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

    Neuronpedia

    INDEX
    Explanations

    the name "Shanti Bahini" mentioned multiple times in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.70
     uſed
    -0.65
     '\\;'
    -0.64
     expédié
    -0.63
     Référence
    -0.63
     myſelf
    -0.60
     Humanos
    -0.60
    didSet
    -0.59
    niająca
    -0.59
     unpacking
    -0.59
    POSITIVE LOGITS
     margin
    0.94
    Margin
    0.85
     marginal
    0.85
     Margin
    0.82
     Marginal
    0.76
    margin
    0.72
    MARGIN
    0.69
    marginal
    0.69
     bottom
    0.68
     marge
    0.66
    Act Density 0.163%

    No Known Activations