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

    Neuronpedia

    INDEX
    Explanations

    the word "let" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emmel
    -0.16
    sdk
    -0.16
    qué
    -0.15
    hazi
    -0.15
    edb
    -0.15
    erland
    -0.15
    strate
    -0.15
    erais
    -0.14
    ently
    -0.14
    573
    -0.14
    POSITIVE LOGITS
    ting
    0.30
    tings
    0.30
    tres
    0.29
    itia
    0.25
    tre
    0.23
    ty
    0.23
    tered
    0.23
    zte
    0.22
    izia
    0.22
    ture
    0.21
    Act Density 0.018%

    No Known Activations