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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "let."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gne
    -0.18
    iez
    -0.17
    rien
    -0.16
    sdk
    -0.15
    azon
    -0.15
    ãģ¾ãģ¨
    -0.15
    strate
    -0.15
    ะ
    -0.15
    illet
    -0.15
    ToLeft
    -0.14
    POSITIVE LOGITS
    tres
    0.26
    tings
    0.26
    ting
    0.24
     us
    0.23
    tle
    0.21
    ÃŃcia
    0.21
    ted
    0.20
    ts
    0.20
    TERS
    0.19
    ters
    0.18
    Act Density 0.050%

    No Known Activations