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

    Neuronpedia

    INDEX
    Explanations

    text enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses or quotes that indicate citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orate
    -0.67
     RC
    -0.66
     Marble
    -0.63
     Nunes
    -0.62
     Hodg
    -0.60
     Mills
    -0.60
     EVs
    -0.59
     ESV
    -0.59
     TTL
    -0.58
     Kin
    -0.58
    POSITIVE LOGITS
    catentry
    0.97
    wcsstore
    0.84
    pes
    0.77
    onduct
    0.74
    rag
    0.71
    ourage
    0.71
    pine
    0.70
    tnc
    0.69
    iquid
    0.67
    insula
    0.67
    Act Density 0.019%

    No Known Activations