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

    Neuronpedia

    INDEX
    Explanations

    events or actions related to political or social issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of introductory phrases or conjunctions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     etc
    -0.88
    Conclusion
    -0.87
    CONCLUS
    -0.77
    Anyway
    -0.77
    Lastly
    -0.72
     Lastly
    -0.71
     ;)
    -0.68
     :(
    -0.68
    ))))
    -0.65
     someday
    -0.65
    POSITIVE LOGITS
    itled
    0.76
     POLITICO
    0.76
    ccording
    0.72
    irteen
    0.71
    ilant
    0.71
     excerpts
    0.69
    ensed
    0.66
    alling
    0.65
     bombshell
    0.65
    eaturing
    0.65
    Act Density 0.537%

    No Known Activations