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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly numbers related to quantities or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    houses
    -0.60
     Vide
    -0.59
     scenery
    -0.59
     mole
    -0.58
     bridges
    -0.58
     Hath
    -0.58
     sab
    -0.57
    onyms
    -0.57
    ween
    -0.56
     Ging
    -0.56
    POSITIVE LOGITS
    39
    1.01
    38
    0.99
    37
    0.97
    34
    0.94
    390
    0.91
    477
    0.91
    31
    0.90
    194
    0.90
    42
    0.90
    43
    0.89
    Act Density 0.131%

    No Known Activations