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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating location

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "under."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eln
    -0.69
    iterranean
    -0.66
    ³³³³³³³³³³³³³³³³
    -0.66
     Begins
    -0.65
    utenberg
    -0.65
    ************
    -0.63
     mov
    -0.63
    ennial
    -0.62
    ILY
    -0.62
    ãĥ£
    -0.60
    POSITIVE LOGITS
    neath
    1.12
    pins
    0.94
    oos
    0.89
    dogs
    0.89
    whelming
    0.88
    cuts
    0.87
    pants
    0.86
    ĸļ
    0.84
    lining
    0.84
    Ļ½
    0.84
    Act Density 0.047%

    No Known Activations