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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote an exception or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating separation or distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crawl
    -0.68
     Huck
    -0.65
     tiss
    -0.63
     tumble
    -0.62
    $$
    -0.60
    IZE
    -0.60
    cat
    -0.59
     descent
    -0.58
    iking
    -0.58
    00000000
    -0.57
    POSITIVE LOGITS
    heid
    1.43
    ments
    1.27
    comings
    1.06
    Ħ¢
    0.90
    osite
    0.87
    isphere
    0.86
     Apart
    0.80
    inguished
    0.77
    MENT
    0.75
    Side
    0.75
    Act Density 0.006%

    No Known Activations