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

    Neuronpedia

    INDEX
    Explanations

    terms related to modern technology and tools

    oai_token-act-pair · gpt-3.5-turbo

    topics related to specific events or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dfx
    -0.84
    )."
    -0.67
    illary
    -0.62
    sic
    -0.61
     externalToEVAOnly
    -0.60
    ische
    -0.59
    lich
    -0.59
    flex
    -0.59
     msec
    -0.58
    DERR
    -0.58
    POSITIVE LOGITS
     Us
    0.70
    verages
    0.68
     Again
    0.66
    caster
    0.66
     Levels
    0.62
     Category
    0.61
    ths
    0.61
     âĨij
    0.61
     (?,
    0.58
    earances
    0.58
    Act Density 0.366%

    No Known Activations