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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    timestamped entries indicating document or content revisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     expansion
    -0.68
    ļéĨĴ
    -0.64
     Administration
    -0.63
     ACTIONS
    -0.63
     Handbook
    -0.59
     Opportun
    -0.59
     pockets
    -0.58
     Generations
    -0.56
     Mao
    -0.56
     intimidate
    -0.56
    POSITIVE LOGITS
    08
    1.21
    22
    1.19
    02
    1.18
    28
    1.17
    09
    1.17
    01
    1.17
    07
    1.15
    29
    1.14
    05
    1.12
    04
    1.12
    Act Density 0.032%

    No Known Activations