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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ideas, beliefs, and concepts

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to ideals and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iatus
    -0.78
    usercontent
    -0.78
     haul
    -0.72
    reports
    -0.72
    glers
    -0.71
    oops
    -0.71
     cleanup
    -0.70
    ãĥīãĥ©
    -0.70
     parcels
    -0.68
    ebin
    -0.67
    POSITIVE LOGITS
     essential
    1.24
     characteristic
    1.24
     antit
    1.22
     inherent
    1.10
     hallmark
    1.09
     embodied
    1.08
     sorely
    1.07
     innate
    1.06
     paramount
    1.04
     admirable
    1.04
    Act Density 0.325%

    No Known Activations