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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing negative opinions or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to negative evaluations or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Benefits
    -0.80
     Flavoring
    -0.76
    iencies
    -0.74
     Rewards
    -0.72
    ventures
    -0.72
    uries
    -0.71
     Norn
    -0.71
     Locations
    -0.71
     Costs
    -0.70
     Utt
    -0.68
    POSITIVE LOGITS
     uttered
    1.36
     sarcastic
    1.22
     misinterpret
    1.19
     laced
    1.18
     echoed
    1.17
     prophetic
    1.14
     interpreted
    1.12
     tongue
    1.12
     truthful
    1.10
     heartfelt
    1.10
    Act Density 0.244%

    No Known Activations