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

    Neuronpedia

    INDEX
    Explanations

    terms related to a specific currency or monetary system

    oai_token-act-pair · gpt-3.5-turbo

    references to currency or coin denominations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.72
     vengeance
    -0.69
    hower
    -0.68
    ĪĴ
    -0.66
     Micha
    -0.62
    gaard
    -0.61
    sbm
    -0.61
     Judicial
    -0.61
     Lisa
    -0.59
    closed
    -0.59
    POSITIVE LOGITS
    itals
    1.24
    ITAL
    1.03
     CAP
    0.96
    prus
    0.96
    CAP
    0.94
    itol
    0.93
    encies
    0.90
    TION
    0.90
    idon
    0.90
    TAIN
    0.88
    Act Density 0.003%

    No Known Activations