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

    Neuronpedia

    INDEX
    Explanations

    dialogue quotes from a conversation

    oai_token-act-pair · gpt-3.5-turbo

    dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.85
     stunts
    -0.78
     helicop
    -0.78
    aukee
    -0.72
     ingred
    -0.69
     incorpor
    -0.69
     endorsements
    -0.67
     maximal
    -0.67
     creatively
    -0.66
    otin
    -0.65
    POSITIVE LOGITS
    pause
    1.01
    Pause
    0.90
     Silence
    0.87
     Pyrrha
    0.82
     Slowly
    0.82
     Jaune
    0.82
     Suddenly
    0.80
     Calm
    0.79
     murm
    0.79
     Naruto
    0.78
    Act Density 0.106%

    No Known Activations