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

    Neuronpedia

    INDEX
    Explanations

    elements or components related to navigation structures in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     (
    -0.65
     in
    -0.62
     
    -0.60
     for
    -0.58
     s
    -0.57
     S
    -0.57
     E
    -0.57
     but
    -0.56
     due
    -0.56
     is
    -0.56
    POSITIVE LOGITS
     Theſe
    1.27
     Efq
    1.27
     myſelf
    1.18
     Monfieur
    1.13
     ainfi
    1.11
     auffi
    1.09
     ſeveral
    1.09
     feroit
    1.07
     pleaſure
    1.05
     auroit
    1.05
    Act Density 0.001%

    No Known Activations