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

    Neuronpedia

    INDEX
    Explanations

    specific phrases and words that indicate opinions, emotional responses, or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Diss
    -0.17
    asta
    -0.15
     Ant
    -0.15
     Stephens
    -0.14
    à¥ģà¤Ĩ
    -0.14
    obic
    -0.14
     Howe
    -0.14
    hs
    -0.14
     relative
    -0.14
    anda
    -0.14
    POSITIVE LOGITS
    hum
    0.15
    ambi
    0.14
     hum
    0.14
    Ïĥιο
    0.14
     GObject
    0.14
    uster
    0.14
    æ°ı
    0.14
    uxtap
    0.14
    ayet
    0.14
    ully
    0.14
    Act Density 0.118%

    No Known Activations