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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values related to dosage or measurements in scientific studies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    '
    -0.53
    -
    -0.52
    <bos>
    -0.46
     team
    -0.45
    ’
    -0.40
     tool
    -0.39
    短期
    -0.39
    PRET
    -0.39
    Short
    -0.38
     inst
    -0.38
    POSITIVE LOGITS
     препратки
    1.05
     autorytatywna
    1.01
    AddTagHelper
    1.01
     ujednoznacz
    0.97
    twimg
    0.94
    UnusedPrivate
    0.92
     '\\;'
    0.90
    RenderAtEndOf
    0.90
    LabelTagHelper
    0.88
    EDEFAULT
    0.87
    Act Density 0.075%

    No Known Activations