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

    Neuronpedia

    INDEX
    Explanations

    proper acronyms or abbreviations related to organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or councils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ance
    -0.84
    URA
    -0.73
    ãĤ¢ãĥ«
    -0.71
    Wire
    -0.71
     Colt
    -0.70
    etr
    -0.69
    Side
    -0.68
    AAAA
    -0.68
     Tarant
    -0.67
    sson
    -0.67
    POSITIVE LOGITS
     CPC
    0.98
    ocobo
    0.76
    akings
    0.75
    odore
    0.72
    artney
    0.68
     primates
    0.68
    rador
    0.65
     corrected
    0.65
    devices
    0.65
     leaflets
    0.65
    Act Density 0.001%

    No Known Activations