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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adjectives that indicate a judgment of propriety or correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hin
    -0.16
    raries
    -0.16
    iddi
    -0.15
    iphy
    -0.15
     rem
    -0.15
    adel
    -0.15
    hdl
    -0.14
     experiment
    -0.14
    235
    -0.14
     riches
    -0.14
    POSITIVE LOGITS
    fully
    0.17
    asename
    0.15
    icks
    0.15
    zı
    0.15
    efined
    0.14
    å¥Ķ
    0.14
    heimer
    0.14
    -find
    0.14
    figcaption
    0.14
     existing
    0.14
    Act Density 0.012%

    No Known Activations