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

    Neuronpedia

    INDEX
    Explanations

    instances of the preposition "to" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive form "to" followed by various verbs indicating actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opens
    -0.68
     Rapids
    -0.67
    ascript
    -0.66
    bats
    -0.63
     Marcos
    -0.63
    loads
    -0.61
    aroo
    -0.59
    blooded
    -0.58
     helicop
    -0.58
     Delicious
    -0.57
    POSITIVE LOGITS
     indicate
    0.93
     imply
    0.87
     settle
    0.83
     be
    0.81
     embody
    0.80
     contradict
    0.80
     confirm
    0.80
     differentiate
    0.78
     agree
    0.78
     satisfy
    0.77
    Act Density 0.064%

    No Known Activations