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

    Neuronpedia

    INDEX
    Explanations

    instances of self-introduction and naming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    my name is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.62
     autorytatywna
    -0.60
    AISSEE
    -0.56
    ▭
    -0.52
    bollah
    -0.51
     corações
    -0.50
     apsau
    -0.49
    OpenHelper
    -0.49
    出版年
    -0.49
    ckså
    -0.47
    POSITIVE LOGITS
     name
    0.88
     Name
    0.71
     NAME
    0.68
    Name
    0.59
    name
    0.57
     名前
    0.52
    myname
    0.50
    名前
    0.48
    NAME
    0.47
     nome
    0.46
    Act Density 0.004%

    No Known Activations