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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.17
    rette
    -0.16
    amax
    -0.15
    imits
    -0.15
    sian
    -0.15
    ummer
    -0.14
    urt
    -0.14
    illac
    -0.14
    seau
    -0.14
    yor
    -0.14
    POSITIVE LOGITS
    paged
    0.18
    abouts
    0.17
    isle
    0.17
    jÅ¡ÃŃ
    0.15
    ems
    0.14
    after
    0.14
    966
    0.14
    uze
    0.13
    adow
    0.13
    idl
    0.13
    Act Density 0.053%

    No Known Activations