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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in digits

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and identifiers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    archive
    -0.71
    ocracy
    -0.64
    ocrats
    -0.62
     liqu
    -0.59
    909
    -0.57
    craft
    -0.56
    resses
    -0.54
     Fug
    -0.54
    ãĥķãĤ©
    -0.54
     Faul
    -0.54
    POSITIVE LOGITS
     externalToEVAOnly
    0.80
    âĢ²
    0.76
    verages
    0.73
    âĢ³
    0.71
    mAh
    0.66
    th
    0.64
    +)
    0.62
    AIN
    0.62
    pun
    0.59
     Specifications
    0.59
    Act Density 0.151%

    No Known Activations