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

    Neuronpedia

    INDEX
    Explanations

    discussions of philosophical concepts and the importance of human connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words like "purpose" or "expectations."

    np_acts-logits-general · gemini-2.0-flash

    purpose and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plus
    -0.56
     reportedly
    -0.52
     {}
    -0.52
    plus
    -0.52
     aber
    -0.52
     Thompson
    -0.52
    )
    -0.51
    ↵↵
    -0.50
    ))
    -0.50
    +}
    -0.50
    POSITIVE LOGITS
     myſelf
    0.99
     greateſt
    0.95
     becauſe
    0.91
     itſelf
    0.90
     purpoſe
    0.90
     preſent
    0.88
     poffible
    0.87
     ་་
    0.84
     unſ
    0.83
    ſelves
    0.82
    Act Density 0.502%

    No Known Activations