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

    Neuronpedia

    INDEX
    Explanations

    verbs related to accomplishments and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate completion of tasks or accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rish
    -0.75
    iru
    -0.70
    article
    -0.68
    apo
    -0.63
    idental
    -0.61
    Whoever
    -0.59
    cms
    -0.59
     anymore
    -0.59
    $$$$
    -0.58
    terday
    -0.57
    POSITIVE LOGITS
     countless
    1.22
     numerous
    1.20
     plenty
    1.14
     innumerable
    1.10
     extensively
    1.04
     since
    0.98
     several
    0.93
     considerable
    0.93
     dozens
    0.91
     many
    0.90
    Act Density 0.236%

    No Known Activations