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

    Neuronpedia

    INDEX
    Explanations

    short distinctive patterns

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or the end of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extrad
    -0.75
     legally
    -0.73
     estranged
    -0.71
     herself
    -0.70
     frontline
    -0.70
     amnesty
    -0.69
     orchestr
    -0.68
     divest
    -0.68
     marching
    -0.67
    illance
    -0.67
    POSITIVE LOGITS
    Anyway
    1.08
    ³³³³
    1.07
    ³³³³³³³³³³³³³³³³
    1.07
    Conclusion
    1.03
    CONCLUS
    1.01
    Characters
    0.97
    Posted
    0.97
    Lastly
    0.97
    Example
    0.96
    Recommended
    0.96
    Act Density 1.060%

    No Known Activations