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

    Neuronpedia

    INDEX
    Explanations

    references to trade or trade secrets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ering
    -0.18
    er
    -0.17
    ERING
    -0.16
    obel
    -0.15
    ly
    -0.15
    zet
    -0.15
    erator
    -0.15
    la
    -0.15
    theless
    -0.15
    ness
    -0.14
    POSITIVE LOGITS
    offs
    0.29
     trade
    0.27
    -trade
    0.23
     Trade
    0.23
    MARK
    0.22
     secrets
    0.21
    -offs
    0.21
     union
    0.21
    trade
    0.20
     Winds
    0.20
    Act Density 0.010%

    No Known Activations