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

    Neuronpedia

    INDEX
    Explanations

    specific parts of objects or machines

    oai_token-act-pair · gpt-3.5-turbo

    specific components and features of physical objects and mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.71
    undown
    -0.68
    acerb
    -0.68
    Ô
    -0.68
    HAHAHAHA
    -0.66
    invoke
    -0.65
    licensed
    -0.63
     Gamble
    -0.62
    alg
    -0.62
    named
    -0.62
    POSITIVE LOGITS
     itself
    1.13
     casing
    1.10
     shaft
    1.10
     nozzle
    1.08
     cavity
    1.05
     surface
    1.05
     envelope
    1.04
     enclosure
    1.04
     coil
    1.03
     axle
    1.03
    Act Density 0.272%

    No Known Activations