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

    Neuronpedia

    INDEX
    Explanations

    statements and questions related to beliefs and opinions

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

    Follows discourse markers or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    And with certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    깥
    -0.78
     ddelweddau
    -0.68
    ]}"
    -0.68
     undersigned
    -0.68
     Roskov
    -0.66
    Such
    -0.65
     !)
    -0.65
     Pois
    -0.63
    )="
    -0.63
     Such
    -0.62
    POSITIVE LOGITS
     obviously
    1.10
     certainly
    1.02
    obviously
    0.93
     oftentimes
    0.92
    certainly
    0.91
     particularly
    0.88
     basically
    0.86
     everybody
    0.85
     essentially
    0.85
     effectivement
    0.84
    Act Density 0.177%

    No Known Activations