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

    Neuronpedia

    INDEX
    Explanations

    sections of text containing special characters "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    references to moral dilemma or ethical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighb
    -0.78
     greeting
    -0.76
     nightly
    -0.73
     bundled
    -0.73
    reet
    -0.71
     encomp
    -0.71
     quir
    -0.70
     sculpt
    -0.69
     frontline
    -0.69
     spitting
    -0.68
    POSITIVE LOGITS
    Secondly
    1.56
    Advertisement
    1.51
    Furthermore
    1.50
    Anyway
    1.48
    Conclusion
    1.48
    Therefore
    1.46
    Moreover
    1.46
    CONCLUS
    1.45
    However
    1.43
    Advertisements
    1.43
    Act Density 0.655%

    No Known Activations