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

    Neuronpedia

    INDEX
    Explanations

    phrases describing permission or allowance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating permission or the ability to perform an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.98
     Explan
    -0.76
    furt
    -0.71
    til
    -0.68
    tons
    -0.65
    teen
    -0.64
     Needs
    -0.63
     Compass
    -0.62
     Lines
    -0.61
    lights
    -0.60
    POSITIVE LOGITS
     indulge
    1.13
     participate
    1.08
     avoid
    1.08
     accumulate
    1.05
     achieve
    1.05
     negotiate
    1.05
     communicate
    1.02
     partake
    1.02
     carve
    1.02
     reproduce
    1.02
    Act Density 0.124%

    No Known Activations