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

    Neuronpedia

    INDEX
    Explanations

    the word "To" followed by a verb, indicating an action or purpose

    oai_token-act-pair · gpt-3.5-turbo

    the word "To" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nets
    -0.69
     drops
    -0.64
     plans
    -0.63
     Travels
    -0.61
    dro
    -0.61
     dips
    -0.60
     diapers
    -0.60
     shares
    -0.59
    hops
    -0.59
     forg
    -0.59
    POSITIVE LOGITS
    ilet
    1.35
     summarize
    1.10
     reiterate
    1.02
    ppings
    0.96
     clarify
    0.95
    oru
    0.94
    pping
    0.92
     complicate
    0.91
    asty
    0.90
     illustrate
    0.86
    Act Density 0.067%

    No Known Activations