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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Theſe
    -0.86
     Houſe
    -0.81
     transfieras
    -0.80
     Monfieur
    -0.79
     itſelf
    -0.77
     faſt
    -0.75
     Cæsar
    -0.75
     Efq
    -0.72
     himſelf
    -0.71
     surla
    -0.71
    POSITIVE LOGITS
    ười
    0.54
     Bel
    0.53
    orice
    0.50
     Ad
    0.48
    minos
    0.48
    toHave
    0.47
     Mathis
    0.47
    TUR
    0.47
     Lo
    0.46
    tellations
    0.46
    Act Density 0.026%

    No Known Activations