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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions with emotional context

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and text transitions indicating emotional context or narrative flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carson
    -0.92
    espie
    -0.92
     helicop
    -0.87
     bolted
    -0.87
     loaf
    -0.86
     Webb
    -0.86
     ranc
    -0.80
    Colorado
    -0.80
     Rudd
    -0.80
     JFK
    -0.79
    POSITIVE LOGITS
     manga
    1.46
     anime
    1.41
     ãĢĮ
    1.38
     Anime
    1.38
     Yamato
    1.37
    ãĢİ
    1.35
    ãĢIJ
    1.35
     æ
    1.34
     ¥
    1.30
    âĺĨ
    1.30
    Act Density 0.791%

    No Known Activations