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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or the nature of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    бÑĥдÑĮ
    -0.17
    ợ
    -0.15
     happiest
    -0.14
    happy
    -0.14
    igor
    -0.13
    تÙĩا
    -0.13
    å»·
    -0.13
     #'
    -0.13
     Nicol
    -0.13
    शन
    -0.13
    POSITIVE LOGITS
     very
    0.24
     really
    0.20
     quite
    0.19
    very
    0.16
     indeed
    0.16
     like
    0.15
     sehr
    0.15
    really
    0.15
    Very
    0.15
     Very
    0.14
    Act Density 0.099%

    No Known Activations