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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "stay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ici
    -0.69
     ello
    -0.68
     Dickerson
    -0.68
    icos
    -0.66
     zod
    -0.63
     Rasmussen
    -0.62
    ज्ञ
    -0.62
    czną
    -0.60
     Nilsson
    -0.59
     neod
    -0.59
    POSITIVE LOGITS
    stay
    2.07
     stay
    2.02
    STAY
    1.95
     Stay
    1.92
    Stay
    1.88
     STAY
    1.83
     stays
    1.78
     Staying
    1.75
     staying
    1.72
     stayed
    1.70
    Act Density 0.126%

    No Known Activations