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

    Neuronpedia

    INDEX
    Explanations

    economic and political terms

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or negativity towards situations or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lastly
    -0.67
    Attach
    -0.67
     thereafter
    -0.65
     withdrew
    -0.61
     respectively
    -0.60
    anwhile
    -0.60
    uez
    -0.60
     mosqu
    -0.59
     Finally
    -0.58
     Option
    -0.58
    POSITIVE LOGITS
     âĢº
    0.78
    Especially
    0.77
    esides
    0.76
    pecially
    0.67
     à¨
    0.65
    especially
    0.62
     cynicism
    0.62
    ËĪ
    0.61
     rightfully
    0.61
     cringe
    0.60
    Act Density 1.108%

    No Known Activations