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

    Neuronpedia

    INDEX
    Explanations

    names of characters in a storyline

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "Weiss" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ���
    -0.77
     Baptist
    -0.76
     cattle
    -0.72
     Lak
    -0.70
     Argentine
    -0.69
     Converted
    -0.68
     RF
    -0.68
     Vide
    -0.67
     agriculture
    -0.67
     pastoral
    -0.66
    POSITIVE LOGITS
     Weiss
    3.40
    Weiss
    3.37
    Yang
    2.63
     Yang
    2.58
     Pyrrha
    2.50
     Jaune
    2.20
    Blake
    2.00
    Ruby
    1.99
     Ruby
    1.93
     Blake
    1.90
    Act Density 0.039%

    No Known Activations