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

    Neuronpedia

    INDEX
    Explanations

    terms related to dual configurations or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bfd
    -0.15
    auses
    -0.15
    places
    -0.14
    ToDevice
    -0.14
    legen
    -0.14
    atik
    -0.13
    lenÃŃ
    -0.13
     bì
    -0.13
    ones
    -0.13
    luck
    -0.13
    POSITIVE LOGITS
    -purpose
    0.26
    /tr
    0.25
    /single
    0.22
    -sided
    0.21
    ityEngine
    0.21
    Shock
    0.20
     purpose
    0.20
    ities
    0.19
    Ended
    0.19
     sided
    0.19
    Act Density 0.018%

    No Known Activations