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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive form of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afety
    -0.71
     packets
    -0.65
     cass
    -0.63
     freezes
    -0.62
     refunds
    -0.60
     airs
    -0.60
     drops
    -0.60
     curfew
    -0.60
     coats
    -0.60
     suspensions
    -0.59
    POSITIVE LOGITS
     behold
    0.94
     obtain
    0.91
    ilet
    0.91
    ggles
    0.91
     contemplate
    0.90
     attain
    0.89
    adies
    0.88
    asty
    0.88
     achieve
    0.88
     cherish
    0.86
    Act Density 0.174%

    No Known Activations