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

    Neuronpedia

    INDEX
    Explanations

    statistical terms related to proportions and fractions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.92
    AndEndTag
    -0.92
    ConstraintMaker
    -0.90
    AutoScale
    -0.90
     StatefulWidget
    -0.85
     Climatic
    -0.78
    dieu
    -0.76
    ocarditis
    -0.76
    (=)
    -0.76
    CodeAttribute
    -0.76
    POSITIVE LOGITS
     different
    0.55
     dist
    0.54
    ρίζ
    0.54
    s
    0.54
    dą
    0.52
     '
    0.52
    ...
    0.51
     turn
    0.51
    owe
    0.50
     later
    0.48
    Act Density 0.036%

    No Known Activations