
    1.03
    conom
    0.95
    phrine
    0.94
    eping
    0.91
    ffect
    0.90
    gger
    0.89
    Act Density 0.044%

    No Known Activations