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

    Neuronpedia

    INDEX
    Explanations

    superscript notations in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EEA
    -0.91
     Eggers
    -0.87
    writeObject
    -0.84
    borderSide
    -0.84
     Gerber
    -0.79
    Pierre
    -0.77
     Pierre
    -0.74
    dresser
    -0.74
     ModelExpression
    -0.74
     Beek
    -0.73
    POSITIVE LOGITS
    sup
    1.56
    Sup
    1.40
     Sup
    1.36
     sup
    1.19
    SUP
    1.11
     SUP
    1.07
     supr
    1.03
     supre
    0.98
     supra
    0.81
     Sop
    0.73
    Act Density 0.007%

    No Known Activations