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

    Neuronpedia

    INDEX
    Explanations

    terms related to the combination or merging of different concepts or elements

    oai_token-act-pair · gpt-3.5-turbo

    references to combinations or fusions of various elements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.86
    lest
    -0.76
    deal
    -0.75
    die
    -0.75
    bye
    -0.75
    º
    -0.74
    gow
    -0.74
    iland
    -0.72
    erer
    -0.71
    by
    -0.71
    POSITIVE LOGITS
     disparate
    1.32
     sexes
    1.21
     genres
    1.16
     oppos
    1.09
     elements
    1.05
     two
    1.03
     extremes
    1.02
     genders
    1.00
     factors
    0.97
     conflicting
    0.96
    Act Density 0.138%

    No Known Activations