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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is nodding, sighing, smiling, chuckling, rolling, or grinning in a conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of characters expressing agreement or acknowledgment through nodding or similar actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    modern
    -0.74
    por
    -0.74
    lat
    -0.71
    ãĥķãĤ¡
    -0.70
     Kardash
    -0.68
    historic
    -0.67
    gins
    -0.67
    ãĥİ
    -0.66
    fits
    -0.66
    port
    -0.65
    POSITIVE LOGITS
     nervously
    1.03
     aloud
    0.92
     angrily
    0.82
     calmly
    0.82
     omin
    0.81
     silently
    0.81
     confidently
    0.80
     softly
    0.79
     bitterly
    0.79
     quizz
    0.79
    Act Density 0.113%

    No Known Activations