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

    Neuronpedia

    INDEX
    Explanations

    instances of using tools or technology to accomplish tasks or solve problems efficiently

    oai_token-act-pair · gpt-3.5-turbo

    phrases or structures that indicate purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Needs
    -0.72
     Closing
    -0.71
     Removal
    -0.66
    soDeliveryDate
    -0.66
    quickShipAvailable
    -0.65
     Caller
    -0.65
    nil
    -0.65
    icipated
    -0.64
    soType
    -0.63
    comings
    -0.63
    POSITIVE LOGITS
     enhance
    1.27
     maximize
    1.27
     create
    1.24
     promote
    1.21
     facilitate
    1.21
     minimize
    1.19
     preserve
    1.18
     protect
    1.17
     ensure
    1.16
     navigate
    1.15
    Act Density 0.150%

    No Known Activations