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

    Neuronpedia

    INDEX
    Explanations

    function calls related to converting objects to string representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mandu
    -0.71
    o
    -0.66
     Bal
    -0.65
    en
    -0.63
    6
    -0.58
    kwds
    -0.57
     Pat
    -0.55
     Вікі
    -0.55
     mar
    -0.54
     ce
    -0.53
    POSITIVE LOGITS
    toString
    1.55
     toString
    1.45
    ToString
    1.18
     ToString
    1.08
     Monfieur
    1.08
     itſelf
    1.01
     Theſe
    0.94
     himſelf
    0.94
     Toh
    0.92
     myſelf
    0.90
    Act Density 0.028%

    No Known Activations