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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unlocking codes and instructions for devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rack
    -0.17
    igr
    -0.16
    vern
    -0.15
    stÃŃ
    -0.15
     Victor
    -0.15
    tember
    -0.15
    rende
    -0.14
    ukkan
    -0.14
    lesia
    -0.14
    kova
    -0.14
    POSITIVE LOGITS
    ynos
    0.16
     Experimental
    0.15
    Experimental
    0.15
     experimental
    0.14
     sidew
    0.14
    elah
    0.14
     Ziel
    0.14
     Adj
    0.14
    uhn
    0.13
    SAFE
    0.13
    Act Density 0.005%

    No Known Activations