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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stay" and its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    </b>
    -0.73
    pekt
    -0.71
    >";
    -0.69
    막
    -0.66
    >";
    -0.63
     Keil
    -0.62
     fortun
    -0.62
     stol
    -0.60
     cib
    -0.60
    hib
    -0.59
    POSITIVE LOGITS
    stay
    1.17
     stay
    1.11
     STAY
    1.02
    STAY
    1.02
    abestanden
    1.02
     Staying
    1.02
     Stay
    0.98
    Stay
    0.98
    PhysRevD
    0.97
    Staying
    0.93
    Act Density 0.012%

    No Known Activations