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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts in the millions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of monetary values or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resting
    -0.74
     orient
    -0.66
     Destination
    -0.66
     dwelling
    -0.64
     resp
    -0.63
     Fa
    -0.63
     kingdom
    -0.62
     Ars
    -0.61
    itives
    -0.61
     refuge
    -0.59
    POSITIVE LOGITS
    MM
    3.54
    MG
    1.32
    CM
    1.25
    MK
    1.17
    RS
    1.16
    MC
    1.15
    ME
    1.11
    mm
    1.11
    ML
    1.10
    HH
    1.10
    Act Density 0.014%

    No Known Activations