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

    Neuronpedia

    INDEX
    Explanations

    sensory-related descriptive language

    oai_token-act-pair · gpt-3.5-turbo

    indicative phrases detailing conditions or situations related to guidance or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONCLUS
    -0.77
     UNCLASSIFIED
    -0.68
    forth
    -0.68
    vati
    -0.67
    Conclusion
    -0.66
    ionage
    -0.65
     unres
    -0.61
    è¦ļéĨĴ
    -0.61
    venge
    -0.60
     externalToEVAOnly
    -0.59
    POSITIVE LOGITS
     frontman
    0.62
     Hockey
    0.61
    neau
    0.61
    actionDate
    0.61
     infographic
    0.60
     Transcript
    0.60
     Nerd
    0.59
    utterstock
    0.59
    eaturing
    0.58
    ategories
    0.58
    Act Density 0.782%

    No Known Activations