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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs followed by an object or concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate instructions or recommended actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mails
    -0.64
    quickShipAvailable
    -0.62
    âĿ
    -0.61
     looms
    -0.61
     replies
    -0.61
     handles
    -0.60
    listed
    -0.59
    Dur
    -0.59
     Hind
    -0.59
    typ
    -0.58
    POSITIVE LOGITS
     dismantle
    1.06
     minimize
    1.06
     create
    1.05
     maximize
    1.04
     educate
    1.04
     find
    1.02
     recreate
    1.00
     eliminate
    1.00
     conserve
    1.00
     deprive
    0.99
    Act Density 0.132%

    No Known Activations