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

    Neuronpedia

    INDEX
    Explanations

    variables in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     PropTypes
    -0.70
    helial
    -0.70
     trebui
    -0.69
     spade
    -0.69
     ​​
    -0.68
     Española
    -0.67
    gatsby
    -0.67
    webElement
    -0.66
    brainly
    -0.66
     Mujeres
    -0.66
    POSITIVE LOGITS
     فريبيس
    0.82
    Cec
    0.72
     w
    0.72
     Cec
    0.69
     Swanson
    0.68
     noDo
    0.67
     ویکی‌پدی
    0.66
    şekkür
    0.65
     Curran
    0.65
     Moha
    0.65
    Act Density 0.050%

    No Known Activations