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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "see."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rien
    -0.18
    pcs
    -0.18
    soever
    -0.17
    ôi
    -0.17
    cai
    -0.16
    uzzer
    -0.16
    orsi
    -0.16
    serie
    -0.16
    stem
    -0.16
    cs
    -0.16
    POSITIVE LOGITS
    /he
    0.33
    dust
    0.24
     fit
    0.23
     cref
    0.21
     how
    0.21
     xét
    0.20
    -through
    0.20
    kest
    0.20
    /read
    0.18
    lessly
    0.17
    Act Density 0.117%

    No Known Activations