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

    Neuronpedia

    INDEX
    Explanations

    references to acronyms related to organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or entities with the acronym "OC."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    things
    -0.78
    selves
    -0.76
    gets
    -0.75
     Somers
    -0.69
    fuck
    -0.68
    boards
    -0.68
     Dresden
    -0.68
     Keynes
    -0.68
     dab
    -0.67
    flies
    -0.67
    POSITIVE LOGITS
    ombat
    1.06
    ategory
    0.99
    ARB
    0.98
    ontent
    0.98
    EED
    0.97
    IAL
    0.96
    OPS
    0.94
    OC
    0.94
    ACY
    0.93
    ESS
    0.92
    Act Density 0.020%

    No Known Activations