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

    Neuronpedia

    INDEX
    Explanations

    the phrase "has" indicating possession or completion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to people's actions or accomplishments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Interested
    -0.80
    OOL
    -0.73
    seless
    -0.71
    typ
    -0.65
    winner
    -0.64
     Apart
    -0.63
    eem
    -0.62
    —-
    -0.61
     selves
    -0.60
     Recap
    -0.59
    POSITIVE LOGITS
     been
    1.46
    been
    1.22
     undergone
    1.16
     risen
    1.11
     gotten
    1.09
     vowed
    1.08
     become
    1.07
     amassed
    1.06
     gone
    1.05
     spoken
    1.03
    Act Density 0.216%

    No Known Activations