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

    Neuronpedia

    INDEX
    Explanations

    expressions of interest or curiosity in various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caw
    -0.58
     Mahl
    -0.55
     machines
    -0.53
     cages
    -0.52
     Goy
    -0.52
     giù
    -0.51
     Machines
    -0.51
     Swain
    -0.51
    máquina
    -0.50
     Malk
    -0.50
    POSITIVE LOGITS
     Interest
    1.14
    Interest
    1.04
     interest
    1.03
    interest
    1.02
     Interests
    0.90
     INTEREST
    0.88
    INTEREST
    0.88
     interests
    0.81
     interested
    0.81
     Interested
    0.81
    Act Density 0.107%

    No Known Activations