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

    Neuronpedia

    INDEX
    Explanations

    the word "to" followed by a verb in infinitive form

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate methods or approaches to achieve a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     airs
    -0.62
     Appears
    -0.61
     reperto
    -0.60
    chains
    -0.59
     reacts
    -0.59
     scares
    -0.56
    quickShipAvailable
    -0.56
     faces
    -0.55
     handles
    -0.55
     triggers
    -0.55
    POSITIVE LOGITS
    othy
    0.90
     provide
    0.90
     minimize
    0.87
    ifle
    0.84
     educate
    0.83
     enlarge
    0.83
     maximize
    0.83
    ffee
    0.83
     avoid
    0.82
     refine
    0.82
    Act Density 0.069%

    No Known Activations