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

    Neuronpedia

    INDEX
    Explanations

    information about computer programming and data manipulation

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to data storage and retrieval processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hutch
    -0.72
    Ħ¢
    -0.71
    otics
    -0.70
    forums
    -0.69
     controversies
    -0.68
     resurg
    -0.67
    姫
    -0.66
     critics
    -0.65
    tics
    -0.64
     tactics
    -0.63
    POSITIVE LOGITS
     corresponding
    1.15
     bytes
    1.09
     containing
    1.08
     representing
    1.04
     initialized
    1.03
     byte
    1.02
     tuple
    1.02
     integer
    1.01
     (%
    1.00
     "\
    0.98
    Act Density 0.247%

    No Known Activations