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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing surprising or interesting information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the words "interestingly" and "ironically."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.73
    aily
    -0.71
    "},"
    -0.68
     throats
    -0.66
    ainment
    -0.64
     commitment
    -0.63
     newsletters
    -0.62
    aden
    -0.61
     laundry
    -0.61
    ujah
    -0.60
    POSITIVE LOGITS
    nown
    0.82
     ironically
    0.78
     Ironically
    0.75
     coinc
    0.74
     interestingly
    0.72
     ironic
    0.71
     titled
    0.70
     disposed
    0.70
    SPONSORED
    0.70
     Interestingly
    0.68
    Act Density 0.054%

    No Known Activations