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

    Neuronpedia

    INDEX
    Explanations

    action verbs in the present or past tense, such as "is", "are", "was", "has", and "have"

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.90
    stood
    -0.83
    accompan
    -0.77
    edIn
    -0.70
    ilaterally
    -0.65
     Azerb
    -0.60
     equivalents
    -0.59
     Chero
    -0.59
    eteria
    -0.58
     Kurd
    -0.57
    POSITIVE LOGITS
     Psy
    0.67
     SHARES
    0.62
     Helpful
    0.60
     UPDATE
    0.60
    CRIPTION
    0.59
     understatement
    0.58
    PRESS
    0.58
    buquerque
    0.58
    actionDate
    0.57
     Update
    0.56
    Act Density 0.109%

    No Known Activations