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

    Neuronpedia

    INDEX
    Explanations

    keywords related to specific lists or categories

    oai_token-act-pair · gpt-3.5-turbo

    colons followed by lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orie
    -0.69
    ewitness
    -0.63
    yan
    -0.63
    oland
    -0.62
    mire
    -0.62
    izons
    -0.61
    leased
    -0.61
    aukee
    -0.60
    aney
    -0.59
     neighb
    -0.59
    POSITIVE LOGITS
     âĹı
    1.01
     Firstly
    0.98
     namely
    0.90
    âĹı
    0.88
     "âĢ¦
    0.77
     Provided
    0.75
    ↵Âł
    0.73
    ³³³³³³³³³³³³³³³³
    0.71
    $$$$
    0.71
    *:
    0.70
    Act Density 0.082%

    No Known Activations