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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    dialogue and quotations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unsus
    -0.81
     autonom
    -0.79
     privat
    -0.79
     holdings
    -0.78
     authorised
    -0.78
     coerc
    -0.77
     predec
    -0.77
     nude
    -0.77
     explicitly
    -0.76
     censored
    -0.76
    POSITIVE LOGITS
     Hopefully
    1.45
     Obviously
    1.38
     Guys
    1.35
    Hopefully
    1.29
    Obviously
    1.28
    Coach
    1.25
     Whoever
    1.19
     Everybody
    1.17
    Playing
    1.17
    Everybody
    1.16
    Act Density 0.207%

    No Known Activations