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

    Neuronpedia

    INDEX
    Explanations

    phrases related to character interactions and emotions, particularly focusing on a specific character named Weiss

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Weiss" and its associated relationships with other characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.92
     ILCS
    -0.79
    Indiana
    -0.77
    Afee
    -0.72
    ally
    -0.71
    osaurs
    -0.70
    anism
    -0.68
    dos
    -0.67
    assic
    -0.67
    ously
    -0.66
    POSITIVE LOGITS
     Schwarz
    1.00
     Swift
    0.78
     Weiss
    0.76
     Pyrrha
    0.72
    lda
    0.72
    ullivan
    0.71
     Ruby
    0.69
    schild
    0.68
    Weiss
    0.68
    yang
    0.67
    Act Density 0.034%

    No Known Activations