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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Respons
    -0.80
    mails
    -0.74
    listed
    -0.72
    quickShipAvailable
    -0.71
     Explan
    -0.67
    lights
    -0.67
     Coff
    -0.65
    cloth
    -0.63
     destined
    -0.63
     Directions
    -0.62
    POSITIVE LOGITS
     achieve
    1.14
     accomplish
    1.14
     withstand
    1.12
     cope
    1.07
     penetrate
    1.06
     solve
    1.05
     accommodate
    1.04
     navigate
    1.02
     convince
    1.02
     overcome
    1.02
    Act Density 0.096%

    No Known Activations