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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating frequency or commonality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or regularity of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atur
    -0.91
    itivity
    -0.86
    ves
    -0.82
    uble
    -0.80
    atures
    -0.80
    ibility
    -0.78
    own
    -0.78
    idates
    -0.76
    itives
    -0.76
    leground
    -0.73
    POSITIVE LOGITS
     excluding
    1.06
     implying
    1.01
     preferring
    0.96
     indicating
    0.91
     numbering
    0.91
     suggesting
    0.90
     culminating
    0.89
     skipping
    0.88
     consisting
    0.88
     conclud
    0.88
    Act Density 0.146%

    No Known Activations