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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    intense emotional experiences and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zens
    -0.63
    pport
    -0.62
    ãĥķãĤ¡
    -0.61
    erenn
    -0.56
     Prepare
    -0.55
    ãĤ
    -0.54
     Profession
    -0.53
    Pacific
    -0.53
    GAN
    -0.53
     recent
    -0.52
    POSITIVE LOGITS
     consisted
    1.59
     lasted
    1.52
     remained
    1.42
     seemed
    1.41
     depended
    1.37
     tended
    1.35
     differed
    1.35
     didnt
    1.29
     resembled
    1.29
     lacked
    1.26
    Act Density 0.600%

    No Known Activations