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

    Neuronpedia

    INDEX
    Explanations

    words that convey a sense of continuity, such as prefixes indicating repetition or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uster
    -0.17
    jian
    -0.16
     inplace
    -0.15
    izmet
    -0.15
    ronics
    -0.14
    ÛĮÙĩ
    -0.14
     crossings
    -0.14
     Chin
    -0.14
    oog
    -0.13
    umi
    -0.13
    POSITIVE LOGITS
     Burl
    0.16
    bal
    0.15
    itr
    0.15
    ạp
    0.15
    eyen
    0.15
    ÑĢоÑģ
    0.15
    -stack
    0.15
    sik
    0.15
    ecer
    0.15
     Sai
    0.14
    Act Density 0.017%

    No Known Activations