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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of speaking, making, supporting, and bringing

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate movement or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.70
     prest
    -0.65
    lear
    -0.65
     Seym
    -0.64
     Azerb
    -0.63
    emale
    -0.59
    inse
    -0.57
    iterranean
    -0.56
     Gaw
    -0.55
    odynam
    -0.55
    POSITIVE LOGITS
     ][
    0.72
     ]
    0.68
    actionDate
    0.65
     Vulkan
    0.60
    OTOS
    0.58
    Í
    0.57
     Provided
    0.57
     ];
    0.56
     ].
    0.56
    CLUS
    0.56
    Act Density 0.200%

    No Known Activations