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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a contrast or exception in a statement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "not that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auri
    -0.71
    ortment
    -0.68
    raq
    -0.67
    ãĥ©ãĥ³
    -0.66
    ione
    -0.66
    oided
    -0.64
     Consider
    -0.62
    pez
    -0.62
    oran
    -0.61
    980
    -0.60
    POSITIVE LOGITS
     anymore
    1.38
     nor
    1.11
     slightest
    1.10
     bothered
    1.04
     bothers
    1.01
     whatsoever
    0.94
     anybody
    0.91
     any
    0.88
     anyone
    0.86
     bother
    0.85
    Act Density 0.204%

    No Known Activations