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

    Neuronpedia

    INDEX
    Explanations

    conclusive statements or transitions in reasoning

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

    introducing a conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anteen
    -0.57
    erview
    -0.52
     Badge
    -0.52
     Bowling
    -0.52
     Ventilation
    -0.51
     Lint
    -0.50
    Auditor
    -0.50
    ⒝
    -0.50
     ſeine
    -0.50
     telemetry
    -0.49
    POSITIVE LOGITS
     Thus
    1.39
    Thus
    1.37
    Ainsi
    0.89
     Ainsi
    0.87
    Hence
    0.76
     Hence
    0.76
     Therefore
    0.73
    Therefore
    0.71
     thus
    0.62
    thus
    0.60
    Act Density 0.016%

    No Known Activations