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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "to be" and associated linguistic nuances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imir
    -0.17
    andle
    -0.15
    andles
    -0.15
    annel
    -0.15
    ANDLE
    -0.15
    apor
    -0.14
    abyrin
    -0.14
    iod
    -0.14
    å®
    -0.14
    asury
    -0.14
    POSITIVE LOGITS
    olon
    0.22
     Rolling
    0.19
     rolling
    0.18
    Ke
    0.18
    airo
    0.17
     Ke
    0.17
    llib
    0.15
    OLON
    0.15
    rolling
    0.15
     KE
    0.15
    Act Density 0.027%

    No Known Activations