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

    Neuronpedia

    INDEX
    Explanations

    questions directed at the reader

    oai_token-act-pair · gpt-3.5-turbo

    questions or prompts directed at the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assemb
    -0.85
     Continued
    -0.71
    objects
    -0.68
    ilus
    -0.67
    artifacts
    -0.66
    Dialogue
    -0.65
    assembly
    -0.65
    accompan
    -0.64
     Integrity
    -0.64
    Whereas
    -0.62
    POSITIVE LOGITS
     mention
    0.88
     originate
    0.88
     survive
    0.87
     stumble
    0.87
     realise
    0.84
     intend
    0.82
     disappear
    0.81
     anticipate
    0.80
     lapse
    0.79
     manage
    0.79
    Act Density 0.105%

    No Known Activations