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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a person or entity taking a specific action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "has" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eem
    -0.74
    Newsletter
    -0.70
    raw
    -0.66
     behold
    -0.65
    seless
    -0.62
    etting
    -0.61
    ItemThumbnailImage
    -0.61
    ecd
    -0.61
    catentry
    -0.61
    jam
    -0.60
    POSITIVE LOGITS
     been
    1.37
    been
    1.16
     undergone
    1.14
     become
    1.11
     apologised
    1.08
     begun
    1.06
     emerged
    1.06
     teamed
    0.96
     gotten
    0.95
     reportedly
    0.94
    Act Density 0.235%

    No Known Activations