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

    Neuronpedia

    INDEX
    Explanations

    references to humanity and its condition or impact on the world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewe
    -0.15
    /autoload
    -0.14
    insky
    -0.14
    olan
    -0.14
    ster
    -0.14
    olv
    -0.14
    uff
    -0.13
    oints
    -0.13
    elsius
    -0.13
     Gund
    -0.13
    POSITIVE LOGITS
    zcze
    0.17
    /world
    0.17
    istrat
    0.16
     erotique
    0.16
     Hin
    0.15
    ARRIER
    0.15
    ispecies
    0.14
    ReuseIdentifier
    0.14
    reau
    0.14
    vale
    0.14
    Act Density 0.010%

    No Known Activations