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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating completed actions or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rish
    -0.76
    iru
    -0.73
     Sabha
    -0.70
    ofi
    -0.62
    article
    -0.61
     anymore
    -0.60
    inki
    -0.60
    November
    -0.60
    Pierre
    -0.60
    now
    -0.60
    POSITIVE LOGITS
     countless
    1.11
     innumerable
    0.98
     extensively
    0.94
     numerous
    0.92
     hitherto
    0.91
     plenty
    0.89
     since
    0.83
     enough
    0.82
     dozens
    0.76
     previously
    0.76
    Act Density 0.279%

    No Known Activations