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

    Neuronpedia

    INDEX
    Explanations

    keywords related to computer programming commands and functions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to user interaction and application functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bryce
    -0.53
    stra
    -0.45
     Cheng
    -0.42
    adr
    -0.42
    Moscow
    -0.42
     Blasio
    -0.42
    addon
    -0.41
    thouse
    -0.40
    raltar
    -0.38
     Cherry
    -0.37
    POSITIVE LOGITS
    ....
    0.53
     hemor
    0.49
    âĢ¦.
    0.48
    !!!
    0.48
     aph
    0.48
     ....
    0.47
    ...
    0.46
    !!!!!
    0.46
    .......
    0.46
     [-
    0.45
    Act Density 3.111%

    No Known Activations