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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "let" and its variations, often in contexts implying allowance or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Slf
    -0.16
    ssp
    -0.16
    veau
    -0.15
    yb
    -0.15
    rien
    -0.15
    aiser
    -0.14
    okt
    -0.14
    olland
    -0.14
    евеÑĢ
    -0.14
    =__
    -0.14
    POSITIVE LOGITS
    tings
    0.19
    ting
    0.17
    chas
    0.16
    erea
    0.16
    TING
    0.15
    ted
    0.15
    427
    0.15
     us
    0.15
    tres
    0.15
    GO
    0.15
    Act Density 0.049%

    No Known Activations