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

    Neuronpedia

    INDEX
    Explanations

    words related to identity and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "The first," "the last," "the [adjective] of"

    np_acts-logits-general · gemini-2.0-flash

    unique roles and superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.89
     للمعارف
    -0.81
    livé
    -0.70
    vedať
    -0.64
     pelbagai
    -0.63
     BoxDecoration
    -0.62
     laterales
    -0.61
    ьаж
    -0.60
     estimés
    -0.59
    richTextPanel
    -0.58
    POSITIVE LOGITS
     only
    1.04
    only
    0.78
     recipient
    0.74
     youngest
    0.73
     sole
    0.69
     subject
    0.67
     ONLY
    0.67
     winner
    0.67
     epitome
    0.66
     oldest
    0.66
    Act Density 0.267%

    No Known Activations