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

    Neuronpedia

    INDEX
    Explanations

    references to 'I'

    oai_token-act-pair · gemini-2.0-flash

    the word 'stay'

    np_token-act-pair-logits · gpt-4o-mini

    stay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.83
    astéroïdes
    -0.72
    ElementException
    -0.64
    OrBuilder
    -0.63
     grecque
    -0.61
    MergeFrom
    -0.59
    }{*}{
    -0.58
    #+#
    -0.56
    InjectAttribute
    -0.56
     &___
    -0.53
    POSITIVE LOGITS
     stay
    0.78
     Stay
    0.71
    stay
    0.71
     STAY
    0.70
     staying
    0.70
     stayed
    0.67
     Staying
    0.66
    Continue
    0.65
    Stay
    0.64
     stays
    0.58
    Act Density 2.054%

    No Known Activations