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

    Neuronpedia

    INDEX
    Explanations

    academic references, names, and numerical identifiers in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Amon
    -1.00
    AccessorTable
    -0.98
     Réponses
    -0.94
    Paraguay
    -0.94
     Heisenberg
    -0.91
    Zeneca
    -0.90
     Wittgenstein
    -0.89
     Thebes
    -0.88
     UPM
    -0.88
     Indoch
    -0.88
    POSITIVE LOGITS
    ing
    0.76
     Yan
    0.72
     Brodie
    0.70
     Deer
    0.70
     McRae
    0.70
     Hama
    0.68
    peč
    0.67
    Nes
    0.67
    ING
    0.67
     Schulze
    0.65
    Act Density 1.919%

    No Known Activations