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

    Neuronpedia

    INDEX
    Explanations

    numeric values and format markers in a data structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -1.11
    irot
    -0.74
    erl
    -0.74
    anair
    -0.70
    

    -0.69
    ner
    -0.69
     Feld
    -0.69
    ')))
    -0.67
     Parsons
    -0.67
     par
    -0.66
    POSITIVE LOGITS
    7
    1.86
     SEVEN
    1.24
    SEVEN
    1.18
     Seventh
    1.17
     Siete
    1.11
     seventh
    1.09
     Seven
    1.08
    Seventh
    1.06
    8
    1.06
     VII
    1.05
    Act Density 0.667%

    No Known Activations