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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to remaining in a certain state or location

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "stay" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ces
    -0.75
    aeda
    -0.65
     Impl
    -0.64
    ace
    -0.62
    ubi
    -0.61
    rogen
    -0.60
    rote
    -0.60
     illustrates
    -0.59
     ISBN
    -0.58
     instances
    -0.57
    POSITIVE LOGITS
     stay
    3.52
     stays
    2.34
     Stay
    2.28
    stay
    2.14
    Stay
    1.99
     stayed
    1.98
     staying
    1.85
     remain
    1.80
     keep
    1.40
     leave
    1.28
    Act Density 0.013%

    No Known Activations