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

    Neuronpedia

    INDEX
    Explanations

    phrases containing punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotes and statements that highlight numeric values or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boro
    -0.77
     purse
    -0.70
     compass
    -0.68
     lifes
    -0.67
     favor
    -0.66
     treasure
    -0.64
     retreat
    -0.64
     affili
    -0.64
     pursuit
    -0.64
    utical
    -0.62
    POSITIVE LOGITS
    Instead
    1.12
    His
    1.12
    However
    1.11
    Nevertheless
    1.06
    Meanwhile
    1.04
    Asked
    1.04
    He
    1.01
    Regarding
    1.00
    Nonetheless
    0.98
    Speaking
    0.97
    Act Density 0.535%

    No Known Activations