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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "letter" and related forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ot
    -0.16
    fak
    -0.15
    opi
    -0.15
    jour
    -0.15
    물
    -0.15
    itary
    -0.14
    emaker
    -0.14
    ara
    -0.14
    ivic
    -0.14
    ä½Ļ
    -0.14
    POSITIVE LOGITS
    xeb
    0.16
    reuse
    0.15
    stash
    0.15
    ToDevice
    0.14
    ICENSE
    0.14
    rente
    0.14
    istrovstvÃŃ
    0.14
    rops
    0.14
    abyrinth
    0.14
    bird
    0.14
    Act Density 0.035%

    No Known Activations