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

    Neuronpedia

    INDEX
    Explanations

    patterns related to compatibility and intent in shared contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    PropertyChanging
    -0.58
    ArgumentParser
    -0.58
    zeera
    -0.53
    SequentialGroup
    -0.53
    HandlerContext
    -0.53
     ***!
    -0.52
    ViewImports
    -0.51
    }{*}{
    -0.50
     rhestr
    -0.50
     kaarangay
    -0.49
    POSITIVE LOGITS
     initComponents
    0.69
     uſ
    0.57
     ſtre
    0.57
    schild
    0.57
    rsiniz
    0.56
     blanches
    0.55
    turma
    0.54
    extAlignment
    0.54
    ::~
    0.53
    TOBER
    0.52
    Act Density 0.012%

    No Known Activations