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

    Neuronpedia

    INDEX
    Explanations

    instances of statements indicating emotional responses or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thus
    -0.19
    thus
    -0.18
    ucch
    -0.16
     thereby
    -0.16
    dess
    -0.15
    Thus
    -0.15
    оÑĩка
    -0.14
    imeo
    -0.14
    noch
    -0.14
    ãģ¡
    -0.14
    POSITIVE LOGITS
    æ¯ķ
    0.25
     Firstly
    0.21
     especially
    0.21
     ведÑĮ
    0.20
    especially
    0.20
     Especially
    0.18
     aside
    0.18
     firstly
    0.18
    é¦ĸ
    0.17
    pecially
    0.17
    Act Density 0.428%

    No Known Activations