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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the value and significance of experiences and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.18
    obot
    -0.17
    alling
    -0.14
    inish
    -0.14
    iedy
    -0.14
    iž
    -0.14
    ocket
    -0.14
    riel
    -0.14
    ê¹Įì§Ģ
    -0.14
    double
    -0.13
    POSITIVE LOGITS
     simple
    0.34
     mere
    0.33
    mere
    0.33
     merely
    0.30
    simple
    0.29
     simply
    0.29
     tiny
    0.28
     simples
    0.27
    ç®Ģåįķ
    0.25
     einfach
    0.25
    Act Density 0.229%

    No Known Activations