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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" and phrases indicating collective action or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     we
    -0.24
    æĪij们
    -0.22
     мÑĭ
    -0.22
     ours
    -0.19
    we
    -0.19
    æĪijåĢij
    -0.19
    .we
    -0.18
     us
    -0.18
    amo
    -0.18
    our
    -0.17
    POSITIVE LOGITS
    ACHE
    0.17
    swer
    0.16
    .getOwnProperty
    0.15
    coli
    0.15
    zeich
    0.15
    ApiClient
    0.14
    blink
    0.14
     honeymoon
    0.14
    inan
    0.14
     writ
    0.13
    Act Density 0.067%

    No Known Activations