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

    Neuronpedia

    INDEX
    Explanations

    expressions or phrases indicating emphasis or incredulity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I mean."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iets
    -0.78
    rimp
    -0.67
    è¦ļéĨĴ
    -0.64
    itter
    -0.63
    omal
    -0.62
    oder
    -0.61
    omsky
    -0.61
    "},"
    -0.60
    shaw
    -0.59
    Desktop
    -0.59
    POSITIVE LOGITS
    terday
    0.77
     LOOK
    0.73
    htaking
    0.73
     WHAT
    0.72
     frankly
    0.70
     yeah
    0.70
     REALLY
    0.70
     obviously
    0.67
     seriously
    0.67
     honestly
    0.66
    Act Density 0.025%

    No Known Activations