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

    Neuronpedia

    INDEX
    Explanations

    keywords related to class and method definitions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    мся
    -0.47
    éu
    -0.46
     ơn
    -0.45
     might
    -0.45
     U
    -0.44
    oral
    -0.43
    во
    -0.43
    ͐
    -0.43
     ré
    -0.42
     Va
    -0.42
    POSITIVE LOGITS
     Monfieur
    0.86
     Houſe
    0.86
     houſe
    0.85
     himſelf
    0.83
     themſelves
    0.82
    Personendaten
    0.82
     purpoſe
    0.82
     Diſ
    0.80
     pleaſure
    0.80
     myſelf
    0.78
    Act Density 0.247%

    No Known Activations