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

    Neuronpedia

    INDEX
    Explanations

    references to the word "us" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    och
    -0.16
    ous
    -0.15
    endon
    -0.15
    quist
    -0.15
     himself
    -0.15
    arah
    -0.15
    lein
    -0.14
    cala
    -0.14
    uchi
    -0.14
    hattan
    -0.14
    POSITIVE LOGITS
    /me
    0.23
    /us
    0.22
    urious
    0.20
    eping
    0.18
    ury
    0.17
    SEL
    0.17
    tesy
    0.16
    opia
    0.16
     $č↵
    0.16
    ’re
    0.15
    Act Density 0.061%

    No Known Activations