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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" indicating collective or group involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andon
    -0.15
    weise
    -0.14
     itself
    -0.14
    endon
    -0.14
    aye
    -0.13
    ãĤıãĤĬ
    -0.13
    lem
    -0.13
    å®ı
    -0.13
     Levine
    -0.13
    mq
    -0.13
    POSITIVE LOGITS
    eping
    0.24
    ’re
    0.24
    've
    0.24
    're
    0.23
    ’ve
    0.22
    'll
    0.20
    ’ll
    0.20
    apons
    0.19
    isman
    0.19
    eding
    0.18
    Act Density 0.290%

    No Known Activations