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

    Neuronpedia

    INDEX
    Explanations

    words related to media news articles or journalism, especially mentioning the website 'www.leaseweb.com'

    oai_token-act-pair · gpt-3.5-turbo

    the word "new" indicating novel concepts or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.69
    REDACTED
    -0.65
     anat
    -0.62
     blush
    -0.61
     inhibition
    -0.59
    senal
    -0.59
     unarmed
    -0.59
     bribery
    -0.58
     embarrassed
    -0.58
     localization
    -0.58
    POSITIVE LOGITS
    een
    1.18
    estern
    1.15
    esome
    1.12
    riter
    1.09
    esley
    1.07
    ITNESS
    1.06
    sburg
    1.03
    alker
    1.01
    rote
    1.01
    ritten
    0.96
    Act Density 0.020%

    No Known Activations