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

    Neuronpedia

    INDEX
    Explanations

    code-related structures or sections

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.72
     myſelf
    -0.71
     EconPapers
    -0.66
    setVerticalGroup
    -0.65
    tadır
    -0.65
     Theſe
    -0.63
     Conſ
    -0.59
     purpoſe
    -0.58
    TargetException
    -0.57
     Inſ
    -0.57
    POSITIVE LOGITS
     protoimpl
    0.58
    TagMode
    0.56
    %");
    0.52
    poon
    0.51
    orant
    0.51
    흘
    0.50
    kloped
    0.50
    <eos>
    0.50
    jupiter
    0.49
    gdala
    0.49
    Act Density 0.022%

    No Known Activations