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

    Neuronpedia

    INDEX
    Explanations

    references to large, impressive structures or beings

    oai_token-act-pair · gpt-3.5-turbo

    descriptive terms related to size and grandeur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endment
    -0.81
    topic
    -0.77
    said
    -0.76
    saf
    -0.74
    ersion
    -0.72
    summary
    -0.71
    burn
    -0.71
    LOG
    -0.70
    Board
    -0.70
    washer
    -0.70
    POSITIVE LOGITS
     towering
    1.12
     imposing
    1.00
     colossal
    0.95
     monstrous
    0.95
     stature
    0.93
    oppable
    0.88
     tremend
    0.88
     lumber
    0.87
     majestic
    0.85
     menacing
    0.83
    Act Density 0.048%

    No Known Activations