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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and definitions related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     them
    -0.47
    いえ
    -0.42
    MessageTagHelper
    -0.42
     just
    -0.41
    まま
    -0.41
    立て
    -0.41
    Extension
    -0.40
     wouldn
    -0.40
     won
    -0.40
    Extensions
    -0.39
    POSITIVE LOGITS
     &___
    0.83
    Erreferentziak
    0.80
    Sklici
    0.77
    новниш
    0.75
    NOPQRST
    0.73
     Савезне
    0.72
     ovviamente
    0.72
    ंदीखरीदारी
    0.71
    nodoc
    0.71
    AndEndTag
    0.71
    Act Density 0.663%

    No Known Activations