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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical properties and concepts related to correlations and results in theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.14
     Anſ
    -1.12
     Houſe
    -1.11
     Diſ
    -1.02
    ########.
    -1.00
     Monfieur
    -0.98
     ſy
    -0.97
     doubtnut
    -0.96
     raiſ
    -0.94
    hhhhhhhh
    -0.94
    POSITIVE LOGITS
     Cor
    2.09
    cor
    1.92
    Cor
    1.89
     cor
    1.81
     COR
    1.75
    COR
    1.56
     Corbett
    1.41
     Corridor
    1.40
     Kor
    1.35
     Correa
    1.34
    Act Density 0.137%

    No Known Activations