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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between characters in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    419
    -0.17
    Cro
    -0.17
     Cro
    -0.16
    endra
    -0.15
     sublist
    -0.15
     dust
    -0.14
    Portal
    -0.14
    edom
    -0.14
     portal
    -0.14
     Baba
    -0.14
    POSITIVE LOGITS
    .Fat
    0.19
     Rek
    0.18
    hiba
    0.18
    agma
    0.18
     Fat
    0.18
     Rich
    0.17
     PRI
    0.17
     Sum
    0.17
    ваÑĤи
    0.17
    Fat
    0.17
    Act Density 0.298%

    No Known Activations