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

    Neuronpedia

    INDEX
    Explanations

    elements related to design quality and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESCO
    -0.16
    urtle
    -0.16
    oleÄį
    -0.15
    -sdk
    -0.15
    ยม
    -0.15
    bots
    -0.15
    æŁı
    -0.15
    éĩįè¦ģ
    -0.14
    chied
    -0.14
    ogui
    -0.14
    POSITIVE LOGITS
     THEN
    0.37
     then
    0.36
    then
    0.33
     Then
    0.30
    THEN
    0.28
    Then
    0.27
    _then
    0.27
     entonces
    0.26
     ÑĤогда
    0.25
     então
    0.24
    Act Density 0.209%

    No Known Activations