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

    Neuronpedia

    INDEX
    Explanations

    keywords related to coding and technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of examples or references to specific cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utral
    -0.78
    ocaust
    -0.77
    olit
    -0.73
    bent
    -0.73
    ridor
    -0.71
    ONSORED
    -0.71
    Los
    -0.68
    enary
    -0.68
    ometown
    -0.68
    orne
    -0.67
    POSITIVE LOGITS
     specifying
    1.10
     you
    1.06
     we
    1.04
     Emacs
    1.03
     GHC
    1.03
     jQuery
    0.98
     xml
    0.98
     mysql
    0.97
     JSON
    0.97
     disabling
    0.97
    Act Density 0.218%

    No Known Activations