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

    Neuronpedia

    INDEX
    Explanations

    references to statistical significance or comparison in scientific research

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.07
    ViewFeatures
    -1.03
     ujednoznacz
    -1.03
     unknownFields
    -0.98
    elemField
    -0.98
    AndEndTag
    -0.96
     ProtoMessage
    -0.95
    setVerticalGroup
    -0.94
     typelib
    -0.93
     препратки
    -0.93
    POSITIVE LOGITS
    En
    0.44
    برة
    0.43
     En
    0.39
    ={`${
    0.39
     B
    0.38
     Procu
    0.37
     considera
    0.36
     [
    0.35
    pure
    0.35
    en
    0.35
    Act Density 0.011%

    No Known Activations