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

    Neuronpedia

    INDEX
    Explanations

    Twitter retweets and mentions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the ">>>" symbol, indicating transitions or prompts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagon
    -0.99
    ahime
    -0.90
    laus
    -0.80
    ible
    -0.77
    enzie
    -0.77
    rive
    -0.76
    drive
    -0.74
    fare
    -0.73
    ouver
    -0.73
    alez
    -0.73
    POSITIVE LOGITS
    >>>>>>>>
    1.60
    >>>>
    1.37
    >>>
    1.15
     >>>
    0.99
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.84
    ertodd
    0.79
    _>
    0.75
    ¶
    0.74
    âĸĵ
    0.74
    >>
    0.74
    Act Density 0.010%

    No Known Activations