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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions, limitations, or clauses

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "no bid" contracts and similar agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reloaded
    -0.78
     Rouge
    -0.71
    APTER
    -0.70
     Fork
    -0.68
    ãĥ¼ãĥĨ
    -0.67
     Unch
    -0.66
     Sparrow
    -0.66
    çīĪ
    -0.66
     Debor
    -0.65
     Royale
    -0.65
    POSITIVE LOGITS
    brainer
    1.07
    matter
    1.04
    notice
    1.00
    interest
    0.96
    purpose
    0.94
    contact
    0.94
    move
    0.94
    touch
    0.94
    issue
    0.94
    repeat
    0.93
    Act Density 0.019%

    No Known Activations