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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical movements or gestures

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate giving or moving towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.70
     vows
    -0.65
     boycot
    -0.64
     warr
    -0.60
     drafted
    -0.59
     trusts
    -0.59
     warrants
    -0.58
    owship
    -0.58
     Monthly
    -0.58
     advertis
    -0.57
    POSITIVE LOGITS
    ggles
    1.15
     stabilize
    1.11
     minimize
    1.09
    wered
    1.07
     relieve
    1.07
     ensure
    1.06
     maximize
    1.06
    othy
    1.03
     prevent
    1.02
     conserve
    1.02
    Act Density 0.183%

    No Known Activations