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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stay" and its variations, indicating a focus on permanence or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ็ต
    -0.69
     Richmond
    -0.68
     ello
    -0.68
     zod
    -0.68
     éc
    -0.66
     Dickerson
    -0.66
    Richmond
    -0.66
    icos
    -0.66
    "])){
    -0.65
    ]))
    -0.65
    POSITIVE LOGITS
    stay
    1.57
     stay
    1.54
    STAY
    1.48
     Stay
    1.42
    Stay
    1.41
     STAY
    1.38
     Staying
    1.32
     stays
    1.29
     staying
    1.25
     stayed
    1.24
    Act Density 0.097%

    No Known Activations