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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments and expressions of enjoyment related to products and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jom
    -0.18
    Çİ
    -0.17
    лем
    -0.16
    agement
    -0.14
    weis
    -0.14
     Proud
    -0.14
    rum
    -0.14
    nave
    -0.14
    Tek
    -0.14
    æĺ¾
    -0.14
    POSITIVE LOGITS
     guts
    0.19
     mucho
    0.18
     болÑĮÑĪе
    0.18
    .reserve
    0.17
     more
    0.16
     much
    0.16
     enough
    0.16
    otify
    0.16
     tanto
    0.15
     Thumb
    0.15
    Act Density 0.166%

    No Known Activations