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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    end-of-sentence punctuation, indicating conclusions or separations between statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scenery
    -0.77
    ebook
    -0.68
     anthology
    -0.68
    itably
    -0.68
     sleeve
    -0.67
     expl
    -0.66
     everywhere
    -0.66
     ourselves
    -0.65
    ishly
    -0.65
    bred
    -0.63
    POSITIVE LOGITS
     Critics
    1.35
     However
    1.15
     Earlier
    1.15
     Previously
    1.13
     Though
    1.10
     Additionally
    1.09
     Although
    1.09
     Since
    1.08
     Initially
    1.08
     Despite
    1.04
    Act Density 0.413%

    No Known Activations