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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to memory and forgetting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LT
    -0.17
    finder
    -0.17
    ylko
    -0.16
    æ°Ĺãģ«åħ¥
    -0.15
    upa
    -0.15
    anine
    -0.14
    yla
    -0.14
    ropa
    -0.14
    ynchronously
    -0.14
    ighet
    -0.14
    POSITIVE LOGITS
    fulness
    0.28
    ful
    0.23
     about
    0.23
    ting
    0.22
    ten
    0.22
    tings
    0.21
    FUL
    0.20
    table
    0.20
    about
    0.19
    -about
    0.18
    Act Density 0.043%

    No Known Activations