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

    Neuronpedia

    INDEX
    Explanations

    references to the use of bold or similarly styled fonts in text

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     courage
    -0.67
     Courage
    -0.66
    Courage
    -0.66
     bravery
    -0.64
     intrepid
    -0.61
     intptr
    -0.59
    UnusedPrivate
    -0.59
     gall
    -0.58
    UnknownFields
    -0.57
     nakalista
    -0.57
    POSITIVE LOGITS
     bold
    1.84
     bolder
    1.16
     boldly
    0.95
     boldness
    0.88
    expandindo
    0.62
    大胆
    0.61
    ">*</
    0.60
     fevere
    0.58
    getDoctrine
    0.57
     muerta
    0.56
    Act Density 0.001%

    No Known Activations