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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong emotions or states of mind

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "em."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.73
     kittens
    -0.70
    é¾įå
    -0.68
    apest
    -0.66
    cules
    -0.65
     incon
    -0.64
    jri
    -0.64
     dearly
    -0.61
    ittens
    -0.60
     Butterfly
    -0.60
    POSITIVE LOGITS
    ciating
    1.09
    enment
    0.98
    ãĤ¨ãĥ«
    0.91
    achment
    0.87
    ĸļ
    0.78
    à¼
    0.70
    emy
    0.70
    oyer
    0.68
     Pradesh
    0.67
    ãĥĢ
    0.67
    Act Density 0.048%

    No Known Activations