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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "dual" followed by a numerical value and possibly a hyphenated descriptor

    oai_token-act-pair · gpt-3.5-turbo

    references to dual systems or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORE
    -0.82
    Dialogue
    -0.70
    orio
    -0.69
     Warehouse
    -0.68
    ################
    -0.68
    UFF
    -0.67
    inventoryQuantity
    -0.65
    ONEY
    -0.65
     Lans
    -0.65
    aceae
    -0.64
    POSITIVE LOGITS
    ples
    0.94
    ity
    0.88
    fold
    0.88
    ities
    0.85
     sided
    0.84
     wielding
    0.82
    xes
    0.81
    tone
    0.79
     elig
    0.77
    handedly
    0.76
    Act Density 0.021%

    No Known Activations