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

    Neuronpedia

    INDEX
    Explanations

    references to data formatting and conversion in programming contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     B
    -0.56
     S
    -0.53
     (
    -0.53
     custom
    -0.53
     to
    -0.49
     or
    -0.49
     &
    -0.49
     can
    -0.49
     Can
    -0.48
    ...
    -0.48
    POSITIVE LOGITS
     betweenstory
    1.00
     تضيفلها
    0.98
    StructEnd
    0.98
     disambiguazione
    0.94
     Theſe
    0.91
    abestanden
    0.89
     ſeveral
    0.88
     Roskov
    0.87
    AnchorStyles
    0.86
     themſelves
    0.86
    Act Density 0.188%

    No Known Activations