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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "me."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vitis
    -0.54
    CodeAttribute
    -0.51
    руд
    -0.49
    Atsauces
    -0.49
     hauteur
    -0.48
     net
    -0.47
    qiu
    -0.47
    casm
    -0.46
     benne
    -0.45
    kori
    -0.45
    POSITIVE LOGITS
     Tarzan
    0.60
    KURZBESCHREIBUNG
    0.57
    gap
    0.56
     timbers
    0.55
     OFDb
    0.54
     selves
    0.54
     metav
    0.54
    CFS
    0.53
    Me
    0.52
    setVerticalGroup
    0.52
    Act Density 0.108%

    No Known Activations